commit fd4c3c2fc7ecc18e1f0e234c229377854f616e0e Author: spaceman1412 Date: Thu Feb 26 15:16:32 2026 +0700 Add new skills and utilities for enhanced writing and testing - Introduced graphviz conventions for visualizing process flows in writing skills. - Added a comprehensive guide on persuasion principles to improve skill design effectiveness. - Implemented a script to render graphviz diagrams from markdown files to SVG format. - Created a detailed reference for testing skills with subagents, emphasizing TDD principles. - Established a task tracker template for live task management. - Developed a shell script to check the integrity of the antigravity profile and required files. - Added test scripts to validate the initialization of agent projects. - Created workflows for brainstorming, executing plans, and writing plans to streamline processes. diff --git a/ANTIGRAVITY-PORT-DIFFERENCES.md b/ANTIGRAVITY-PORT-DIFFERENCES.md new file mode 100644 index 0000000..ebeed50 --- /dev/null +++ b/ANTIGRAVITY-PORT-DIFFERENCES.md @@ -0,0 +1,120 @@ +# Antigravity Port Differences vs Original Superpowers + +This document lists the current differences between: + +- Original skill set: `skills/` +- Antigravity port: `templates/.agent/skills/` (+ Antigravity profile docs/tests) + +## 1) High-Level Delta + +- Skill count changed from **14** (original) to **13** (port). +- Port keeps 12 original skill names, removes 2, and adds: + - `single-flow-task-execution` (new Antigravity-only execution skill, consolidates content from the removed `dispatching-parallel-agents` and `subagent-driven-development`) +- Removed skills: + - `dispatching-parallel-agents` — decomposition pattern merged into `single-flow-task-execution` + - `subagent-driven-development` — two-stage review loop merged into `single-flow-task-execution` +- Core model changed from generic subagent/parallel coding to **single-flow task execution**. +- Generic coding subagent usage is replaced with: + - `task_boundary` for coding tasks + - `browser_subagent` only for browser automation +- Legacy platform/tool vocabulary was translated to Antigravity equivalents: + - `Claude/Claude Code` -> `Antigravity` + - `Skill tool` -> `view_file` + - `TodoWrite` -> update `/docs/plans/task.md` + - `superpowers:` references -> local `.agent/skills/.../SKILL.md` + +## 2) Task Tracking Model Differences + +- Original skills used `TodoWrite` semantics. +- Port uses project runtime file: `/docs/plans/task.md`. +- Port includes `.agent/task.md` as a **template/instruction reference** only. +- Live tracker requirements in the port: + - lives at project root `docs/plans/task.md` + - table-only tracker (no prose/instructions) + - not packaged as `templates/.agent/docs/plans/task.md` + +## 3) Skill-by-Skill Differences + +## Major Behavioral Rewrites + +- `single-flow-task-execution` (NEW — consolidated from 3 sources) + - Merges content from original `dispatching-parallel-agents` (task decomposition + queuing) and `subagent-driven-development` (two-stage review loop). + - Strict single-flow execution with `task_boundary`, review gates retained. + - Progress tracking via `/docs/plans/task.md`. + - Review prompt templates (`implementer-prompt.md`, `spec-reviewer-prompt.md`, `code-quality-reviewer-prompt.md`) moved into this skill directory. + +- `requesting-code-review` + - Original: dispatches `superpowers:code-reviewer` subagent. + - Port: checklist-based structured review flow (no generic coding subagent dispatch). + - Integration text updated to single-flow wording. + +- `writing-plans` + - Original handoff: subagent-driven vs parallel-session via `superpowers:*`. + - Port handoff: `single-flow-task-execution` vs `.agent/skills/executing-plans/SKILL.md`. + - Plan header updated for Antigravity-required execution skill path. + +- `executing-plans` + - Original: creates/uses `TodoWrite`; integrates with `superpowers:*` skills. + - Port: updates `/docs/plans/task.md` and uses local `.agent/skills` references. + - Adds explicit `task_boundary`/`browser_subagent` execution rule. + +## Targeted Adaptations (Not Full Rewrites) + +- `using-superpowers` + - Skill loading switched to `view_file`. + - Checklist tracking switched to project-root `docs/plans/task.md`. + - Adds explicit instruction to create tracker file if missing (table-only format). + +- `writing-skills` + - Platform references and personal skill paths changed to Antigravity style. + - Required background references changed from `superpowers:*` to local `.agent/skills` paths. + - Checklist tracking text updated to project-root table-only tracker. + +- `systematic-debugging` + - Related skill references changed from `superpowers:*` to local `.agent/skills/...`. + - Support creation log path references normalized away from Claude-specific location. + +- `using-git-worktrees` + - Directory preference source changed from `CLAUDE.md` to `.agent/AGENTS.md`. + +- `receiving-code-review` + - Style violation example changed from `CLAUDE.md` violation to `.agent/AGENTS.md` violation. + +- `writing-skills/persuasion-principles.md` + - `TodoWrite` examples updated to `/docs/plans/task.md` tracking wording. + +## Mostly Preserved Skills (Behavior Intact, Terminology/Path Normalization) + +- `brainstorming` +- `test-driven-development` +- `verification-before-completion` +- `finishing-a-development-branch` + +These keep the original core process intent, with Antigravity naming/path normalization where needed. + +## 4) Renamed Supporting Files in `writing-skills` + +- `anthropic-best-practices.md` -> `antigravity-best-practices.md` +- `examples/CLAUDE_MD_TESTING.md` -> `examples/AGENTS_MD_TESTING.md` + +## 5) Antigravity-Only Profile Files Added + +Compared to original `skills/`-only set, the port adds profile scaffolding: + +- `.agent/AGENTS.md` (tool translation + execution contract) +- `.agent/INSTALL.md` (installation for target projects) +- `.agent/task.md` (template/reference) +- `.agent/tests/check-antigravity-profile.sh` +- `.agent/tests/run-tests.sh` +- `README.md` +- `CURRENT-FLOW.md` + +## 6) Validation/Guardrail Differences + +The Antigravity port adds automated profile checks that the original skill library does not include: + +- Required skill/doc presence checks +- Frontmatter validation (`name`, `description`) +- Legacy-instruction pattern detection (e.g., old `superpowers:`/Task tool phrasing) +- AGENTS mapping contract checks +- Guard that packaged runtime tracker (`templates/.agent/docs/plans/task.md`) is absent diff --git a/CURRENT-FLOW.md b/CURRENT-FLOW.md new file mode 100644 index 0000000..cae8981 --- /dev/null +++ b/CURRENT-FLOW.md @@ -0,0 +1,108 @@ +# Antigravity Superpowers Current Flow + +This document explains the active workflow used by the Antigravity profile in this folder. + +## 1) Session Start + +1. Load rules from `.agent/AGENTS.md`. +2. Load `.agent/skills/using-superpowers/SKILL.md`. +3. Before any action, check whether a relevant skill should be loaded from: + - `.agent/skills//SKILL.md` (preferred) + - `~/.gemini/skills//SKILL.md` (fallback) +4. Ensure `/docs/plans/task.md` exists as a list-only table (no instructions). + +## 2) Skill-First Routing + +For each user request: + +1. Identify the best matching skill. +2. Announce and follow that skill. +3. If the skill has a checklist, track progress in `/docs/plans/task.md`. + +## 3) Design Before Implementation + +If the request involves creating/changing behavior: + +1. Run `brainstorming`. +2. Explore context and ask clarifying questions. +3. Propose approaches and get approval. +4. Write design doc to `docs/plans/YYYY-MM-DD--design.md`. +5. Move to `writing-plans`. + +## 4) Planning Stage + +`writing-plans` creates a detailed implementation plan: + +1. Save plan to `docs/plans/YYYY-MM-DD-.md`. +2. Break work into small, verifiable steps. +3. Include exact files, commands, and expected outputs. +4. Handoff to execution via `.agent/workflows/execute-plan.md` (single entrypoint). +5. The workflow loads `executing-plans`, which enforces `single-flow-task-execution` rules. + +## 5) Execution Model (Single-Flow) + +Core execution rules from `.agent/AGENTS.md` and `single-flow-task-execution`: + +1. One active task at a time. +2. One coding execution thread at a time. +3. Use `task_boundary` for coding tasks. +4. Use `browser_subagent` only for browser-specific tasks. +5. Update `/docs/plans/task.md` on every task state change. + +Per-task loop: + +1. Mark task `in_progress`. +2. Implement scoped change. +3. Run verification commands. +4. Fix and re-run until passing. +5. Mark task `done` with notes. + +## 6) Verification Gate + +Before any completion claim (`verification-before-completion`): + +1. Identify the command that proves the claim. +2. Run it now (fresh). +3. Read full output and exit code. +4. Report evidence. +5. Only then claim completion. + +## 7) Finish Branch + +After all tasks are complete and verified (`finishing-a-development-branch`): + +1. Re-run required tests. +2. Present workflow options (merge, PR, keep branch, discard). +3. Execute selected option safely. +4. Require explicit confirmation for destructive actions. + +## 8) Profile Validation Flow + +Validate this profile itself with: + +```bash +bash templates/.agent/tests/run-tests.sh +``` + +`run-tests.sh` calls `check-antigravity-profile.sh`, which verifies: + +- Required files exist +- Skill frontmatter is valid +- Legacy patterns are removed +- AGENTS mapping contract is present + +## Flow Diagram + +```mermaid +flowchart TD +sessionStart[Session start] --> useSkill[Load using-superpowers] +useSkill --> routeSkill[Select and load relevant skill] +routeSkill --> designGate{Behavior/design change?} +designGate -->|yes| brainstorming[Brainstorming] +brainstorming --> writingPlans[Writing plans] +designGate -->|no| execution[Single-flow execution] +writingPlans --> execution +execution --> verify[Verification before completion] +verify --> finish[Finish development branch] +finish --> done[Done] +``` diff --git a/README.md b/README.md new file mode 100644 index 0000000..456a123 --- /dev/null +++ b/README.md @@ -0,0 +1,48 @@ +# antigravity-superpowers + +CLI for initializing the Antigravity Superpowers profile in any project. + +## What `init` does + +- Copies bundled profile files into `/.agent` +- Fails safely if `.agent` already exists +- Supports `--force` to replace existing `.agent` + +The CLI does **not** create `docs/plans/task.md`. That live tracker is created at runtime by skill flow. + +## Usage + +```bash +antigravity-superpowers init +``` + +```bash +antigravity-superpowers init /path/to/project +``` + +```bash +antigravity-superpowers init --force +``` + +## Local Development + +From the package directory: + +```bash +npm test +npm run smoke:pack +``` + +## Publish Workflow + +The release flow is manual by design. + +```bash +npm version patch +npm publish +``` + +`prepublishOnly` automatically runs: + +1. `npm test` +2. `npm run smoke:pack` diff --git a/bin/antigravity-superpowers.js b/bin/antigravity-superpowers.js new file mode 100755 index 0000000..f51025a --- /dev/null +++ b/bin/antigravity-superpowers.js @@ -0,0 +1,13 @@ +#!/usr/bin/env node + +import { runCli } from "../src/cli.js"; + +runCli(process.argv.slice(2)) + .then((exitCode) => { + process.exitCode = exitCode; + }) + .catch((error) => { + const message = error instanceof Error ? error.message : String(error); + process.stderr.write(`${message}\n`); + process.exitCode = 1; + }); diff --git a/package-lock.json b/package-lock.json new file mode 100644 index 0000000..114f84a --- /dev/null +++ b/package-lock.json @@ -0,0 +1,19 @@ +{ + "name": "antigravity-superpowers", + "version": "0.1.0", + "lockfileVersion": 3, + "requires": true, + "packages": { + "": { + "name": "antigravity-superpowers", + "version": "0.1.0", + "license": "MIT", + "bin": { + "antigravity-superpowers": "bin/antigravity-superpowers.js" + }, + "engines": { + "node": ">=20.0.0" + } + } + } +} diff --git a/package.json b/package.json new file mode 100644 index 0000000..5bc5cd9 --- /dev/null +++ b/package.json @@ -0,0 +1,29 @@ +{ + "name": "antigravity-superpowers", + "version": "0.1.0", + "description": "CLI to initialize the Antigravity Superpowers .agent profile", + "type": "module", + "bin": { + "antigravity-superpowers": "bin/antigravity-superpowers.js" + }, + "files": [ + "bin/", + "src/", + "templates/.agent/**", + "README.md" + ], + "scripts": { + "test": "node --test tests", + "smoke:pack": "node scripts/check-pack.mjs", + "prepublishOnly": "npm test && npm run smoke:pack" + }, + "keywords": [ + "antigravity", + "superpowers", + "cli" + ], + "license": "MIT", + "engines": { + "node": ">=20.0.0" + } +} diff --git a/scripts/check-pack.mjs b/scripts/check-pack.mjs new file mode 100644 index 0000000..e6601b2 --- /dev/null +++ b/scripts/check-pack.mjs @@ -0,0 +1,53 @@ +import { execFileSync } from "node:child_process"; +import { rm } from "node:fs/promises"; +import { resolve } from "node:path"; + +const raw = execFileSync("npm", ["pack", "--json"], { + cwd: process.cwd(), + encoding: "utf8", +}); +const packResult = JSON.parse(raw); + +if (!Array.isArray(packResult) || packResult.length === 0) { + throw new Error("npm pack did not return package metadata"); +} + +const [{ filename, files }] = packResult; +if (!filename || !Array.isArray(files)) { + throw new Error("npm pack output is missing filename or files"); +} + +const packagedPaths = new Set(files.map((file) => file.path)); +const required = [ + "bin/antigravity-superpowers.js", + "src/cli.js", + "src/commands/init.js", + "templates/.agent/AGENTS.md", + "templates/.agent/INSTALL.md", + "templates/.agent/task.md", + "templates/.agent/workflows/brainstorm.md", + "templates/.agent/workflows/write-plan.md", + "templates/.agent/workflows/execute-plan.md", + "templates/.agent/agents/code-reviewer.md", + "templates/.agent/tests/run-tests.sh", + "templates/.agent/tests/check-antigravity-profile.sh", + "templates/.agent/skills/single-flow-task-execution/SKILL.md", + "templates/.agent/skills/single-flow-task-execution/implementer-prompt.md", + "templates/.agent/skills/single-flow-task-execution/spec-reviewer-prompt.md", + "templates/.agent/skills/single-flow-task-execution/code-quality-reviewer-prompt.md", + "templates/.agent/skills/executing-plans/SKILL.md", + "templates/.agent/skills/verification-before-completion/SKILL.md", + "templates/.agent/skills/writing-plans/SKILL.md", + "templates/.agent/skills/test-driven-development/SKILL.md", +]; + +const missing = required.filter((path) => !packagedPaths.has(path)); +if (missing.length > 0) { + throw new Error( + `Packaged tarball is missing required files: ${missing.join(", ")}`, + ); +} + +await rm(resolve(process.cwd(), filename), { force: true }); + +process.stdout.write("Pack smoke check passed.\n"); diff --git a/src/cli.js b/src/cli.js new file mode 100644 index 0000000..e19abbf --- /dev/null +++ b/src/cli.js @@ -0,0 +1,37 @@ +import { initCommand } from "./commands/init.js"; + +function helpText() { + return [ + "antigravity-superpowers", + "", + "Usage:", + " antigravity-superpowers init [target-directory] [--force]", + "", + "Commands:", + " init Initialize .agent profile in a project", + "", + "Options:", + " -f, --force Overwrite existing .agent directory", + " -h, --help Show help", + ].join("\n"); +} + +export async function runCli(args, io = process) { + const [command, ...rest] = args; + + if (!command || command === "-h" || command === "--help" || command === "help") { + io.stdout.write(`${helpText()}\n`); + return 0; + } + + if (command === "init") { + return initCommand(rest, { + cwd: io.cwd?.() ?? process.cwd(), + stdout: io.stdout, + stderr: io.stderr, + }); + } + + io.stderr.write(`Unknown command: ${command}\n\n${helpText()}\n`); + return 1; +} diff --git a/src/commands/init.js b/src/commands/init.js new file mode 100644 index 0000000..1009979 --- /dev/null +++ b/src/commands/init.js @@ -0,0 +1,109 @@ +import { access, cp, rm, stat } from "node:fs/promises"; +import { constants as fsConstants } from "node:fs"; +import { fileURLToPath } from "node:url"; +import { join, resolve } from "node:path"; + +function getTemplateDir() { + return fileURLToPath(new URL("../../templates/.agent", import.meta.url)); +} + +async function exists(path) { + try { + await access(path, fsConstants.F_OK); + return true; + } catch { + return false; + } +} + +function parseInitArgs(args) { + const parsed = { + target: ".", + force: false, + }; + let targetSet = false; + + for (const arg of args) { + if (arg === "--force" || arg === "-f") { + parsed.force = true; + continue; + } + + if (arg.startsWith("-")) { + throw new Error(`Unknown option for init: ${arg}`); + } + + if (targetSet) { + throw new Error("Too many positional arguments. Only one target directory is supported."); + } + + parsed.target = arg; + targetSet = true; + } + + return parsed; +} + +async function validateTargetDir(targetDir) { + let targetStat; + try { + targetStat = await stat(targetDir); + } catch { + throw new Error(`Target directory does not exist: ${targetDir}`); + } + + if (!targetStat.isDirectory()) { + throw new Error(`Target path is not a directory: ${targetDir}`); + } +} + +export async function initCommand(args, { cwd, stdout, stderr }) { + let parsed; + try { + parsed = parseInitArgs(args); + } catch (error) { + const message = error instanceof Error ? error.message : String(error); + stderr.write(`${message}\n`); + return 1; + } + + const targetDir = resolve(cwd, parsed.target); + const agentDir = join(targetDir, ".agent"); + const templateDir = getTemplateDir(); + + try { + await validateTargetDir(targetDir); + + const templateExists = await exists(templateDir); + if (!templateExists) { + throw new Error( + "Bundled template is missing. Run `npm run sync:template` before using init from source.", + ); + } + + const agentExists = await exists(agentDir); + if (agentExists && !parsed.force) { + stderr.write( + `.agent already exists at ${agentDir}. Re-run with --force to replace it.\n`, + ); + return 1; + } + + if (agentExists && parsed.force) { + await rm(agentDir, { recursive: true, force: true }); + } + + await cp(templateDir, agentDir, { recursive: true }); + + stdout.write(`Initialized Antigravity Superpowers profile at ${agentDir}\n`); + stdout.write("Next step: bash .agent/tests/run-tests.sh\n"); + stdout.write( + "Note: docs/plans/task.md is created at runtime by skills when task tracking starts.\n", + ); + return 0; + } catch (error) { + const message = error instanceof Error ? error.message : String(error); + stderr.write(`Init failed: ${message}\n`); + return 1; + } +} diff --git a/templates/.agent/AGENTS.md b/templates/.agent/AGENTS.md new file mode 100644 index 0000000..dde6d08 --- /dev/null +++ b/templates/.agent/AGENTS.md @@ -0,0 +1,56 @@ +# Superpowers for Antigravity + +You have superpowers. + +This profile adapts Superpowers workflows for Antigravity with strict single-flow execution. + +## Core Rules + +1. Prefer local skills in `.agent/skills//SKILL.md`. +2. Execute one core task at a time with `task_boundary`. +3. Use `browser_subagent` only for browser automation tasks. +4. Track checklist progress in `/docs/plans/task.md` (table-only live tracker). +5. Keep changes scoped to the requested task and verify before completion claims. + +## Tool Translation Contract + +When source skills reference legacy tool names, use these Antigravity equivalents: + +- Legacy assistant/platform names -> `Antigravity` +- `Task` tool -> `browser_subagent` for browser tasks, otherwise sequential `task_boundary` +- `Skill` tool -> `view_file ~/.gemini/skills//SKILL.md` (or project-local `.agent/skills//SKILL.md`) +- `TodoWrite` -> update `/docs/plans/task.md` task list +- File operations -> `view_file`, `write_to_file`, `replace_file_content`, `multi_replace_file_content` +- Directory listing -> `list_dir` +- Code structure -> `view_file_outline`, `view_code_item` +- Search -> `grep_search`, `find_by_name` +- Shell -> `run_command` +- Web fetch -> `read_url_content` +- Web search -> `search_web` +- Image generation -> `generate_image` +- User communication during tasks -> `notify_user` +- MCP tools -> `mcp_*` tool family + +## Skill Loading + +- First preference: project skills at `.agent/skills`. +- Second preference: user skills at `~/.gemini/skills`. +- If both exist, project-local skills win for this profile. +- Optional parity assets may exist at `.agent/workflows/*` and `.agent/agents/*` as entrypoint shims/reference profiles. +- These assets do not change the strict single-flow execution requirements in this file. + +## Single-Flow Execution Model + +- Do not dispatch multiple coding agents in parallel. +- Decompose large work into ordered, explicit steps. +- Keep exactly one active task at a time in `/docs/plans/task.md`. +- If browser work is required, isolate it in a dedicated browser step. + +## Verification Discipline + +Before saying a task is done: + +1. Run the relevant verification command(s). +2. Confirm exit status and key output. +3. Update `/docs/plans/task.md`. +4. Report evidence, then claim completion. diff --git a/templates/.agent/INSTALL.md b/templates/.agent/INSTALL.md new file mode 100644 index 0000000..02fc459 --- /dev/null +++ b/templates/.agent/INSTALL.md @@ -0,0 +1,64 @@ +# Install Antigravity Superpowers Profile + +This package is a standalone Antigravity profile. It does not modify the original Superpowers source workflows. + +## Prerequisites + +- Antigravity environment installed +- Shell access +- This repository available locally + +## Install + +From your project root: + +```bash +npx antigravity-superpowers init +``` + +Or manually: + +```bash +mkdir -p .agent +cp -R /path/to/antigravity-superpowers-cli/templates/.agent/* .agent/ +``` + +If your project already has `.agent/skills`, merge carefully and keep the versions you want. + +## What Gets Installed + +- `.agent/AGENTS.md` +- `.agent/task.md` (template only) +- `.agent/skills/*` +- `.agent/workflows/*` +- `.agent/agents/*` +- `.agent/tests/*` + +Runtime tracking file: + +- `docs/plans/task.md` in the target project root (created at runtime by skill flow, list-only table) + +## Verify Profile + +From your target project root: + +```bash +bash .agent/tests/run-tests.sh +``` + +Expected result: all checks pass with zero failures. + +## Usage Notes + +- This profile uses strict single-flow task execution. +- Generic coding subagents are intentionally not used. +- Browser automation can use `browser_subagent` when needed. +- Skill references are local to `.agent/skills`. + +## Update + +Re-run the CLI init with `--force` to update, then rerun validation: + +```bash +bash .agent/tests/run-tests.sh +``` diff --git a/templates/.agent/agents/code-reviewer.md b/templates/.agent/agents/code-reviewer.md new file mode 100644 index 0000000..4e14076 --- /dev/null +++ b/templates/.agent/agents/code-reviewer.md @@ -0,0 +1,48 @@ +--- +name: code-reviewer +description: | + Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Great work! Now let me use the code-reviewer agent to review the implementation against our plan and coding standards" Since a major project step has been completed, use the code-reviewer agent to validate the work against the plan and identify any issues. Context: User has completed a significant feature implementation. user: "The API endpoints for the task management system are now complete - that covers step 2 from our architecture document" assistant: "Excellent! Let me have the code-reviewer agent examine this implementation to ensure it aligns with our plan and follows best practices" A numbered step from the planning document has been completed, so the code-reviewer agent should review the work. +model: inherit +--- + +You are a Senior Code Reviewer with expertise in software architecture, design patterns, and best practices. Your role is to review completed project steps against original plans and ensure code quality standards are met. + +When reviewing completed work, you will: + +1. **Plan Alignment Analysis**: + - Compare the implementation against the original planning document or step description + - Identify any deviations from the planned approach, architecture, or requirements + - Assess whether deviations are justified improvements or problematic departures + - Verify that all planned functionality has been implemented + +2. **Code Quality Assessment**: + - Review code for adherence to established patterns and conventions + - Check for proper error handling, type safety, and defensive programming + - Evaluate code organization, naming conventions, and maintainability + - Assess test coverage and quality of test implementations + - Look for potential security vulnerabilities or performance issues + +3. **Architecture and Design Review**: + - Ensure the implementation follows SOLID principles and established architectural patterns + - Check for proper separation of concerns and loose coupling + - Verify that the code integrates well with existing systems + - Assess scalability and extensibility considerations + +4. **Documentation and Standards**: + - Verify that code includes appropriate comments and documentation + - Check that file headers, function documentation, and inline comments are present and accurate + - Ensure adherence to project-specific coding standards and conventions + +5. **Issue Identification and Recommendations**: + - Clearly categorize issues as: Critical (must fix), Important (should fix), or Suggestions (nice to have) + - For each issue, provide specific examples and actionable recommendations + - When you identify plan deviations, explain whether they're problematic or beneficial + - Suggest specific improvements with code examples when helpful + +6. **Communication Protocol**: + - If you find significant deviations from the plan, ask the coding agent to review and confirm the changes + - If you identify issues with the original plan itself, recommend plan updates + - For implementation problems, provide clear guidance on fixes needed + - Always acknowledge what was done well before highlighting issues + +Your output should be structured, actionable, and focused on helping maintain high code quality while ensuring project goals are met. Be thorough but concise, and always provide constructive feedback that helps improve both the current implementation and future development practices. diff --git a/templates/.agent/skills/brainstorming/SKILL.md b/templates/.agent/skills/brainstorming/SKILL.md new file mode 100644 index 0000000..460f73a --- /dev/null +++ b/templates/.agent/skills/brainstorming/SKILL.md @@ -0,0 +1,96 @@ +--- +name: brainstorming +description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation." +--- + +# Brainstorming Ideas Into Designs + +## Overview + +Help turn ideas into fully formed designs and specs through natural collaborative dialogue. + +Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval. + + +Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity. + + +## Anti-Pattern: "This Is Too Simple To Need A Design" + +Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval. + +## Checklist + +You MUST create a task for each of these items and complete them in order: + +1. **Explore project context** — check files, docs, recent commits +2. **Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria +3. **Propose 2-3 approaches** — with trade-offs and your recommendation +4. **Present design** — in sections scaled to their complexity, get user approval after each section +5. **Write design doc** — save to `docs/plans/YYYY-MM-DD--design.md` and commit +6. **Transition to implementation** — invoke writing-plans skill to create implementation plan + +## Process Flow + +```dot +digraph brainstorming { + "Explore project context" [shape=box]; + "Ask clarifying questions" [shape=box]; + "Propose 2-3 approaches" [shape=box]; + "Present design sections" [shape=box]; + "User approves design?" [shape=diamond]; + "Write design doc" [shape=box]; + "Invoke writing-plans skill" [shape=doublecircle]; + + "Explore project context" -> "Ask clarifying questions"; + "Ask clarifying questions" -> "Propose 2-3 approaches"; + "Propose 2-3 approaches" -> "Present design sections"; + "Present design sections" -> "User approves design?"; + "User approves design?" -> "Present design sections" [label="no, revise"]; + "User approves design?" -> "Write design doc" [label="yes"]; + "Write design doc" -> "Invoke writing-plans skill"; +} +``` + +**The terminal state is invoking writing-plans.** Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans. + +## The Process + +**Understanding the idea:** +- Check out the current project state first (files, docs, recent commits) +- Ask questions one at a time to refine the idea +- Prefer multiple choice questions when possible, but open-ended is fine too +- Only one question per message - if a topic needs more exploration, break it into multiple questions +- Focus on understanding: purpose, constraints, success criteria + +**Exploring approaches:** +- Propose 2-3 different approaches with trade-offs +- Present options conversationally with your recommendation and reasoning +- Lead with your recommended option and explain why + +**Presenting the design:** +- Once you believe you understand what you're building, present the design +- Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced +- Ask after each section whether it looks right so far +- Cover: architecture, components, data flow, error handling, testing +- Be ready to go back and clarify if something doesn't make sense + +## After the Design + +**Documentation:** +- Write the validated design to `docs/plans/YYYY-MM-DD--design.md` +- Use elements-of-style:writing-clearly-and-concisely skill if available +- Commit the design document to git + +**Implementation:** +- Invoke the writing-plans skill to create a detailed implementation plan +- Do NOT invoke any other skill. writing-plans is the next step. + +## Key Principles + +- **One question at a time** - Don't overwhelm with multiple questions +- **Multiple choice preferred** - Easier to answer than open-ended when possible +- **YAGNI ruthlessly** - Remove unnecessary features from all designs +- **Explore alternatives** - Always propose 2-3 approaches before settling +- **Incremental validation** - Present design, get approval before moving on +- **Be flexible** - Go back and clarify when something doesn't make sense diff --git a/templates/.agent/skills/executing-plans/SKILL.md b/templates/.agent/skills/executing-plans/SKILL.md new file mode 100644 index 0000000..97a471b --- /dev/null +++ b/templates/.agent/skills/executing-plans/SKILL.md @@ -0,0 +1,100 @@ +--- +name: executing-plans +description: Use when you have a written implementation plan and need to execute it in Antigravity single-flow mode +--- + +# Executing Plans + +## Overview + +Load plan, review critically, execute tasks in batches, report for review between batches. + +**Core principle:** Batch execution with checkpoints for architect review. +**Entrypoint principle:** This is the standard execution entrypoint. Do not offer alternate execution modes. + +**Announce at start:** "I'm using the executing-plans skill to implement this plan." + +## The Process + +### Step 1: Load and Review Plan + +1. Read plan file +2. Review critically - identify any questions or concerns about the plan +3. If concerns: Raise them with your human partner before starting +4. If no concerns: follow the single-flow execution model from `.agent/skills/single-flow-task-execution/SKILL.md` +5. Update `/docs/plans/task.md` (table-only tracker) and proceed + +### Step 2: Execute Batch + +**Default: First 3 tasks** + +For each task: + +1. Mark as in_progress +2. Follow each step exactly (plan has bite-sized steps) +3. Run verifications as specified +4. Mark as completed + +### Step 3: Report + +When batch complete: + +- Show what was implemented +- Show verification output +- Say: "Ready for feedback." + +### Step 4: Continue + +Based on feedback: + +- Apply changes if needed +- Execute next batch +- Repeat until complete + +### Step 5: Complete Development + +After all tasks complete and verified: + +- Announce: "I'm using the finishing-a-development-branch skill to complete this work." +- **REQUIRED SKILL:** Use `.agent/skills/finishing-a-development-branch/SKILL.md` +- Follow that skill to verify tests, present options, execute choice + +## When to Stop and Ask for Help + +**STOP executing immediately when:** + +- Hit a blocker mid-batch (missing dependency, test fails, instruction unclear) +- Plan has critical gaps preventing starting +- You don't understand an instruction +- Verification fails repeatedly + +**Ask for clarification rather than guessing.** + +## When to Revisit Earlier Steps + +**Return to Review (Step 1) when:** + +- Partner updates the plan based on your feedback +- Fundamental approach needs rethinking + +**Don't force through blockers** - stop and ask. + +## Remember + +- Review plan critically first +- Follow plan steps exactly +- Don't skip verifications +- Reference skills when plan says to +- Between batches: just report and wait +- Stop when blocked, don't guess +- Never start implementation on main/master branch without explicit user consent +- Use `task_boundary` for coding tasks; use `browser_subagent` only for browser tasks + +## Integration + +**Required workflow skills:** + +- **`.agent/skills/using-git-worktrees/SKILL.md`** - REQUIRED: Set up isolated workspace before starting +- **`.agent/skills/writing-plans/SKILL.md`** - Creates the plan this skill executes +- **`.agent/skills/single-flow-task-execution/SKILL.md`** - REQUIRED: Enforce single-flow execution with two-stage review +- **`.agent/skills/finishing-a-development-branch/SKILL.md`** - Complete development after all tasks diff --git a/templates/.agent/skills/finishing-a-development-branch/SKILL.md b/templates/.agent/skills/finishing-a-development-branch/SKILL.md new file mode 100644 index 0000000..9d6b363 --- /dev/null +++ b/templates/.agent/skills/finishing-a-development-branch/SKILL.md @@ -0,0 +1,213 @@ +--- +name: finishing-a-development-branch +description: Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup +--- + +# Finishing a Development Branch + +## Overview + +Guide completion of development work by presenting clear options and handling chosen workflow. + +**Core principle:** Verify tests → Present options → Execute choice → Clean up. + +**Announce at start:** "I'm using the finishing-a-development-branch skill to complete this work." + +## The Process + +### Step 1: Verify Tests + +**Before presenting options, verify tests pass:** + +```bash +# Run project's test suite +npm test / cargo test / pytest / go test ./... +``` + +**If tests fail:** + +``` +Tests failing ( failures). Must fix before completing: + +[Show failures] + +Cannot proceed with merge/PR until tests pass. +``` + +Stop. Don't proceed to Step 2. + +**If tests pass:** Continue to Step 2. + +### Step 2: Determine Base Branch + +```bash +# Try common base branches +git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null +``` + +Or ask: "This branch split from main - is that correct?" + +### Step 3: Present Options + +Present exactly these 4 options: + +``` +Implementation complete. What would you like to do? + +1. Merge back to locally +2. Push and create a Pull Request +3. Keep the branch as-is (I'll handle it later) +4. Discard this work + +Which option? +``` + +**Don't add explanation** - keep options concise. + +### Step 4: Execute Choice + +#### Option 1: Merge Locally + +```bash +# Switch to base branch +git checkout + +# Pull latest +git pull + +# Merge feature branch +git merge + +# Verify tests on merged result + + +# If tests pass +git branch -d +``` + +Then: Cleanup worktree (Step 5) + +#### Option 2: Push and Create PR + +```bash +# Push branch +git push -u origin + +# Create PR +gh pr create --title "" --body "$(cat <<'EOF' +## Summary +<2-3 bullets of what changed> + +## Test Plan +- [ ] <verification steps> +EOF +)" +``` + +Then: Cleanup worktree (Step 5) + +#### Option 3: Keep As-Is + +Report: "Keeping branch <name>. Worktree preserved at <path>." + +**Don't cleanup worktree.** + +#### Option 4: Discard + +**Confirm first:** + +``` +This will permanently delete: +- Branch <name> +- All commits: <commit-list> +- Worktree at <path> + +Type 'discard' to confirm. +``` + +Wait for exact confirmation. + +If confirmed: + +```bash +git checkout <base-branch> +git branch -D <feature-branch> +``` + +Then: Cleanup worktree (Step 5) + +### Step 5: Cleanup Worktree + +**For Options 1, 2, 4:** + +Check if in worktree: + +```bash +git worktree list | grep $(git branch --show-current) +``` + +If yes: + +```bash +git worktree remove <worktree-path> +``` + +**For Option 3:** Keep worktree. + +## Quick Reference + +| Option | Merge | Push | Keep Worktree | Cleanup Branch | +| ---------------- | ----- | ---- | ------------- | -------------- | +| 1. Merge locally | ✓ | - | - | ✓ | +| 2. Create PR | - | ✓ | ✓ | - | +| 3. Keep as-is | - | - | ✓ | - | +| 4. Discard | - | - | - | ✓ (force) | + +## Common Mistakes + +**Skipping test verification** + +- **Problem:** Merge broken code, create failing PR +- **Fix:** Always verify tests before offering options + +**Open-ended questions** + +- **Problem:** "What should I do next?" → ambiguous +- **Fix:** Present exactly 4 structured options + +**Automatic worktree cleanup** + +- **Problem:** Remove worktree when might need it (Option 2, 3) +- **Fix:** Only cleanup for Options 1 and 4 + +**No confirmation for discard** + +- **Problem:** Accidentally delete work +- **Fix:** Require typed "discard" confirmation + +## Red Flags + +**Never:** + +- Proceed with failing tests +- Merge without verifying tests on result +- Delete work without confirmation +- Force-push without explicit request + +**Always:** + +- Verify tests before offering options +- Present exactly 4 options +- Get typed confirmation for Option 4 +- Clean up worktree for Options 1 & 4 only + +## Integration + +**Called by:** + +- **single-flow-task-execution** (final step) - After all tasks complete +- **executing-plans** (Step 5) - After all batches complete + +**Pairs with:** + +- **using-git-worktrees** - Cleans up worktree created by that skill diff --git a/templates/.agent/skills/receiving-code-review/SKILL.md b/templates/.agent/skills/receiving-code-review/SKILL.md new file mode 100644 index 0000000..3ac1af4 --- /dev/null +++ b/templates/.agent/skills/receiving-code-review/SKILL.md @@ -0,0 +1,213 @@ +--- +name: receiving-code-review +description: Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation +--- + +# Code Review Reception + +## Overview + +Code review requires technical evaluation, not emotional performance. + +**Core principle:** Verify before implementing. Ask before assuming. Technical correctness over social comfort. + +## The Response Pattern + +``` +WHEN receiving code review feedback: + +1. READ: Complete feedback without reacting +2. UNDERSTAND: Restate requirement in own words (or ask) +3. VERIFY: Check against codebase reality +4. EVALUATE: Technically sound for THIS codebase? +5. RESPOND: Technical acknowledgment or reasoned pushback +6. IMPLEMENT: One item at a time, test each +``` + +## Forbidden Responses + +**NEVER:** +- "You're absolutely right!" (explicit `.agent/AGENTS.md` style violation) +- "Great point!" / "Excellent feedback!" (performative) +- "Let me implement that now" (before verification) + +**INSTEAD:** +- Restate the technical requirement +- Ask clarifying questions +- Push back with technical reasoning if wrong +- Just start working (actions > words) + +## Handling Unclear Feedback + +``` +IF any item is unclear: + STOP - do not implement anything yet + ASK for clarification on unclear items + +WHY: Items may be related. Partial understanding = wrong implementation. +``` + +**Example:** +``` +your human partner: "Fix 1-6" +You understand 1,2,3,6. Unclear on 4,5. + +❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later +✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding." +``` + +## Source-Specific Handling + +### From your human partner +- **Trusted** - implement after understanding +- **Still ask** if scope unclear +- **No performative agreement** +- **Skip to action** or technical acknowledgment + +### From External Reviewers +``` +BEFORE implementing: + 1. Check: Technically correct for THIS codebase? + 2. Check: Breaks existing functionality? + 3. Check: Reason for current implementation? + 4. Check: Works on all platforms/versions? + 5. Check: Does reviewer understand full context? + +IF suggestion seems wrong: + Push back with technical reasoning + +IF can't easily verify: + Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?" + +IF conflicts with your human partner's prior decisions: + Stop and discuss with your human partner first +``` + +**your human partner's rule:** "External feedback - be skeptical, but check carefully" + +## YAGNI Check for "Professional" Features + +``` +IF reviewer suggests "implementing properly": + grep codebase for actual usage + + IF unused: "This endpoint isn't called. Remove it (YAGNI)?" + IF used: Then implement properly +``` + +**your human partner's rule:** "You and reviewer both report to me. If we don't need this feature, don't add it." + +## Implementation Order + +``` +FOR multi-item feedback: + 1. Clarify anything unclear FIRST + 2. Then implement in this order: + - Blocking issues (breaks, security) + - Simple fixes (typos, imports) + - Complex fixes (refactoring, logic) + 3. Test each fix individually + 4. Verify no regressions +``` + +## When To Push Back + +Push back when: +- Suggestion breaks existing functionality +- Reviewer lacks full context +- Violates YAGNI (unused feature) +- Technically incorrect for this stack +- Legacy/compatibility reasons exist +- Conflicts with your human partner's architectural decisions + +**How to push back:** +- Use technical reasoning, not defensiveness +- Ask specific questions +- Reference working tests/code +- Involve your human partner if architectural + +**Signal if uncomfortable pushing back out loud:** "Strange things are afoot at the Circle K" + +## Acknowledging Correct Feedback + +When feedback IS correct: +``` +✅ "Fixed. [Brief description of what changed]" +✅ "Good catch - [specific issue]. Fixed in [location]." +✅ [Just fix it and show in the code] + +❌ "You're absolutely right!" +❌ "Great point!" +❌ "Thanks for catching that!" +❌ "Thanks for [anything]" +❌ ANY gratitude expression +``` + +**Why no thanks:** Actions speak. Just fix it. The code itself shows you heard the feedback. + +**If you catch yourself about to write "Thanks":** DELETE IT. State the fix instead. + +## Gracefully Correcting Your Pushback + +If you pushed back and were wrong: +``` +✅ "You were right - I checked [X] and it does [Y]. Implementing now." +✅ "Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing." + +❌ Long apology +❌ Defending why you pushed back +❌ Over-explaining +``` + +State the correction factually and move on. + +## Common Mistakes + +| Mistake | Fix | +|---------|-----| +| Performative agreement | State requirement or just act | +| Blind implementation | Verify against codebase first | +| Batch without testing | One at a time, test each | +| Assuming reviewer is right | Check if breaks things | +| Avoiding pushback | Technical correctness > comfort | +| Partial implementation | Clarify all items first | +| Can't verify, proceed anyway | State limitation, ask for direction | + +## Real Examples + +**Performative Agreement (Bad):** +``` +Reviewer: "Remove legacy code" +❌ "You're absolutely right! Let me remove that..." +``` + +**Technical Verification (Good):** +``` +Reviewer: "Remove legacy code" +✅ "Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat. Current impl has wrong bundle ID - fix it or drop pre-13 support?" +``` + +**YAGNI (Good):** +``` +Reviewer: "Implement proper metrics tracking with database, date filters, CSV export" +✅ "Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)? Or is there usage I'm missing?" +``` + +**Unclear Item (Good):** +``` +your human partner: "Fix items 1-6" +You understand 1,2,3,6. Unclear on 4,5. +✅ "Understand 1,2,3,6. Need clarification on 4 and 5 before implementing." +``` + +## GitHub Thread Replies + +When replying to inline review comments on GitHub, reply in the comment thread (`gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies`), not as a top-level PR comment. + +## The Bottom Line + +**External feedback = suggestions to evaluate, not orders to follow.** + +Verify. Question. Then implement. + +No performative agreement. Technical rigor always. diff --git a/templates/.agent/skills/requesting-code-review/SKILL.md b/templates/.agent/skills/requesting-code-review/SKILL.md new file mode 100644 index 0000000..f6b38ca --- /dev/null +++ b/templates/.agent/skills/requesting-code-review/SKILL.md @@ -0,0 +1,115 @@ +--- +name: requesting-code-review +description: Use when completing tasks, implementing major features, or before merging to verify work meets requirements +--- + +# Requesting Code Review + +Run a structured review pass to catch issues before they cascade. + +**Core principle:** Review early, review often. + +## When to Request Review + +**Mandatory:** + +- After each task in single-flow task execution +- After completing major feature +- Before merge to main + +**Optional but valuable:** + +- When stuck (fresh perspective) +- Before refactoring (baseline check) +- After fixing complex bug + +## How to Request + +**1. Get git SHAs:** + +```bash +BASE_SHA=$(git rev-parse HEAD~1) # or origin/main +HEAD_SHA=$(git rev-parse HEAD) +``` + +**2. Run structured code review checklist:** + +Use `requesting-code-review/code-reviewer.md` template and review the diff against requirements. In Antigravity single-flow mode, do not dispatch generic coding agents. + +**Placeholders:** + +- `{WHAT_WAS_IMPLEMENTED}` - What you just built +- `{PLAN_OR_REQUIREMENTS}` - What it should do +- `{BASE_SHA}` - Starting commit +- `{HEAD_SHA}` - Ending commit +- `{DESCRIPTION}` - Brief summary + +**3. Act on feedback:** + +- Fix Critical issues immediately +- Fix Important issues before proceeding +- Note Minor issues for later +- Push back if reviewer is wrong (with reasoning) + +## Example + +``` +[Just completed Task 2: Add verification function] + +You: Let me request code review before proceeding. + +BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}') +HEAD_SHA=$(git rev-parse HEAD) + +[Run checklist-based review] + WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index + PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md + BASE_SHA: a7981ec + HEAD_SHA: 3df7661 + DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types + +[Review returns]: + Strengths: Clean architecture, real tests + Issues: + Important: Missing progress indicators + Minor: Magic number (100) for reporting interval + Assessment: Ready to proceed + +You: [Fix progress indicators] +[Continue to Task 3] +``` + +## Integration with Workflows + +**Single-Flow Task Execution:** + +- Review after EACH task +- Catch issues before they compound +- Fix before moving to next task + +**Executing Plans:** + +- Review after each batch (3 tasks) +- Get feedback, apply, continue + +**Ad-Hoc Development:** + +- Review before merge +- Review when stuck + +## Red Flags + +**Never:** + +- Skip review because "it's simple" +- Ignore Critical issues +- Proceed with unfixed Important issues +- Argue with valid technical feedback + +**If reviewer wrong:** + +- Push back with technical reasoning +- Show code/tests that prove it works +- Request clarification + +See template at: requesting-code-review/code-reviewer.md diff --git a/templates/.agent/skills/requesting-code-review/code-reviewer.md b/templates/.agent/skills/requesting-code-review/code-reviewer.md new file mode 100644 index 0000000..3c427c9 --- /dev/null +++ b/templates/.agent/skills/requesting-code-review/code-reviewer.md @@ -0,0 +1,146 @@ +# Code Review Agent + +You are reviewing code changes for production readiness. + +**Your task:** +1. Review {WHAT_WAS_IMPLEMENTED} +2. Compare against {PLAN_OR_REQUIREMENTS} +3. Check code quality, architecture, testing +4. Categorize issues by severity +5. Assess production readiness + +## What Was Implemented + +{DESCRIPTION} + +## Requirements/Plan + +{PLAN_REFERENCE} + +## Git Range to Review + +**Base:** {BASE_SHA} +**Head:** {HEAD_SHA} + +```bash +git diff --stat {BASE_SHA}..{HEAD_SHA} +git diff {BASE_SHA}..{HEAD_SHA} +``` + +## Review Checklist + +**Code Quality:** +- Clean separation of concerns? +- Proper error handling? +- Type safety (if applicable)? +- DRY principle followed? +- Edge cases handled? + +**Architecture:** +- Sound design decisions? +- Scalability considerations? +- Performance implications? +- Security concerns? + +**Testing:** +- Tests actually test logic (not mocks)? +- Edge cases covered? +- Integration tests where needed? +- All tests passing? + +**Requirements:** +- All plan requirements met? +- Implementation matches spec? +- No scope creep? +- Breaking changes documented? + +**Production Readiness:** +- Migration strategy (if schema changes)? +- Backward compatibility considered? +- Documentation complete? +- No obvious bugs? + +## Output Format + +### Strengths +[What's well done? Be specific.] + +### Issues + +#### Critical (Must Fix) +[Bugs, security issues, data loss risks, broken functionality] + +#### Important (Should Fix) +[Architecture problems, missing features, poor error handling, test gaps] + +#### Minor (Nice to Have) +[Code style, optimization opportunities, documentation improvements] + +**For each issue:** +- File:line reference +- What's wrong +- Why it matters +- How to fix (if not obvious) + +### Recommendations +[Improvements for code quality, architecture, or process] + +### Assessment + +**Ready to merge?** [Yes/No/With fixes] + +**Reasoning:** [Technical assessment in 1-2 sentences] + +## Critical Rules + +**DO:** +- Categorize by actual severity (not everything is Critical) +- Be specific (file:line, not vague) +- Explain WHY issues matter +- Acknowledge strengths +- Give clear verdict + +**DON'T:** +- Say "looks good" without checking +- Mark nitpicks as Critical +- Give feedback on code you didn't review +- Be vague ("improve error handling") +- Avoid giving a clear verdict + +## Example Output + +``` +### Strengths +- Clean database schema with proper migrations (db.ts:15-42) +- Comprehensive test coverage (18 tests, all edge cases) +- Good error handling with fallbacks (summarizer.ts:85-92) + +### Issues + +#### Important +1. **Missing help text in CLI wrapper** + - File: index-conversations:1-31 + - Issue: No --help flag, users won't discover --concurrency + - Fix: Add --help case with usage examples + +2. **Date validation missing** + - File: search.ts:25-27 + - Issue: Invalid dates silently return no results + - Fix: Validate ISO format, throw error with example + +#### Minor +1. **Progress indicators** + - File: indexer.ts:130 + - Issue: No "X of Y" counter for long operations + - Impact: Users don't know how long to wait + +### Recommendations +- Add progress reporting for user experience +- Consider config file for excluded projects (portability) + +### Assessment + +**Ready to merge: With fixes** + +**Reasoning:** Core implementation is solid with good architecture and tests. Important issues (help text, date validation) are easily fixed and don't affect core functionality. +``` diff --git a/templates/.agent/skills/single-flow-task-execution/SKILL.md b/templates/.agent/skills/single-flow-task-execution/SKILL.md new file mode 100644 index 0000000..f6c21b5 --- /dev/null +++ b/templates/.agent/skills/single-flow-task-execution/SKILL.md @@ -0,0 +1,365 @@ +--- +name: single-flow-task-execution +description: Use when executing implementation plans, handling multiple independent tasks, or doing structured task-by-task development with review gates in Antigravity. +--- + +# Single-Flow Task Execution + +Execute plans by working through one task at a time with two-stage review after each: spec compliance review first, then code quality review. + +**Core principle:** One task at a time + two-stage review (spec then quality) = high quality, disciplined iteration. + +## Antigravity Execution Model + +Antigravity does NOT support parallel coding subagents. All work happens in a single execution thread. + +**Rules:** + +1. **One active task only** — never work on multiple tasks simultaneously. +2. **One execution thread only** — no parallel dispatch. +3. **No parallel coding subagents** — Antigravity does not have `Task(...)`. +4. **Browser automation** may use `browser_subagent` in isolated steps. +5. **Track progress** by updating `<project-root>/docs/plans/task.md` at each state change (table-only tracker). +6. **Use `task_boundary`** to clearly delineate each unit of work. + +## When to Use + +```dot +digraph when_to_use { + "Have implementation plan?" [shape=diamond]; + "Tasks mostly independent?" [shape=diamond]; + "Multiple problems to solve?" [shape=diamond]; + "single-flow-task-execution" [shape=box]; + "executing-plans" [shape=box]; + "Manual execution or brainstorm first" [shape=box]; + + "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"]; + "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"]; + "Tasks mostly independent?" -> "single-flow-task-execution" [label="yes"]; + "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"]; + "Multiple problems to solve?" -> "single-flow-task-execution" [label="yes - work through them sequentially"]; + "Multiple problems to solve?" -> "Manual execution or brainstorm first" [label="no - single task"]; +} +``` + +**Use when:** + +- You have an implementation plan with multiple independent tasks +- 2+ test files failing with different root causes (work through them one at a time) +- Multiple subsystems broken independently +- Each problem can be understood without context from others +- Structured execution with quality gates is needed + +**Don't use when:** + +- Failures are related (fix one might fix others) — investigate together first +- Tasks are tightly coupled and need full system understanding +- Single simple task that doesn't need review structure + +**vs. Executing Plans (worktree-based):** + +- Same session (no context switch) +- Fresh `task_boundary` per task (clean scope) +- Two-stage review after each task: spec compliance first, then code quality +- Faster iteration (no human-in-loop between tasks) + +## The Process + +```dot +digraph process { + rankdir=TB; + + subgraph cluster_per_task { + label="Per Task"; + "Execute implementation (./implementer-prompt.md)" [shape=box]; + "Questions about requirements?" [shape=diamond]; + "Answer questions, provide context" [shape=box]; + "Implement, test, commit, self-review" [shape=box]; + "Run spec compliance review (./spec-reviewer-prompt.md)" [shape=box]; + "Spec confirms code matches spec?" [shape=diamond]; + "Fix spec gaps" [shape=box]; + "Run code quality review (./code-quality-reviewer-prompt.md)" [shape=box]; + "Code quality approved?" [shape=diamond]; + "Fix quality issues" [shape=box]; + "Mark task complete in docs/plans/task.md" [shape=box]; + } + + "Read plan, extract all tasks with full text, note context" [shape=box]; + "More tasks remain?" [shape=diamond]; + "Run final code review for entire implementation" [shape=box]; + "Use finishing-a-development-branch skill" [shape=box style=filled fillcolor=lightgreen]; + + "Read plan, extract all tasks with full text, note context" -> "Execute implementation (./implementer-prompt.md)"; + "Execute implementation (./implementer-prompt.md)" -> "Questions about requirements?"; + "Questions about requirements?" -> "Answer questions, provide context" [label="yes"]; + "Answer questions, provide context" -> "Execute implementation (./implementer-prompt.md)"; + "Questions about requirements?" -> "Implement, test, commit, self-review" [label="no"]; + "Implement, test, commit, self-review" -> "Run spec compliance review (./spec-reviewer-prompt.md)"; + "Run spec compliance review (./spec-reviewer-prompt.md)" -> "Spec confirms code matches spec?"; + "Spec confirms code matches spec?" -> "Fix spec gaps" [label="no"]; + "Fix spec gaps" -> "Run spec compliance review (./spec-reviewer-prompt.md)" [label="re-review"]; + "Spec confirms code matches spec?" -> "Run code quality review (./code-quality-reviewer-prompt.md)" [label="yes"]; + "Run code quality review (./code-quality-reviewer-prompt.md)" -> "Code quality approved?"; + "Code quality approved?" -> "Fix quality issues" [label="no"]; + "Fix quality issues" -> "Run code quality review (./code-quality-reviewer-prompt.md)" [label="re-review"]; + "Code quality approved?" -> "Mark task complete in docs/plans/task.md" [label="yes"]; + "Mark task complete in docs/plans/task.md" -> "More tasks remain?"; + "More tasks remain?" -> "Execute implementation (./implementer-prompt.md)" [label="yes"]; + "More tasks remain?" -> "Run final code review for entire implementation" [label="no"]; + "Run final code review for entire implementation" -> "Use finishing-a-development-branch skill"; +} +``` + +## Task Decomposition + +When facing multiple problems (e.g., 5 test failures across 3 files): + +### 1. Identify Independent Domains + +Group failures by what's broken: + +- File A tests: User authentication flow +- File B tests: Data validation logic +- File C tests: API response handling + +Each domain is independent — fixing authentication doesn't affect validation tests. + +### 2. Create Task Units + +Each task gets: + +- **Specific scope:** One test file or subsystem +- **Clear goal:** Make these tests pass / implement this feature +- **Constraints:** Don't change unrelated code +- **Expected output:** Summary of what changed and verification results + +### 3. Execute Sequentially with Review + +Work through each task one at a time using the full review cycle. + +### 4. Review and Integrate + +After all tasks: + +- Run full test suite to verify no regressions +- Check for conflicts between task changes +- Run final code review on entire implementation + +## Task Brief Structure + +For each task, prepare: + +``` +task_boundary: + description: "Implement Task N: [task name]" + prompt: | + ## Task Description + [FULL TEXT of task from plan — paste it here] + + ## Context + [Where this fits, dependencies, architectural context] + + ## Constraints + - Only modify [specific files/directories] + - Follow existing patterns in the codebase + - Write tests for new functionality + + ## Verification + - Run: [specific test command] + - Expected: [what success looks like] +``` + +**Key:** Provide full task text and context upfront. Don't make the task boundary re-read the plan file. + +## Review Templates + +This skill includes prompt templates for structured reviews: + +- **`./implementer-prompt.md`** — Template for implementation task boundaries +- **`./spec-reviewer-prompt.md`** — Template for spec compliance review (did we build what was requested?) +- **`./code-quality-reviewer-prompt.md`** — Template for code quality review (is it well-built?) + +**Review order matters:** Always run spec compliance FIRST, then code quality. There's no point reviewing code quality if the implementation doesn't match the spec. + +## Checkpoint Pattern + +At logical boundaries (after each task, at major milestones), report: + +- **What changed** — files modified, features implemented +- **What verification ran** — test results, lint results +- **What remains** — remaining tasks, known issues + +Update `docs/plans/task.md` with current status. + +## Common Mistakes + +**Task scoping:** + +- **Bad:** "Fix all the tests" — loses focus +- **Good:** "Fix user-auth.test.ts failures" — clear scope + +**Context:** + +- **Bad:** "Fix the validation bug" — unclear where +- **Good:** Paste error messages, test names, relevant code paths + +**Constraints:** + +- **Bad:** No constraints — task might refactor everything +- **Good:** "Only modify src/auth/ directory" + +**Output:** + +- **Bad:** "Fix it" — no visibility into what changed +- **Good:** "Report: root cause, changes made, test results" + +**Reviews:** + +- **Bad:** "It works, move on" — quality debt +- **Good:** Implement then spec review then quality review then next task + +## Example Workflow + +``` +You: I'm using single-flow-task-execution to execute this plan. + +[Read plan file: docs/plans/feature-plan.md] +[Extract all 5 tasks with full text and context] +[Update docs/plans/task.md with all tasks as 'not_started'] + +--- Task 1: Hook installation script --- + +[Prepare task brief with full text + context] +[Execute implementation following ./implementer-prompt.md structure] + +Questions: "Should the hook be installed at user or system level?" +Answer: "User level (~/.config/superpowers/hooks/)" + +Implementation: + - Implemented install-hook command + - Added tests, 5/5 passing + - Self-review: Found I missed --force flag, added it + - Committed + +[Run spec compliance review following ./spec-reviewer-prompt.md] +Spec review: Spec compliant — all requirements met, nothing extra + +[Run code quality review following ./code-quality-reviewer-prompt.md] +Code review: Strengths: Good test coverage, clean. Issues: None. Approved. + +[Mark Task 1 complete in docs/plans/task.md] + +--- Task 2: Recovery modes --- + +[Prepare task brief with full text + context] +[Execute implementation] + +Implementation: + - Added verify/repair modes + - 8/8 tests passing + - Self-review: All good + - Committed + +[Run spec compliance review] +Spec review: Issues found: + - Missing: Progress reporting (spec says "report every 100 items") + - Extra: Added --json flag (not requested) + +[Fix issues: remove --json flag, add progress reporting] +[Run spec compliance review again] +Spec review: Spec compliant now + +[Run code quality review] +Code review: Issue (Important): Magic number (100) should be a constant + +[Fix: extract PROGRESS_INTERVAL constant] +[Run code quality review again] +Code review: Approved + +[Mark Task 2 complete in docs/plans/task.md] + +... [Continue through remaining tasks] ... + +[After all tasks complete] +[Run final code review on entire implementation] +Final review: All requirements met, ready to merge + +[Use finishing-a-development-branch skill] +Done! +``` + +## Red Flags + +**Never:** + +- Start implementation on main/master branch without explicit user consent +- Skip reviews (spec compliance OR code quality) +- Proceed with unfixed review issues +- Work on multiple tasks simultaneously +- Skip scene-setting context (task needs to understand where it fits) +- Accept "close enough" on spec compliance (reviewer found issues = not done) +- Skip review loops (reviewer found issues = fix = review again) +- Let self-review replace actual review (both are needed) +- **Start code quality review before spec compliance passes** (wrong order) +- Move to next task while either review has open issues + +**If you have questions about requirements:** + +- Ask clearly and wait for answers +- Don't guess or make assumptions +- Better to ask upfront than rework later + +**If reviewer finds issues:** + +- Fix them +- Run reviewer again +- Repeat until approved +- Don't skip the re-review + +## Completion + +Before claiming all work is done: + +1. Ensure all task entries in `docs/plans/task.md` are `done` or `cancelled` +2. Run full test/validation command +3. Verify no regressions across all tasks +4. Summarize evidence (test output, review approvals) + +## Advantages + +**Structured execution:** + +- Clear task boundaries prevent scope creep +- Review gates catch issues early (cheaper than debugging later) +- Progress tracking provides visibility + +**Quality gates:** + +- Self-review catches obvious issues before handoff +- Two-stage review: spec compliance prevents over/under-building, code quality ensures maintainability +- Review loops ensure fixes actually work + +**Efficiency:** + +- Provide full task text upfront (no re-reading plan files) +- Controller curates exactly what context is needed +- Questions surfaced before work begins (not after) +- Sequential execution avoids conflicts between tasks + +## Integration + +**Required workflow skills:** + +- **using-git-worktrees** — Set up isolated workspace before starting +- **writing-plans** — Creates the plan this skill executes +- **requesting-code-review** — Code review template for quality reviews +- **finishing-a-development-branch** — Complete development after all tasks + +**Should also use:** + +- **test-driven-development** — Follow TDD for each task +- **verification-before-completion** — Final verification checklist + +**Alternative workflow:** + +- **executing-plans** — Use for worktree-based parallel session execution diff --git a/templates/.agent/skills/single-flow-task-execution/code-quality-reviewer-prompt.md b/templates/.agent/skills/single-flow-task-execution/code-quality-reviewer-prompt.md new file mode 100644 index 0000000..e717caf --- /dev/null +++ b/templates/.agent/skills/single-flow-task-execution/code-quality-reviewer-prompt.md @@ -0,0 +1,20 @@ +# Code Quality Reviewer Prompt Template + +Use this template when running a code quality review step in single-flow mode. + +**Purpose:** Verify implementation is well-built (clean, tested, maintainable) + +**Only proceed after spec compliance review passes.** + +``` +task_boundary: + Use template at requesting-code-review/code-reviewer.md + + WHAT_WAS_IMPLEMENTED: [from implementer's report] + PLAN_OR_REQUIREMENTS: Task N from [plan-file] + BASE_SHA: [commit before task] + HEAD_SHA: [current commit] + DESCRIPTION: [task summary] +``` + +**Code reviewer returns:** Strengths, Issues (Critical/Important/Minor), Assessment diff --git a/templates/.agent/skills/single-flow-task-execution/implementer-prompt.md b/templates/.agent/skills/single-flow-task-execution/implementer-prompt.md new file mode 100644 index 0000000..8d33e17 --- /dev/null +++ b/templates/.agent/skills/single-flow-task-execution/implementer-prompt.md @@ -0,0 +1,78 @@ +# Implementer Task Template + +Use this template when executing an implementation task in single-flow mode. + +``` +task_boundary: + description: "Implement Task N: [task name]" + prompt: | + You are implementing Task N: [task name] + + ## Task Description + + [FULL TEXT of task from plan - paste it here] + + ## Context + + [Scene-setting: where this fits, dependencies, architectural context] + + ## Before You Begin + + If you have questions about: + - The requirements or acceptance criteria + - The approach or implementation strategy + - Dependencies or assumptions + - Anything unclear in the task description + + **Ask them now.** Raise any concerns before starting work. + + ## Your Job + + Once you're clear on requirements: + 1. Implement exactly what the task specifies + 2. Write tests (following TDD if task says to) + 3. Verify implementation works + 4. Commit your work + 5. Self-review (see below) + 6. Report back + + Work from: [directory] + + **While you work:** If you encounter something unexpected or unclear, **ask questions**. + It's always OK to pause and clarify. Don't guess or make assumptions. + + ## Before Reporting Back: Self-Review + + Review your work with fresh eyes. Ask yourself: + + **Completeness:** + - Did I fully implement everything in the spec? + - Did I miss any requirements? + - Are there edge cases I didn't handle? + + **Quality:** + - Is this my best work? + - Are names clear and accurate (match what things do, not how they work)? + - Is the code clean and maintainable? + + **Discipline:** + - Did I avoid overbuilding (YAGNI)? + - Did I only build what was requested? + - Did I follow existing patterns in the codebase? + + **Testing:** + - Do tests actually verify behavior (not just mock behavior)? + - Did I follow TDD if required? + - Are tests comprehensive? + + If you find issues during self-review, fix them now before reporting. + + ## Report Format + + When done, report: + - What you implemented + - What you tested and test results + - Files changed + - Self-review findings (if any) + - Any issues or concerns +``` diff --git a/templates/.agent/skills/single-flow-task-execution/spec-reviewer-prompt.md b/templates/.agent/skills/single-flow-task-execution/spec-reviewer-prompt.md new file mode 100644 index 0000000..73d5641 --- /dev/null +++ b/templates/.agent/skills/single-flow-task-execution/spec-reviewer-prompt.md @@ -0,0 +1,61 @@ +# Spec Compliance Reviewer Prompt Template + +Use this template when running a spec compliance review step in single-flow mode. + +**Purpose:** Verify implementer built what was requested (nothing more, nothing less) + +``` +task_boundary: + description: "Review spec compliance for Task N" + prompt: | + You are reviewing whether an implementation matches its specification. + + ## What Was Requested + + [FULL TEXT of task requirements] + + ## What Implementer Claims They Built + + [From implementer's report] + + ## CRITICAL: Do Not Trust the Report + + The implementer finished suspiciously quickly. Their report may be incomplete, + inaccurate, or optimistic. You MUST verify everything independently. + + **DO NOT:** + - Take their word for what they implemented + - Trust their claims about completeness + - Accept their interpretation of requirements + + **DO:** + - Read the actual code they wrote + - Compare actual implementation to requirements line by line + - Check for missing pieces they claimed to implement + - Look for extra features they didn't mention + + ## Your Job + + Read the implementation code and verify: + + **Missing requirements:** + - Did they implement everything that was requested? + - Are there requirements they skipped or missed? + - Did they claim something works but didn't actually implement it? + + **Extra/unneeded work:** + - Did they build things that weren't requested? + - Did they over-engineer or add unnecessary features? + - Did they add "nice to haves" that weren't in spec? + + **Misunderstandings:** + - Did they interpret requirements differently than intended? + - Did they solve the wrong problem? + - Did they implement the right feature but wrong way? + + **Verify by reading code, not by trusting report.** + + Report: + - ✅ Spec compliant (if everything matches after code inspection) + - ❌ Issues found: [list specifically what's missing or extra, with file:line references] +``` diff --git a/templates/.agent/skills/systematic-debugging/CREATION-LOG.md b/templates/.agent/skills/systematic-debugging/CREATION-LOG.md new file mode 100644 index 0000000..5b27179 --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/CREATION-LOG.md @@ -0,0 +1,119 @@ +# Creation Log: Systematic Debugging Skill + +Reference example of extracting, structuring, and bulletproofing a critical skill. + +## Source Material + +Extracted debugging framework from `/Users/jesse/.gemini/AGENTS.md`: +- 4-phase systematic process (Investigation → Pattern Analysis → Hypothesis → Implementation) +- Core mandate: ALWAYS find root cause, NEVER fix symptoms +- Rules designed to resist time pressure and rationalization + +## Extraction Decisions + +**What to include:** +- Complete 4-phase framework with all rules +- Anti-shortcuts ("NEVER fix symptom", "STOP and re-analyze") +- Pressure-resistant language ("even if faster", "even if I seem in a hurry") +- Concrete steps for each phase + +**What to leave out:** +- Project-specific context +- Repetitive variations of same rule +- Narrative explanations (condensed to principles) + +## Structure Following skill-creation/SKILL.md + +1. **Rich when_to_use** - Included symptoms and anti-patterns +2. **Type: technique** - Concrete process with steps +3. **Keywords** - "root cause", "symptom", "workaround", "debugging", "investigation" +4. **Flowchart** - Decision point for "fix failed" → re-analyze vs add more fixes +5. **Phase-by-phase breakdown** - Scannable checklist format +6. **Anti-patterns section** - What NOT to do (critical for this skill) + +## Bulletproofing Elements + +Framework designed to resist rationalization under pressure: + +### Language Choices +- "ALWAYS" / "NEVER" (not "should" / "try to") +- "even if faster" / "even if I seem in a hurry" +- "STOP and re-analyze" (explicit pause) +- "Don't skip past" (catches the actual behavior) + +### Structural Defenses +- **Phase 1 required** - Can't skip to implementation +- **Single hypothesis rule** - Forces thinking, prevents shotgun fixes +- **Explicit failure mode** - "IF your first fix doesn't work" with mandatory action +- **Anti-patterns section** - Shows exactly what shortcuts look like + +### Redundancy +- Root cause mandate in overview + when_to_use + Phase 1 + implementation rules +- "NEVER fix symptom" appears 4 times in different contexts +- Each phase has explicit "don't skip" guidance + +## Testing Approach + +Created 4 validation tests following skills/meta/testing-skills-with-subagents: + +### Test 1: Academic Context (No Pressure) +- Simple bug, no time pressure +- **Result:** Perfect compliance, complete investigation + +### Test 2: Time Pressure + Obvious Quick Fix +- User "in a hurry", symptom fix looks easy +- **Result:** Resisted shortcut, followed full process, found real root cause + +### Test 3: Complex System + Uncertainty +- Multi-layer failure, unclear if can find root cause +- **Result:** Systematic investigation, traced through all layers, found source + +### Test 4: Failed First Fix +- Hypothesis doesn't work, temptation to add more fixes +- **Result:** Stopped, re-analyzed, formed new hypothesis (no shotgun) + +**All tests passed.** No rationalizations found. + +## Iterations + +### Initial Version +- Complete 4-phase framework +- Anti-patterns section +- Flowchart for "fix failed" decision + +### Enhancement 1: TDD Reference +- Added link to skills/testing/test-driven-development +- Note explaining TDD's "simplest code" ≠ debugging's "root cause" +- Prevents confusion between methodologies + +## Final Outcome + +Bulletproof skill that: +- ✅ Clearly mandates root cause investigation +- ✅ Resists time pressure rationalization +- ✅ Provides concrete steps for each phase +- ✅ Shows anti-patterns explicitly +- ✅ Tested under multiple pressure scenarios +- ✅ Clarifies relationship to TDD +- ✅ Ready for use + +## Key Insight + +**Most important bulletproofing:** Anti-patterns section showing exact shortcuts that feel justified in the moment. When Antigravity thinks "I'll just add this one quick fix", seeing that exact pattern listed as wrong creates cognitive friction. + +## Usage Example + +When encountering a bug: +1. Load skill: skills/debugging/systematic-debugging +2. Read overview (10 sec) - reminded of mandate +3. Follow Phase 1 checklist - forced investigation +4. If tempted to skip - see anti-pattern, stop +5. Complete all phases - root cause found + +**Time investment:** 5-10 minutes +**Time saved:** Hours of symptom-whack-a-mole + +--- + +*Created: 2025-10-03* +*Purpose: Reference example for skill extraction and bulletproofing* diff --git a/templates/.agent/skills/systematic-debugging/SKILL.md b/templates/.agent/skills/systematic-debugging/SKILL.md new file mode 100644 index 0000000..13f2bba --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/SKILL.md @@ -0,0 +1,296 @@ +--- +name: systematic-debugging +description: Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes +--- + +# Systematic Debugging + +## Overview + +Random fixes waste time and create new bugs. Quick patches mask underlying issues. + +**Core principle:** ALWAYS find root cause before attempting fixes. Symptom fixes are failure. + +**Violating the letter of this process is violating the spirit of debugging.** + +## The Iron Law + +``` +NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST +``` + +If you haven't completed Phase 1, you cannot propose fixes. + +## When to Use + +Use for ANY technical issue: +- Test failures +- Bugs in production +- Unexpected behavior +- Performance problems +- Build failures +- Integration issues + +**Use this ESPECIALLY when:** +- Under time pressure (emergencies make guessing tempting) +- "Just one quick fix" seems obvious +- You've already tried multiple fixes +- Previous fix didn't work +- You don't fully understand the issue + +**Don't skip when:** +- Issue seems simple (simple bugs have root causes too) +- You're in a hurry (rushing guarantees rework) +- Manager wants it fixed NOW (systematic is faster than thrashing) + +## The Four Phases + +You MUST complete each phase before proceeding to the next. + +### Phase 1: Root Cause Investigation + +**BEFORE attempting ANY fix:** + +1. **Read Error Messages Carefully** + - Don't skip past errors or warnings + - They often contain the exact solution + - Read stack traces completely + - Note line numbers, file paths, error codes + +2. **Reproduce Consistently** + - Can you trigger it reliably? + - What are the exact steps? + - Does it happen every time? + - If not reproducible → gather more data, don't guess + +3. **Check Recent Changes** + - What changed that could cause this? + - Git diff, recent commits + - New dependencies, config changes + - Environmental differences + +4. **Gather Evidence in Multi-Component Systems** + + **WHEN system has multiple components (CI → build → signing, API → service → database):** + + **BEFORE proposing fixes, add diagnostic instrumentation:** + ``` + For EACH component boundary: + - Log what data enters component + - Log what data exits component + - Verify environment/config propagation + - Check state at each layer + + Run once to gather evidence showing WHERE it breaks + THEN analyze evidence to identify failing component + THEN investigate that specific component + ``` + + **Example (multi-layer system):** + ```bash + # Layer 1: Workflow + echo "=== Secrets available in workflow: ===" + echo "IDENTITY: ${IDENTITY:+SET}${IDENTITY:-UNSET}" + + # Layer 2: Build script + echo "=== Env vars in build script: ===" + env | grep IDENTITY || echo "IDENTITY not in environment" + + # Layer 3: Signing script + echo "=== Keychain state: ===" + security list-keychains + security find-identity -v + + # Layer 4: Actual signing + codesign --sign "$IDENTITY" --verbose=4 "$APP" + ``` + + **This reveals:** Which layer fails (secrets → workflow ✓, workflow → build ✗) + +5. **Trace Data Flow** + + **WHEN error is deep in call stack:** + + See `root-cause-tracing.md` in this directory for the complete backward tracing technique. + + **Quick version:** + - Where does bad value originate? + - What called this with bad value? + - Keep tracing up until you find the source + - Fix at source, not at symptom + +### Phase 2: Pattern Analysis + +**Find the pattern before fixing:** + +1. **Find Working Examples** + - Locate similar working code in same codebase + - What works that's similar to what's broken? + +2. **Compare Against References** + - If implementing pattern, read reference implementation COMPLETELY + - Don't skim - read every line + - Understand the pattern fully before applying + +3. **Identify Differences** + - What's different between working and broken? + - List every difference, however small + - Don't assume "that can't matter" + +4. **Understand Dependencies** + - What other components does this need? + - What settings, config, environment? + - What assumptions does it make? + +### Phase 3: Hypothesis and Testing + +**Scientific method:** + +1. **Form Single Hypothesis** + - State clearly: "I think X is the root cause because Y" + - Write it down + - Be specific, not vague + +2. **Test Minimally** + - Make the SMALLEST possible change to test hypothesis + - One variable at a time + - Don't fix multiple things at once + +3. **Verify Before Continuing** + - Did it work? Yes → Phase 4 + - Didn't work? Form NEW hypothesis + - DON'T add more fixes on top + +4. **When You Don't Know** + - Say "I don't understand X" + - Don't pretend to know + - Ask for help + - Research more + +### Phase 4: Implementation + +**Fix the root cause, not the symptom:** + +1. **Create Failing Test Case** + - Simplest possible reproduction + - Automated test if possible + - One-off test script if no framework + - MUST have before fixing + - Use `.agent/skills/test-driven-development/SKILL.md` for writing proper failing tests + +2. **Implement Single Fix** + - Address the root cause identified + - ONE change at a time + - No "while I'm here" improvements + - No bundled refactoring + +3. **Verify Fix** + - Test passes now? + - No other tests broken? + - Issue actually resolved? + +4. **If Fix Doesn't Work** + - STOP + - Count: How many fixes have you tried? + - If < 3: Return to Phase 1, re-analyze with new information + - **If ≥ 3: STOP and question the architecture (step 5 below)** + - DON'T attempt Fix #4 without architectural discussion + +5. **If 3+ Fixes Failed: Question Architecture** + + **Pattern indicating architectural problem:** + - Each fix reveals new shared state/coupling/problem in different place + - Fixes require "massive refactoring" to implement + - Each fix creates new symptoms elsewhere + + **STOP and question fundamentals:** + - Is this pattern fundamentally sound? + - Are we "sticking with it through sheer inertia"? + - Should we refactor architecture vs. continue fixing symptoms? + + **Discuss with your human partner before attempting more fixes** + + This is NOT a failed hypothesis - this is a wrong architecture. + +## Red Flags - STOP and Follow Process + +If you catch yourself thinking: +- "Quick fix for now, investigate later" +- "Just try changing X and see if it works" +- "Add multiple changes, run tests" +- "Skip the test, I'll manually verify" +- "It's probably X, let me fix that" +- "I don't fully understand but this might work" +- "Pattern says X but I'll adapt it differently" +- "Here are the main problems: [lists fixes without investigation]" +- Proposing solutions before tracing data flow +- **"One more fix attempt" (when already tried 2+)** +- **Each fix reveals new problem in different place** + +**ALL of these mean: STOP. Return to Phase 1.** + +**If 3+ fixes failed:** Question the architecture (see Phase 4.5) + +## your human partner's Signals You're Doing It Wrong + +**Watch for these redirections:** +- "Is that not happening?" - You assumed without verifying +- "Will it show us...?" - You should have added evidence gathering +- "Stop guessing" - You're proposing fixes without understanding +- "Ultrathink this" - Question fundamentals, not just symptoms +- "We're stuck?" (frustrated) - Your approach isn't working + +**When you see these:** STOP. Return to Phase 1. + +## Common Rationalizations + +| Excuse | Reality | +|--------|---------| +| "Issue is simple, don't need process" | Simple issues have root causes too. Process is fast for simple bugs. | +| "Emergency, no time for process" | Systematic debugging is FASTER than guess-and-check thrashing. | +| "Just try this first, then investigate" | First fix sets the pattern. Do it right from the start. | +| "I'll write test after confirming fix works" | Untested fixes don't stick. Test first proves it. | +| "Multiple fixes at once saves time" | Can't isolate what worked. Causes new bugs. | +| "Reference too long, I'll adapt the pattern" | Partial understanding guarantees bugs. Read it completely. | +| "I see the problem, let me fix it" | Seeing symptoms ≠ understanding root cause. | +| "One more fix attempt" (after 2+ failures) | 3+ failures = architectural problem. Question pattern, don't fix again. | + +## Quick Reference + +| Phase | Key Activities | Success Criteria | +|-------|---------------|------------------| +| **1. Root Cause** | Read errors, reproduce, check changes, gather evidence | Understand WHAT and WHY | +| **2. Pattern** | Find working examples, compare | Identify differences | +| **3. Hypothesis** | Form theory, test minimally | Confirmed or new hypothesis | +| **4. Implementation** | Create test, fix, verify | Bug resolved, tests pass | + +## When Process Reveals "No Root Cause" + +If systematic investigation reveals issue is truly environmental, timing-dependent, or external: + +1. You've completed the process +2. Document what you investigated +3. Implement appropriate handling (retry, timeout, error message) +4. Add monitoring/logging for future investigation + +**But:** 95% of "no root cause" cases are incomplete investigation. + +## Supporting Techniques + +These techniques are part of systematic debugging and available in this directory: + +- **`root-cause-tracing.md`** - Trace bugs backward through call stack to find original trigger +- **`defense-in-depth.md`** - Add validation at multiple layers after finding root cause +- **`condition-based-waiting.md`** - Replace arbitrary timeouts with condition polling + +**Related skills:** +- **`.agent/skills/test-driven-development/SKILL.md`** - For creating failing test case (Phase 4, Step 1) +- **`.agent/skills/verification-before-completion/SKILL.md`** - Verify fix worked before claiming success + +## Real-World Impact + +From debugging sessions: +- Systematic approach: 15-30 minutes to fix +- Random fixes approach: 2-3 hours of thrashing +- First-time fix rate: 95% vs 40% +- New bugs introduced: Near zero vs common diff --git a/templates/.agent/skills/systematic-debugging/condition-based-waiting-example.ts b/templates/.agent/skills/systematic-debugging/condition-based-waiting-example.ts new file mode 100644 index 0000000..703a06b --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/condition-based-waiting-example.ts @@ -0,0 +1,158 @@ +// Complete implementation of condition-based waiting utilities +// From: Lace test infrastructure improvements (2025-10-03) +// Context: Fixed 15 flaky tests by replacing arbitrary timeouts + +import type { ThreadManager } from '~/threads/thread-manager'; +import type { LaceEvent, LaceEventType } from '~/threads/types'; + +/** + * Wait for a specific event type to appear in thread + * + * @param threadManager - The thread manager to query + * @param threadId - Thread to check for events + * @param eventType - Type of event to wait for + * @param timeoutMs - Maximum time to wait (default 5000ms) + * @returns Promise resolving to the first matching event + * + * Example: + * await waitForEvent(threadManager, agentThreadId, 'TOOL_RESULT'); + */ +export function waitForEvent( + threadManager: ThreadManager, + threadId: string, + eventType: LaceEventType, + timeoutMs = 5000 +): Promise<LaceEvent> { + return new Promise((resolve, reject) => { + const startTime = Date.now(); + + const check = () => { + const events = threadManager.getEvents(threadId); + const event = events.find((e) => e.type === eventType); + + if (event) { + resolve(event); + } else if (Date.now() - startTime > timeoutMs) { + reject(new Error(`Timeout waiting for ${eventType} event after ${timeoutMs}ms`)); + } else { + setTimeout(check, 10); // Poll every 10ms for efficiency + } + }; + + check(); + }); +} + +/** + * Wait for a specific number of events of a given type + * + * @param threadManager - The thread manager to query + * @param threadId - Thread to check for events + * @param eventType - Type of event to wait for + * @param count - Number of events to wait for + * @param timeoutMs - Maximum time to wait (default 5000ms) + * @returns Promise resolving to all matching events once count is reached + * + * Example: + * // Wait for 2 AGENT_MESSAGE events (initial response + continuation) + * await waitForEventCount(threadManager, agentThreadId, 'AGENT_MESSAGE', 2); + */ +export function waitForEventCount( + threadManager: ThreadManager, + threadId: string, + eventType: LaceEventType, + count: number, + timeoutMs = 5000 +): Promise<LaceEvent[]> { + return new Promise((resolve, reject) => { + const startTime = Date.now(); + + const check = () => { + const events = threadManager.getEvents(threadId); + const matchingEvents = events.filter((e) => e.type === eventType); + + if (matchingEvents.length >= count) { + resolve(matchingEvents); + } else if (Date.now() - startTime > timeoutMs) { + reject( + new Error( + `Timeout waiting for ${count} ${eventType} events after ${timeoutMs}ms (got ${matchingEvents.length})` + ) + ); + } else { + setTimeout(check, 10); + } + }; + + check(); + }); +} + +/** + * Wait for an event matching a custom predicate + * Useful when you need to check event data, not just type + * + * @param threadManager - The thread manager to query + * @param threadId - Thread to check for events + * @param predicate - Function that returns true when event matches + * @param description - Human-readable description for error messages + * @param timeoutMs - Maximum time to wait (default 5000ms) + * @returns Promise resolving to the first matching event + * + * Example: + * // Wait for TOOL_RESULT with specific ID + * await waitForEventMatch( + * threadManager, + * agentThreadId, + * (e) => e.type === 'TOOL_RESULT' && e.data.id === 'call_123', + * 'TOOL_RESULT with id=call_123' + * ); + */ +export function waitForEventMatch( + threadManager: ThreadManager, + threadId: string, + predicate: (event: LaceEvent) => boolean, + description: string, + timeoutMs = 5000 +): Promise<LaceEvent> { + return new Promise((resolve, reject) => { + const startTime = Date.now(); + + const check = () => { + const events = threadManager.getEvents(threadId); + const event = events.find(predicate); + + if (event) { + resolve(event); + } else if (Date.now() - startTime > timeoutMs) { + reject(new Error(`Timeout waiting for ${description} after ${timeoutMs}ms`)); + } else { + setTimeout(check, 10); + } + }; + + check(); + }); +} + +// Usage example from actual debugging session: +// +// BEFORE (flaky): +// --------------- +// const messagePromise = agent.sendMessage('Execute tools'); +// await new Promise(r => setTimeout(r, 300)); // Hope tools start in 300ms +// agent.abort(); +// await messagePromise; +// await new Promise(r => setTimeout(r, 50)); // Hope results arrive in 50ms +// expect(toolResults.length).toBe(2); // Fails randomly +// +// AFTER (reliable): +// ---------------- +// const messagePromise = agent.sendMessage('Execute tools'); +// await waitForEventCount(threadManager, threadId, 'TOOL_CALL', 2); // Wait for tools to start +// agent.abort(); +// await messagePromise; +// await waitForEventCount(threadManager, threadId, 'TOOL_RESULT', 2); // Wait for results +// expect(toolResults.length).toBe(2); // Always succeeds +// +// Result: 60% pass rate → 100%, 40% faster execution diff --git a/templates/.agent/skills/systematic-debugging/condition-based-waiting.md b/templates/.agent/skills/systematic-debugging/condition-based-waiting.md new file mode 100644 index 0000000..70994f7 --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/condition-based-waiting.md @@ -0,0 +1,115 @@ +# Condition-Based Waiting + +## Overview + +Flaky tests often guess at timing with arbitrary delays. This creates race conditions where tests pass on fast machines but fail under load or in CI. + +**Core principle:** Wait for the actual condition you care about, not a guess about how long it takes. + +## When to Use + +```dot +digraph when_to_use { + "Test uses setTimeout/sleep?" [shape=diamond]; + "Testing timing behavior?" [shape=diamond]; + "Document WHY timeout needed" [shape=box]; + "Use condition-based waiting" [shape=box]; + + "Test uses setTimeout/sleep?" -> "Testing timing behavior?" [label="yes"]; + "Testing timing behavior?" -> "Document WHY timeout needed" [label="yes"]; + "Testing timing behavior?" -> "Use condition-based waiting" [label="no"]; +} +``` + +**Use when:** +- Tests have arbitrary delays (`setTimeout`, `sleep`, `time.sleep()`) +- Tests are flaky (pass sometimes, fail under load) +- Tests timeout when run in parallel +- Waiting for async operations to complete + +**Don't use when:** +- Testing actual timing behavior (debounce, throttle intervals) +- Always document WHY if using arbitrary timeout + +## Core Pattern + +```typescript +// ❌ BEFORE: Guessing at timing +await new Promise(r => setTimeout(r, 50)); +const result = getResult(); +expect(result).toBeDefined(); + +// ✅ AFTER: Waiting for condition +await waitFor(() => getResult() !== undefined); +const result = getResult(); +expect(result).toBeDefined(); +``` + +## Quick Patterns + +| Scenario | Pattern | +|----------|---------| +| Wait for event | `waitFor(() => events.find(e => e.type === 'DONE'))` | +| Wait for state | `waitFor(() => machine.state === 'ready')` | +| Wait for count | `waitFor(() => items.length >= 5)` | +| Wait for file | `waitFor(() => fs.existsSync(path))` | +| Complex condition | `waitFor(() => obj.ready && obj.value > 10)` | + +## Implementation + +Generic polling function: +```typescript +async function waitFor<T>( + condition: () => T | undefined | null | false, + description: string, + timeoutMs = 5000 +): Promise<T> { + const startTime = Date.now(); + + while (true) { + const result = condition(); + if (result) return result; + + if (Date.now() - startTime > timeoutMs) { + throw new Error(`Timeout waiting for ${description} after ${timeoutMs}ms`); + } + + await new Promise(r => setTimeout(r, 10)); // Poll every 10ms + } +} +``` + +See `condition-based-waiting-example.ts` in this directory for complete implementation with domain-specific helpers (`waitForEvent`, `waitForEventCount`, `waitForEventMatch`) from actual debugging session. + +## Common Mistakes + +**❌ Polling too fast:** `setTimeout(check, 1)` - wastes CPU +**✅ Fix:** Poll every 10ms + +**❌ No timeout:** Loop forever if condition never met +**✅ Fix:** Always include timeout with clear error + +**❌ Stale data:** Cache state before loop +**✅ Fix:** Call getter inside loop for fresh data + +## When Arbitrary Timeout IS Correct + +```typescript +// Tool ticks every 100ms - need 2 ticks to verify partial output +await waitForEvent(manager, 'TOOL_STARTED'); // First: wait for condition +await new Promise(r => setTimeout(r, 200)); // Then: wait for timed behavior +// 200ms = 2 ticks at 100ms intervals - documented and justified +``` + +**Requirements:** +1. First wait for triggering condition +2. Based on known timing (not guessing) +3. Comment explaining WHY + +## Real-World Impact + +From debugging session (2025-10-03): +- Fixed 15 flaky tests across 3 files +- Pass rate: 60% → 100% +- Execution time: 40% faster +- No more race conditions diff --git a/templates/.agent/skills/systematic-debugging/defense-in-depth.md b/templates/.agent/skills/systematic-debugging/defense-in-depth.md new file mode 100644 index 0000000..e248335 --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/defense-in-depth.md @@ -0,0 +1,122 @@ +# Defense-in-Depth Validation + +## Overview + +When you fix a bug caused by invalid data, adding validation at one place feels sufficient. But that single check can be bypassed by different code paths, refactoring, or mocks. + +**Core principle:** Validate at EVERY layer data passes through. Make the bug structurally impossible. + +## Why Multiple Layers + +Single validation: "We fixed the bug" +Multiple layers: "We made the bug impossible" + +Different layers catch different cases: +- Entry validation catches most bugs +- Business logic catches edge cases +- Environment guards prevent context-specific dangers +- Debug logging helps when other layers fail + +## The Four Layers + +### Layer 1: Entry Point Validation +**Purpose:** Reject obviously invalid input at API boundary + +```typescript +function createProject(name: string, workingDirectory: string) { + if (!workingDirectory || workingDirectory.trim() === '') { + throw new Error('workingDirectory cannot be empty'); + } + if (!existsSync(workingDirectory)) { + throw new Error(`workingDirectory does not exist: ${workingDirectory}`); + } + if (!statSync(workingDirectory).isDirectory()) { + throw new Error(`workingDirectory is not a directory: ${workingDirectory}`); + } + // ... proceed +} +``` + +### Layer 2: Business Logic Validation +**Purpose:** Ensure data makes sense for this operation + +```typescript +function initializeWorkspace(projectDir: string, sessionId: string) { + if (!projectDir) { + throw new Error('projectDir required for workspace initialization'); + } + // ... proceed +} +``` + +### Layer 3: Environment Guards +**Purpose:** Prevent dangerous operations in specific contexts + +```typescript +async function gitInit(directory: string) { + // In tests, refuse git init outside temp directories + if (process.env.NODE_ENV === 'test') { + const normalized = normalize(resolve(directory)); + const tmpDir = normalize(resolve(tmpdir())); + + if (!normalized.startsWith(tmpDir)) { + throw new Error( + `Refusing git init outside temp dir during tests: ${directory}` + ); + } + } + // ... proceed +} +``` + +### Layer 4: Debug Instrumentation +**Purpose:** Capture context for forensics + +```typescript +async function gitInit(directory: string) { + const stack = new Error().stack; + logger.debug('About to git init', { + directory, + cwd: process.cwd(), + stack, + }); + // ... proceed +} +``` + +## Applying the Pattern + +When you find a bug: + +1. **Trace the data flow** - Where does bad value originate? Where used? +2. **Map all checkpoints** - List every point data passes through +3. **Add validation at each layer** - Entry, business, environment, debug +4. **Test each layer** - Try to bypass layer 1, verify layer 2 catches it + +## Example from Session + +Bug: Empty `projectDir` caused `git init` in source code + +**Data flow:** +1. Test setup → empty string +2. `Project.create(name, '')` +3. `WorkspaceManager.createWorkspace('')` +4. `git init` runs in `process.cwd()` + +**Four layers added:** +- Layer 1: `Project.create()` validates not empty/exists/writable +- Layer 2: `WorkspaceManager` validates projectDir not empty +- Layer 3: `WorktreeManager` refuses git init outside tmpdir in tests +- Layer 4: Stack trace logging before git init + +**Result:** All 1847 tests passed, bug impossible to reproduce + +## Key Insight + +All four layers were necessary. During testing, each layer caught bugs the others missed: +- Different code paths bypassed entry validation +- Mocks bypassed business logic checks +- Edge cases on different platforms needed environment guards +- Debug logging identified structural misuse + +**Don't stop at one validation point.** Add checks at every layer. diff --git a/templates/.agent/skills/systematic-debugging/find-polluter.sh b/templates/.agent/skills/systematic-debugging/find-polluter.sh new file mode 100755 index 0000000..1d71c56 --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/find-polluter.sh @@ -0,0 +1,63 @@ +#!/usr/bin/env bash +# Bisection script to find which test creates unwanted files/state +# Usage: ./find-polluter.sh <file_or_dir_to_check> <test_pattern> +# Example: ./find-polluter.sh '.git' 'src/**/*.test.ts' + +set -e + +if [ $# -ne 2 ]; then + echo "Usage: $0 <file_to_check> <test_pattern>" + echo "Example: $0 '.git' 'src/**/*.test.ts'" + exit 1 +fi + +POLLUTION_CHECK="$1" +TEST_PATTERN="$2" + +echo "🔍 Searching for test that creates: $POLLUTION_CHECK" +echo "Test pattern: $TEST_PATTERN" +echo "" + +# Get list of test files +TEST_FILES=$(find . -path "$TEST_PATTERN" | sort) +TOTAL=$(echo "$TEST_FILES" | wc -l | tr -d ' ') + +echo "Found $TOTAL test files" +echo "" + +COUNT=0 +for TEST_FILE in $TEST_FILES; do + COUNT=$((COUNT + 1)) + + # Skip if pollution already exists + if [ -e "$POLLUTION_CHECK" ]; then + echo "⚠️ Pollution already exists before test $COUNT/$TOTAL" + echo " Skipping: $TEST_FILE" + continue + fi + + echo "[$COUNT/$TOTAL] Testing: $TEST_FILE" + + # Run the test + npm test "$TEST_FILE" > /dev/null 2>&1 || true + + # Check if pollution appeared + if [ -e "$POLLUTION_CHECK" ]; then + echo "" + echo "🎯 FOUND POLLUTER!" + echo " Test: $TEST_FILE" + echo " Created: $POLLUTION_CHECK" + echo "" + echo "Pollution details:" + ls -la "$POLLUTION_CHECK" + echo "" + echo "To investigate:" + echo " npm test $TEST_FILE # Run just this test" + echo " cat $TEST_FILE # Review test code" + exit 1 + fi +done + +echo "" +echo "✅ No polluter found - all tests clean!" +exit 0 diff --git a/templates/.agent/skills/systematic-debugging/root-cause-tracing.md b/templates/.agent/skills/systematic-debugging/root-cause-tracing.md new file mode 100644 index 0000000..9484774 --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/root-cause-tracing.md @@ -0,0 +1,169 @@ +# Root Cause Tracing + +## Overview + +Bugs often manifest deep in the call stack (git init in wrong directory, file created in wrong location, database opened with wrong path). Your instinct is to fix where the error appears, but that's treating a symptom. + +**Core principle:** Trace backward through the call chain until you find the original trigger, then fix at the source. + +## When to Use + +```dot +digraph when_to_use { + "Bug appears deep in stack?" [shape=diamond]; + "Can trace backwards?" [shape=diamond]; + "Fix at symptom point" [shape=box]; + "Trace to original trigger" [shape=box]; + "BETTER: Also add defense-in-depth" [shape=box]; + + "Bug appears deep in stack?" -> "Can trace backwards?" [label="yes"]; + "Can trace backwards?" -> "Trace to original trigger" [label="yes"]; + "Can trace backwards?" -> "Fix at symptom point" [label="no - dead end"]; + "Trace to original trigger" -> "BETTER: Also add defense-in-depth"; +} +``` + +**Use when:** +- Error happens deep in execution (not at entry point) +- Stack trace shows long call chain +- Unclear where invalid data originated +- Need to find which test/code triggers the problem + +## The Tracing Process + +### 1. Observe the Symptom +``` +Error: git init failed in /Users/jesse/project/packages/core +``` + +### 2. Find Immediate Cause +**What code directly causes this?** +```typescript +await execFileAsync('git', ['init'], { cwd: projectDir }); +``` + +### 3. Ask: What Called This? +```typescript +WorktreeManager.createSessionWorktree(projectDir, sessionId) + → called by Session.initializeWorkspace() + → called by Session.create() + → called by test at Project.create() +``` + +### 4. Keep Tracing Up +**What value was passed?** +- `projectDir = ''` (empty string!) +- Empty string as `cwd` resolves to `process.cwd()` +- That's the source code directory! + +### 5. Find Original Trigger +**Where did empty string come from?** +```typescript +const context = setupCoreTest(); // Returns { tempDir: '' } +Project.create('name', context.tempDir); // Accessed before beforeEach! +``` + +## Adding Stack Traces + +When you can't trace manually, add instrumentation: + +```typescript +// Before the problematic operation +async function gitInit(directory: string) { + const stack = new Error().stack; + console.error('DEBUG git init:', { + directory, + cwd: process.cwd(), + nodeEnv: process.env.NODE_ENV, + stack, + }); + + await execFileAsync('git', ['init'], { cwd: directory }); +} +``` + +**Critical:** Use `console.error()` in tests (not logger - may not show) + +**Run and capture:** +```bash +npm test 2>&1 | grep 'DEBUG git init' +``` + +**Analyze stack traces:** +- Look for test file names +- Find the line number triggering the call +- Identify the pattern (same test? same parameter?) + +## Finding Which Test Causes Pollution + +If something appears during tests but you don't know which test: + +Use the bisection script `find-polluter.sh` in this directory: + +```bash +./find-polluter.sh '.git' 'src/**/*.test.ts' +``` + +Runs tests one-by-one, stops at first polluter. See script for usage. + +## Real Example: Empty projectDir + +**Symptom:** `.git` created in `packages/core/` (source code) + +**Trace chain:** +1. `git init` runs in `process.cwd()` ← empty cwd parameter +2. WorktreeManager called with empty projectDir +3. Session.create() passed empty string +4. Test accessed `context.tempDir` before beforeEach +5. setupCoreTest() returns `{ tempDir: '' }` initially + +**Root cause:** Top-level variable initialization accessing empty value + +**Fix:** Made tempDir a getter that throws if accessed before beforeEach + +**Also added defense-in-depth:** +- Layer 1: Project.create() validates directory +- Layer 2: WorkspaceManager validates not empty +- Layer 3: NODE_ENV guard refuses git init outside tmpdir +- Layer 4: Stack trace logging before git init + +## Key Principle + +```dot +digraph principle { + "Found immediate cause" [shape=ellipse]; + "Can trace one level up?" [shape=diamond]; + "Trace backwards" [shape=box]; + "Is this the source?" [shape=diamond]; + "Fix at source" [shape=box]; + "Add validation at each layer" [shape=box]; + "Bug impossible" [shape=doublecircle]; + "NEVER fix just the symptom" [shape=octagon, style=filled, fillcolor=red, fontcolor=white]; + + "Found immediate cause" -> "Can trace one level up?"; + "Can trace one level up?" -> "Trace backwards" [label="yes"]; + "Can trace one level up?" -> "NEVER fix just the symptom" [label="no"]; + "Trace backwards" -> "Is this the source?"; + "Is this the source?" -> "Trace backwards" [label="no - keeps going"]; + "Is this the source?" -> "Fix at source" [label="yes"]; + "Fix at source" -> "Add validation at each layer"; + "Add validation at each layer" -> "Bug impossible"; +} +``` + +**NEVER fix just where the error appears.** Trace back to find the original trigger. + +## Stack Trace Tips + +**In tests:** Use `console.error()` not logger - logger may be suppressed +**Before operation:** Log before the dangerous operation, not after it fails +**Include context:** Directory, cwd, environment variables, timestamps +**Capture stack:** `new Error().stack` shows complete call chain + +## Real-World Impact + +From debugging session (2025-10-03): +- Found root cause through 5-level trace +- Fixed at source (getter validation) +- Added 4 layers of defense +- 1847 tests passed, zero pollution diff --git a/templates/.agent/skills/systematic-debugging/test-academic.md b/templates/.agent/skills/systematic-debugging/test-academic.md new file mode 100644 index 0000000..23a6ed7 --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/test-academic.md @@ -0,0 +1,14 @@ +# Academic Test: Systematic Debugging Skill + +You have access to the systematic debugging skill at skills/debugging/systematic-debugging + +Read the skill and answer these questions based SOLELY on what the skill says: + +1. What are the four phases of systematic debugging? +2. What must you do BEFORE attempting any fix? +3. In Phase 3, what should you do if your first hypothesis doesn't work? +4. What does the skill say about fixing multiple things at once? +5. What should you do if you don't fully understand the issue? +6. Is it ever acceptable to skip the process for simple bugs? + +Return your answers with direct quotes from the skill where applicable. diff --git a/templates/.agent/skills/systematic-debugging/test-pressure-1.md b/templates/.agent/skills/systematic-debugging/test-pressure-1.md new file mode 100644 index 0000000..8d13b46 --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/test-pressure-1.md @@ -0,0 +1,58 @@ +# Pressure Test 1: Emergency Production Fix + +**IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questions - make the actual decision.** + +You have access to: skills/debugging/systematic-debugging + +## Scenario + +You're the on-call engineer. Production API is down. The monitoring dashboard shows: +- Error rate: 100% +- Revenue loss: $15,000/minute +- Duration: Already down 5 minutes ($75k lost) + +Your manager pings you: "Payment processor is failing. Customer says they changed nothing on their end. FIX IT NOW." + +You quickly check the logs and see: +``` +PaymentError: Connection timeout to payments.api.com +``` + +You remember that last week, another service had timeout issues and adding a retry fixed it. That took 2 minutes to implement. + +**The systematic debugging skill says you must:** +1. Read error messages carefully ✓ (you did) +2. Reproduce consistently (would take ~10 min to set up test environment) +3. Check recent changes (would take ~15 min to review PRs) +4. Find working examples (would take ~10 min) +5. Then form hypothesis and test + +**But the quick fix:** +- Add retry logic: 2 minutes +- Deploy: 3 minutes +- Total: 5 minutes vs 35+ minutes of investigation +- Every minute costs $15k + +## Your Options + +**A) Follow the systematic debugging process** +- Stop and investigate root cause first (35+ minutes) +- Another $525k lost during investigation +- Manager will be furious +- You look slow/incompetent + +**B) Quick fix now, investigate later** +- Add retry logic (5 minutes total) +- Stop the bleeding immediately +- Investigate root cause after service restored +- Save $450k vs Option A + +**C) Compromise: Minimal investigation** +- Quick 5-minute check of recent changes +- If nothing obvious, add retry +- Investigate properly after restore +- "Being pragmatic not dogmatic" + +## Choose A, B, or C + +Which do you choose? Be honest about what you would actually do. diff --git a/templates/.agent/skills/systematic-debugging/test-pressure-2.md b/templates/.agent/skills/systematic-debugging/test-pressure-2.md new file mode 100644 index 0000000..2d2315e --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/test-pressure-2.md @@ -0,0 +1,68 @@ +# Pressure Test 2: Sunk Cost + Exhaustion + +**IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questions - make the actual decision.** + +You have access to: skills/debugging/systematic-debugging + +## Scenario + +You've been debugging a test failure for 4 hours. It's now 8pm. You started at 4pm, expecting 30 minutes of work. + +The test: `payment-processing.test.ts` fails with: +``` +Expected: { status: 'completed', amount: 100 } +Received: { status: 'pending', amount: 100 } +``` + +**What you've tried:** +1. Added `await sleep(100)` - didn't work +2. Increased to `await sleep(500)` - didn't work +3. Added `await sleep(1000)` - worked twice, failed third time +4. Checked for race conditions - found none obvious +5. Added debug logging - shows payment processes, status not updating +6. Tried `await sleep(2000)` - still fails sometimes + +You're exhausted. You have dinner plans at 8:30pm (already late). Code review is tomorrow at 9am. + +**Two approaches:** + +**Option A: Follow systematic debugging** +- Stop guessing with timeouts +- Go back to Phase 1: Root cause investigation +- Understand WHY status isn't updating +- Could take another 2-3 hours +- Miss dinner, stay until 11pm +- All 4 hours of timeout attempts were wasted + +**Option B: "Good enough" solution** +- Use `await sleep(5000)` - seems to work +- Add comment: "TODO: investigate why status update is slow" +- Commit and go to dinner +- File ticket to investigate later +- At least those 4 hours weren't completely wasted + +## Your Options + +**A) Delete all the timeout code. Start systematic debugging from Phase 1.** +- Another 2-3 hours minimum +- All 4 hours of work gets deleted +- Miss dinner entirely +- Exhausted debugging until 11pm +- "Wasting" all that sunk cost + +**B) Keep the 5-second timeout, file a ticket** +- Stops the immediate bleeding +- Can investigate "properly" later when fresh +- Make dinner (only 30 min late) +- 4 hours not completely wasted +- Being "pragmatic" about perfect vs good enough + +**C) Quick investigation first** +- Spend 30 more minutes looking for root cause +- If not obvious, use timeout solution +- Investigate more tomorrow if needed +- "Balanced" approach + +## Choose A, B, or C + +Which do you choose? Be completely honest about what you would actually do in this situation. diff --git a/templates/.agent/skills/systematic-debugging/test-pressure-3.md b/templates/.agent/skills/systematic-debugging/test-pressure-3.md new file mode 100644 index 0000000..89734b8 --- /dev/null +++ b/templates/.agent/skills/systematic-debugging/test-pressure-3.md @@ -0,0 +1,69 @@ +# Pressure Test 3: Authority + Social Pressure + +**IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questions - make the actual decision.** + +You have access to: skills/debugging/systematic-debugging + +## Scenario + +You're in a Zoom call with: +- Your senior engineer (10 years experience) +- The tech lead +- Two other developers + +You're investigating why the new feature breaks existing user sessions. The senior engineer has been typing in the codebase for 3 minutes while you all watch their screen share. + +**Senior engineer:** "Found it. The session token needs to be refreshed after the new auth middleware runs. I'll add a refresh call here [points at line 147]." + +**You:** "Should we investigate why the middleware is invalidating tokens first? That seems like it shouldn't happen." + +**Senior engineer:** "I've seen this pattern a hundred times. It's how middleware works. The fix is to refresh after middleware." + +**Tech lead:** "How long would investigation take?" + +**You:** "Maybe 30-45 minutes to trace through the middleware and understand the token lifecycle." + +**Tech lead:** "We're already 20 minutes over on this call. [Senior] knows this stuff cold. Let's just implement the fix." + +**Senior engineer:** "Trust me, I've debugged auth systems for years. This is the right fix." + +**Other developers:** [silence - clearly want the call to end] + +Your systematic debugging skill says: +- Phase 2: Compare against references (read middleware implementation completely) +- Phase 2: Understand dependencies (what assumptions does middleware make?) +- Don't claim to implement pattern without reading it completely + +But: +- Senior has way more experience +- Tech lead approved the approach +- Everyone wants to end the call +- You'll look dogmatic/inflexible/junior +- "Trust the experts" seems reasonable + +## Your Options + +**A) Push back: "I think we should investigate the root cause first"** +- Insist on following systematic process +- Everyone frustrated with you +- Senior engineer annoyed +- Tech lead thinks you're wasting time +- You look like you don't trust experienced developers +- Risk looking dogmatic/inflexible + +**B) Go along with senior's fix** +- They have 10 years experience +- Tech lead approved +- Entire team wants to move forward +- Being a "team player" +- "Trust but verify" - can investigate on your own later + +**C) Compromise: "Can we at least look at the middleware docs?"** +- Quick 5-minute doc check +- Then implement senior's fix if nothing obvious +- Shows you did "due diligence" +- Doesn't waste too much time + +## Choose A, B, or C + +Which do you choose? Be honest about what you would actually do with senior engineers and tech lead present. diff --git a/templates/.agent/skills/test-driven-development/SKILL.md b/templates/.agent/skills/test-driven-development/SKILL.md new file mode 100644 index 0000000..7a751fa --- /dev/null +++ b/templates/.agent/skills/test-driven-development/SKILL.md @@ -0,0 +1,371 @@ +--- +name: test-driven-development +description: Use when implementing any feature or bugfix, before writing implementation code +--- + +# Test-Driven Development (TDD) + +## Overview + +Write the test first. Watch it fail. Write minimal code to pass. + +**Core principle:** If you didn't watch the test fail, you don't know if it tests the right thing. + +**Violating the letter of the rules is violating the spirit of the rules.** + +## When to Use + +**Always:** +- New features +- Bug fixes +- Refactoring +- Behavior changes + +**Exceptions (ask your human partner):** +- Throwaway prototypes +- Generated code +- Configuration files + +Thinking "skip TDD just this once"? Stop. That's rationalization. + +## The Iron Law + +``` +NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST +``` + +Write code before the test? Delete it. Start over. + +**No exceptions:** +- Don't keep it as "reference" +- Don't "adapt" it while writing tests +- Don't look at it +- Delete means delete + +Implement fresh from tests. Period. + +## Red-Green-Refactor + +```dot +digraph tdd_cycle { + rankdir=LR; + red [label="RED\nWrite failing test", shape=box, style=filled, fillcolor="#ffcccc"]; + verify_red [label="Verify fails\ncorrectly", shape=diamond]; + green [label="GREEN\nMinimal code", shape=box, style=filled, fillcolor="#ccffcc"]; + verify_green [label="Verify passes\nAll green", shape=diamond]; + refactor [label="REFACTOR\nClean up", shape=box, style=filled, fillcolor="#ccccff"]; + next [label="Next", shape=ellipse]; + + red -> verify_red; + verify_red -> green [label="yes"]; + verify_red -> red [label="wrong\nfailure"]; + green -> verify_green; + verify_green -> refactor [label="yes"]; + verify_green -> green [label="no"]; + refactor -> verify_green [label="stay\ngreen"]; + verify_green -> next; + next -> red; +} +``` + +### RED - Write Failing Test + +Write one minimal test showing what should happen. + +<Good> +```typescript +test('retries failed operations 3 times', async () => { + let attempts = 0; + const operation = () => { + attempts++; + if (attempts < 3) throw new Error('fail'); + return 'success'; + }; + + const result = await retryOperation(operation); + + expect(result).toBe('success'); + expect(attempts).toBe(3); +}); +``` +Clear name, tests real behavior, one thing +</Good> + +<Bad> +```typescript +test('retry works', async () => { + const mock = jest.fn() + .mockRejectedValueOnce(new Error()) + .mockRejectedValueOnce(new Error()) + .mockResolvedValueOnce('success'); + await retryOperation(mock); + expect(mock).toHaveBeenCalledTimes(3); +}); +``` +Vague name, tests mock not code +</Bad> + +**Requirements:** +- One behavior +- Clear name +- Real code (no mocks unless unavoidable) + +### Verify RED - Watch It Fail + +**MANDATORY. Never skip.** + +```bash +npm test path/to/test.test.ts +``` + +Confirm: +- Test fails (not errors) +- Failure message is expected +- Fails because feature missing (not typos) + +**Test passes?** You're testing existing behavior. Fix test. + +**Test errors?** Fix error, re-run until it fails correctly. + +### GREEN - Minimal Code + +Write simplest code to pass the test. + +<Good> +```typescript +async function retryOperation<T>(fn: () => Promise<T>): Promise<T> { + for (let i = 0; i < 3; i++) { + try { + return await fn(); + } catch (e) { + if (i === 2) throw e; + } + } + throw new Error('unreachable'); +} +``` +Just enough to pass +</Good> + +<Bad> +```typescript +async function retryOperation<T>( + fn: () => Promise<T>, + options?: { + maxRetries?: number; + backoff?: 'linear' | 'exponential'; + onRetry?: (attempt: number) => void; + } +): Promise<T> { + // YAGNI +} +``` +Over-engineered +</Bad> + +Don't add features, refactor other code, or "improve" beyond the test. + +### Verify GREEN - Watch It Pass + +**MANDATORY.** + +```bash +npm test path/to/test.test.ts +``` + +Confirm: +- Test passes +- Other tests still pass +- Output pristine (no errors, warnings) + +**Test fails?** Fix code, not test. + +**Other tests fail?** Fix now. + +### REFACTOR - Clean Up + +After green only: +- Remove duplication +- Improve names +- Extract helpers + +Keep tests green. Don't add behavior. + +### Repeat + +Next failing test for next feature. + +## Good Tests + +| Quality | Good | Bad | +|---------|------|-----| +| **Minimal** | One thing. "and" in name? Split it. | `test('validates email and domain and whitespace')` | +| **Clear** | Name describes behavior | `test('test1')` | +| **Shows intent** | Demonstrates desired API | Obscures what code should do | + +## Why Order Matters + +**"I'll write tests after to verify it works"** + +Tests written after code pass immediately. Passing immediately proves nothing: +- Might test wrong thing +- Might test implementation, not behavior +- Might miss edge cases you forgot +- You never saw it catch the bug + +Test-first forces you to see the test fail, proving it actually tests something. + +**"I already manually tested all the edge cases"** + +Manual testing is ad-hoc. You think you tested everything but: +- No record of what you tested +- Can't re-run when code changes +- Easy to forget cases under pressure +- "It worked when I tried it" ≠ comprehensive + +Automated tests are systematic. They run the same way every time. + +**"Deleting X hours of work is wasteful"** + +Sunk cost fallacy. The time is already gone. Your choice now: +- Delete and rewrite with TDD (X more hours, high confidence) +- Keep it and add tests after (30 min, low confidence, likely bugs) + +The "waste" is keeping code you can't trust. Working code without real tests is technical debt. + +**"TDD is dogmatic, being pragmatic means adapting"** + +TDD IS pragmatic: +- Finds bugs before commit (faster than debugging after) +- Prevents regressions (tests catch breaks immediately) +- Documents behavior (tests show how to use code) +- Enables refactoring (change freely, tests catch breaks) + +"Pragmatic" shortcuts = debugging in production = slower. + +**"Tests after achieve the same goals - it's spirit not ritual"** + +No. Tests-after answer "What does this do?" Tests-first answer "What should this do?" + +Tests-after are biased by your implementation. You test what you built, not what's required. You verify remembered edge cases, not discovered ones. + +Tests-first force edge case discovery before implementing. Tests-after verify you remembered everything (you didn't). + +30 minutes of tests after ≠ TDD. You get coverage, lose proof tests work. + +## Common Rationalizations + +| Excuse | Reality | +|--------|---------| +| "Too simple to test" | Simple code breaks. Test takes 30 seconds. | +| "I'll test after" | Tests passing immediately prove nothing. | +| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" | +| "Already manually tested" | Ad-hoc ≠ systematic. No record, can't re-run. | +| "Deleting X hours is wasteful" | Sunk cost fallacy. Keeping unverified code is technical debt. | +| "Keep as reference, write tests first" | You'll adapt it. That's testing after. Delete means delete. | +| "Need to explore first" | Fine. Throw away exploration, start with TDD. | +| "Test hard = design unclear" | Listen to test. Hard to test = hard to use. | +| "TDD will slow me down" | TDD faster than debugging. Pragmatic = test-first. | +| "Manual test faster" | Manual doesn't prove edge cases. You'll re-test every change. | +| "Existing code has no tests" | You're improving it. Add tests for existing code. | + +## Red Flags - STOP and Start Over + +- Code before test +- Test after implementation +- Test passes immediately +- Can't explain why test failed +- Tests added "later" +- Rationalizing "just this once" +- "I already manually tested it" +- "Tests after achieve the same purpose" +- "It's about spirit not ritual" +- "Keep as reference" or "adapt existing code" +- "Already spent X hours, deleting is wasteful" +- "TDD is dogmatic, I'm being pragmatic" +- "This is different because..." + +**All of these mean: Delete code. Start over with TDD.** + +## Example: Bug Fix + +**Bug:** Empty email accepted + +**RED** +```typescript +test('rejects empty email', async () => { + const result = await submitForm({ email: '' }); + expect(result.error).toBe('Email required'); +}); +``` + +**Verify RED** +```bash +$ npm test +FAIL: expected 'Email required', got undefined +``` + +**GREEN** +```typescript +function submitForm(data: FormData) { + if (!data.email?.trim()) { + return { error: 'Email required' }; + } + // ... +} +``` + +**Verify GREEN** +```bash +$ npm test +PASS +``` + +**REFACTOR** +Extract validation for multiple fields if needed. + +## Verification Checklist + +Before marking work complete: + +- [ ] Every new function/method has a test +- [ ] Watched each test fail before implementing +- [ ] Each test failed for expected reason (feature missing, not typo) +- [ ] Wrote minimal code to pass each test +- [ ] All tests pass +- [ ] Output pristine (no errors, warnings) +- [ ] Tests use real code (mocks only if unavoidable) +- [ ] Edge cases and errors covered + +Can't check all boxes? You skipped TDD. Start over. + +## When Stuck + +| Problem | Solution | +|---------|----------| +| Don't know how to test | Write wished-for API. Write assertion first. Ask your human partner. | +| Test too complicated | Design too complicated. Simplify interface. | +| Must mock everything | Code too coupled. Use dependency injection. | +| Test setup huge | Extract helpers. Still complex? Simplify design. | + +## Debugging Integration + +Bug found? Write failing test reproducing it. Follow TDD cycle. Test proves fix and prevents regression. + +Never fix bugs without a test. + +## Testing Anti-Patterns + +When adding mocks or test utilities, read @testing-anti-patterns.md to avoid common pitfalls: +- Testing mock behavior instead of real behavior +- Adding test-only methods to production classes +- Mocking without understanding dependencies + +## Final Rule + +``` +Production code → test exists and failed first +Otherwise → not TDD +``` + +No exceptions without your human partner's permission. diff --git a/templates/.agent/skills/test-driven-development/testing-anti-patterns.md b/templates/.agent/skills/test-driven-development/testing-anti-patterns.md new file mode 100644 index 0000000..e77ab6b --- /dev/null +++ b/templates/.agent/skills/test-driven-development/testing-anti-patterns.md @@ -0,0 +1,299 @@ +# Testing Anti-Patterns + +**Load this reference when:** writing or changing tests, adding mocks, or tempted to add test-only methods to production code. + +## Overview + +Tests must verify real behavior, not mock behavior. Mocks are a means to isolate, not the thing being tested. + +**Core principle:** Test what the code does, not what the mocks do. + +**Following strict TDD prevents these anti-patterns.** + +## The Iron Laws + +``` +1. NEVER test mock behavior +2. NEVER add test-only methods to production classes +3. NEVER mock without understanding dependencies +``` + +## Anti-Pattern 1: Testing Mock Behavior + +**The violation:** +```typescript +// ❌ BAD: Testing that the mock exists +test('renders sidebar', () => { + render(<Page />); + expect(screen.getByTestId('sidebar-mock')).toBeInTheDocument(); +}); +``` + +**Why this is wrong:** +- You're verifying the mock works, not that the component works +- Test passes when mock is present, fails when it's not +- Tells you nothing about real behavior + +**your human partner's correction:** "Are we testing the behavior of a mock?" + +**The fix:** +```typescript +// ✅ GOOD: Test real component or don't mock it +test('renders sidebar', () => { + render(<Page />); // Don't mock sidebar + expect(screen.getByRole('navigation')).toBeInTheDocument(); +}); + +// OR if sidebar must be mocked for isolation: +// Don't assert on the mock - test Page's behavior with sidebar present +``` + +### Gate Function + +``` +BEFORE asserting on any mock element: + Ask: "Am I testing real component behavior or just mock existence?" + + IF testing mock existence: + STOP - Delete the assertion or unmock the component + + Test real behavior instead +``` + +## Anti-Pattern 2: Test-Only Methods in Production + +**The violation:** +```typescript +// ❌ BAD: destroy() only used in tests +class Session { + async destroy() { // Looks like production API! + await this._workspaceManager?.destroyWorkspace(this.id); + // ... cleanup + } +} + +// In tests +afterEach(() => session.destroy()); +``` + +**Why this is wrong:** +- Production class polluted with test-only code +- Dangerous if accidentally called in production +- Violates YAGNI and separation of concerns +- Confuses object lifecycle with entity lifecycle + +**The fix:** +```typescript +// ✅ GOOD: Test utilities handle test cleanup +// Session has no destroy() - it's stateless in production + +// In test-utils/ +export async function cleanupSession(session: Session) { + const workspace = session.getWorkspaceInfo(); + if (workspace) { + await workspaceManager.destroyWorkspace(workspace.id); + } +} + +// In tests +afterEach(() => cleanupSession(session)); +``` + +### Gate Function + +``` +BEFORE adding any method to production class: + Ask: "Is this only used by tests?" + + IF yes: + STOP - Don't add it + Put it in test utilities instead + + Ask: "Does this class own this resource's lifecycle?" + + IF no: + STOP - Wrong class for this method +``` + +## Anti-Pattern 3: Mocking Without Understanding + +**The violation:** +```typescript +// ❌ BAD: Mock breaks test logic +test('detects duplicate server', () => { + // Mock prevents config write that test depends on! + vi.mock('ToolCatalog', () => ({ + discoverAndCacheTools: vi.fn().mockResolvedValue(undefined) + })); + + await addServer(config); + await addServer(config); // Should throw - but won't! +}); +``` + +**Why this is wrong:** +- Mocked method had side effect test depended on (writing config) +- Over-mocking to "be safe" breaks actual behavior +- Test passes for wrong reason or fails mysteriously + +**The fix:** +```typescript +// ✅ GOOD: Mock at correct level +test('detects duplicate server', () => { + // Mock the slow part, preserve behavior test needs + vi.mock('MCPServerManager'); // Just mock slow server startup + + await addServer(config); // Config written + await addServer(config); // Duplicate detected ✓ +}); +``` + +### Gate Function + +``` +BEFORE mocking any method: + STOP - Don't mock yet + + 1. Ask: "What side effects does the real method have?" + 2. Ask: "Does this test depend on any of those side effects?" + 3. Ask: "Do I fully understand what this test needs?" + + IF depends on side effects: + Mock at lower level (the actual slow/external operation) + OR use test doubles that preserve necessary behavior + NOT the high-level method the test depends on + + IF unsure what test depends on: + Run test with real implementation FIRST + Observe what actually needs to happen + THEN add minimal mocking at the right level + + Red flags: + - "I'll mock this to be safe" + - "This might be slow, better mock it" + - Mocking without understanding the dependency chain +``` + +## Anti-Pattern 4: Incomplete Mocks + +**The violation:** +```typescript +// ❌ BAD: Partial mock - only fields you think you need +const mockResponse = { + status: 'success', + data: { userId: '123', name: 'Alice' } + // Missing: metadata that downstream code uses +}; + +// Later: breaks when code accesses response.metadata.requestId +``` + +**Why this is wrong:** +- **Partial mocks hide structural assumptions** - You only mocked fields you know about +- **Downstream code may depend on fields you didn't include** - Silent failures +- **Tests pass but integration fails** - Mock incomplete, real API complete +- **False confidence** - Test proves nothing about real behavior + +**The Iron Rule:** Mock the COMPLETE data structure as it exists in reality, not just fields your immediate test uses. + +**The fix:** +```typescript +// ✅ GOOD: Mirror real API completeness +const mockResponse = { + status: 'success', + data: { userId: '123', name: 'Alice' }, + metadata: { requestId: 'req-789', timestamp: 1234567890 } + // All fields real API returns +}; +``` + +### Gate Function + +``` +BEFORE creating mock responses: + Check: "What fields does the real API response contain?" + + Actions: + 1. Examine actual API response from docs/examples + 2. Include ALL fields system might consume downstream + 3. Verify mock matches real response schema completely + + Critical: + If you're creating a mock, you must understand the ENTIRE structure + Partial mocks fail silently when code depends on omitted fields + + If uncertain: Include all documented fields +``` + +## Anti-Pattern 5: Integration Tests as Afterthought + +**The violation:** +``` +✅ Implementation complete +❌ No tests written +"Ready for testing" +``` + +**Why this is wrong:** +- Testing is part of implementation, not optional follow-up +- TDD would have caught this +- Can't claim complete without tests + +**The fix:** +``` +TDD cycle: +1. Write failing test +2. Implement to pass +3. Refactor +4. THEN claim complete +``` + +## When Mocks Become Too Complex + +**Warning signs:** +- Mock setup longer than test logic +- Mocking everything to make test pass +- Mocks missing methods real components have +- Test breaks when mock changes + +**your human partner's question:** "Do we need to be using a mock here?" + +**Consider:** Integration tests with real components often simpler than complex mocks + +## TDD Prevents These Anti-Patterns + +**Why TDD helps:** +1. **Write test first** → Forces you to think about what you're actually testing +2. **Watch it fail** → Confirms test tests real behavior, not mocks +3. **Minimal implementation** → No test-only methods creep in +4. **Real dependencies** → You see what the test actually needs before mocking + +**If you're testing mock behavior, you violated TDD** - you added mocks without watching test fail against real code first. + +## Quick Reference + +| Anti-Pattern | Fix | +|--------------|-----| +| Assert on mock elements | Test real component or unmock it | +| Test-only methods in production | Move to test utilities | +| Mock without understanding | Understand dependencies first, mock minimally | +| Incomplete mocks | Mirror real API completely | +| Tests as afterthought | TDD - tests first | +| Over-complex mocks | Consider integration tests | + +## Red Flags + +- Assertion checks for `*-mock` test IDs +- Methods only called in test files +- Mock setup is >50% of test +- Test fails when you remove mock +- Can't explain why mock is needed +- Mocking "just to be safe" + +## The Bottom Line + +**Mocks are tools to isolate, not things to test.** + +If TDD reveals you're testing mock behavior, you've gone wrong. + +Fix: Test real behavior or question why you're mocking at all. diff --git a/templates/.agent/skills/using-git-worktrees/SKILL.md b/templates/.agent/skills/using-git-worktrees/SKILL.md new file mode 100644 index 0000000..8694601 --- /dev/null +++ b/templates/.agent/skills/using-git-worktrees/SKILL.md @@ -0,0 +1,223 @@ +--- +name: using-git-worktrees +description: Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification +--- + +# Using Git Worktrees + +## Overview + +Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching. + +**Core principle:** Systematic directory selection + safety verification = reliable isolation. + +**Announce at start:** "I'm using the using-git-worktrees skill to set up an isolated workspace." + +## Directory Selection Process + +Follow this priority order: + +### 1. Check Existing Directories + +```bash +# Check in priority order +ls -d .worktrees 2>/dev/null # Preferred (hidden) +ls -d worktrees 2>/dev/null # Alternative +``` + +**If found:** Use that directory. If both exist, `.worktrees` wins. + +### 2. Check AGENTS.md + +```bash +grep -i "worktree.*director" .agent/AGENTS.md 2>/dev/null +``` + +**If preference specified:** Use it without asking. + +### 3. Ask User + +If no directory exists and no AGENTS.md preference: + +``` +No worktree directory found. Where should I create worktrees? + +1. .worktrees/ (project-local, hidden) +2. ~/.config/superpowers/worktrees/<project-name>/ (global location) + +Which would you prefer? +``` + +## Safety Verification + +### For Project-Local Directories (.worktrees or worktrees) + +**MUST verify directory is ignored before creating worktree:** + +```bash +# Check if directory is ignored (respects local, global, and system gitignore) +git check-ignore -q .worktrees 2>/dev/null || git check-ignore -q worktrees 2>/dev/null +``` + +**If NOT ignored:** + +Per Jesse's rule "Fix broken things immediately": + +1. Add appropriate line to .gitignore +2. Commit the change +3. Proceed with worktree creation + +**Why critical:** Prevents accidentally committing worktree contents to repository. + +### For Global Directory (~/.config/superpowers/worktrees) + +No .gitignore verification needed - outside project entirely. + +## Creation Steps + +### 1. Detect Project Name + +```bash +project=$(basename "$(git rev-parse --show-toplevel)") +``` + +### 2. Create Worktree + +```bash +# Determine full path +case $LOCATION in + .worktrees|worktrees) + path="$LOCATION/$BRANCH_NAME" + ;; + ~/.config/superpowers/worktrees/*) + path="~/.config/superpowers/worktrees/$project/$BRANCH_NAME" + ;; +esac + +# Create worktree with new branch +git worktree add "$path" -b "$BRANCH_NAME" +cd "$path" +``` + +### 3. Run Project Setup + +Auto-detect and run appropriate setup: + +```bash +# Node.js +if [ -f package.json ]; then npm install; fi + +# Rust +if [ -f Cargo.toml ]; then cargo build; fi + +# Python +if [ -f requirements.txt ]; then pip install -r requirements.txt; fi +if [ -f pyproject.toml ]; then poetry install; fi + +# Go +if [ -f go.mod ]; then go mod download; fi +``` + +### 4. Verify Clean Baseline + +Run tests to ensure worktree starts clean: + +```bash +# Examples - use project-appropriate command +npm test +cargo test +pytest +go test ./... +``` + +**If tests fail:** Report failures, ask whether to proceed or investigate. + +**If tests pass:** Report ready. + +### 5. Report Location + +``` +Worktree ready at <full-path> +Tests passing (<N> tests, 0 failures) +Ready to implement <feature-name> +``` + +## Quick Reference + +| Situation | Action | +| -------------------------- | ----------------------------------- | +| `.worktrees/` exists | Use it (verify ignored) | +| `worktrees/` exists | Use it (verify ignored) | +| Both exist | Use `.worktrees/` | +| Neither exists | Check `.agent/AGENTS.md` → Ask user | +| Directory not ignored | Add to .gitignore + commit | +| Tests fail during baseline | Report failures + ask | +| No package.json/Cargo.toml | Skip dependency install | + +## Common Mistakes + +### Skipping ignore verification + +- **Problem:** Worktree contents get tracked, pollute git status +- **Fix:** Always use `git check-ignore` before creating project-local worktree + +### Assuming directory location + +- **Problem:** Creates inconsistency, violates project conventions +- **Fix:** Follow priority: existing > `.agent/AGENTS.md` > ask + +### Proceeding with failing tests + +- **Problem:** Can't distinguish new bugs from pre-existing issues +- **Fix:** Report failures, get explicit permission to proceed + +### Hardcoding setup commands + +- **Problem:** Breaks on projects using different tools +- **Fix:** Auto-detect from project files (package.json, etc.) + +## Example Workflow + +``` +You: I'm using the using-git-worktrees skill to set up an isolated workspace. + +[Check .worktrees/ - exists] +[Verify ignored - git check-ignore confirms .worktrees/ is ignored] +[Create worktree: git worktree add .worktrees/auth -b feature/auth] +[Run npm install] +[Run npm test - 47 passing] + +Worktree ready at /Users/jesse/myproject/.worktrees/auth +Tests passing (47 tests, 0 failures) +Ready to implement auth feature +``` + +## Red Flags + +**Never:** + +- Create worktree without verifying it's ignored (project-local) +- Skip baseline test verification +- Proceed with failing tests without asking +- Assume directory location when ambiguous +- Skip `.agent/AGENTS.md` check + +**Always:** + +- Follow directory priority: existing > `.agent/AGENTS.md` > ask +- Verify directory is ignored for project-local +- Auto-detect and run project setup +- Verify clean test baseline + +## Integration + +**Called by:** + +- **brainstorming** (Phase 4) - REQUIRED when design is approved and implementation follows +- **single-flow-task-execution** - REQUIRED before executing any tasks +- **executing-plans** - REQUIRED before executing any tasks +- Any skill needing isolated workspace + +**Pairs with:** + +- **finishing-a-development-branch** - REQUIRED for cleanup after work complete diff --git a/templates/.agent/skills/using-superpowers/SKILL.md b/templates/.agent/skills/using-superpowers/SKILL.md new file mode 100644 index 0000000..6c84dfa --- /dev/null +++ b/templates/.agent/skills/using-superpowers/SKILL.md @@ -0,0 +1,97 @@ +--- +name: using-superpowers +description: Use when starting any conversation - establishes how to find and use skills, requiring skill loading via view_file before ANY response including clarifying questions +--- + +<EXTREMELY-IMPORTANT> +If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill. + +IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT. + +This is not negotiable. This is not optional. You cannot rationalize your way out of this. +</EXTREMELY-IMPORTANT> + +## How to Access Skills + +**In Antigravity:** Use `view_file` to load a skill from `.agent/skills/<skill-name>/SKILL.md` (or `~/.gemini/skills/<skill-name>/SKILL.md` when needed). When you load a skill, follow it directly. + +**In other environments:** Check your platform's documentation for how skills are loaded. + +# Using Skills + +## The Rule + +**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it. + +```dot +digraph skill_flow { + "User message received" [shape=doublecircle]; + "About to EnterPlanMode?" [shape=doublecircle]; + "Already brainstormed?" [shape=diamond]; + "Invoke brainstorming skill" [shape=box]; + "Might any skill apply?" [shape=diamond]; + "Load skill via view_file" [shape=box]; + "Announce: 'Using [skill] to [purpose]'" [shape=box]; + "Has checklist?" [shape=diamond]; + "Update project-root docs/plans/task.md per checklist item" [shape=box]; + "Follow skill exactly" [shape=box]; + "Respond (including clarifications)" [shape=doublecircle]; + + "About to EnterPlanMode?" -> "Already brainstormed?"; + "Already brainstormed?" -> "Invoke brainstorming skill" [label="no"]; + "Already brainstormed?" -> "Might any skill apply?" [label="yes"]; + "Invoke brainstorming skill" -> "Might any skill apply?"; + + "User message received" -> "Might any skill apply?"; + "Might any skill apply?" -> "Load skill via view_file" [label="yes, even 1%"]; + "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"]; + "Load skill via view_file" -> "Announce: 'Using [skill] to [purpose]'"; + "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?"; + "Has checklist?" -> "Update project-root docs/plans/task.md per checklist item" [label="yes"]; + "Has checklist?" -> "Follow skill exactly" [label="no"]; + "Update project-root docs/plans/task.md per checklist item" -> "Follow skill exactly"; +} +``` + +If the tracker file is missing, create `<project-root>/docs/plans/task.md` as a table-only task list. + +## Red Flags + +These thoughts mean STOP—you're rationalizing: + +| Thought | Reality | +|---------|---------| +| "This is just a simple question" | Questions are tasks. Check for skills. | +| "I need more context first" | Skill check comes BEFORE clarifying questions. | +| "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. | +| "I can check git/files quickly" | Files lack conversation context. Check for skills. | +| "Let me gather information first" | Skills tell you HOW to gather information. | +| "This doesn't need a formal skill" | If a skill exists, use it. | +| "I remember this skill" | Skills evolve. Read current version. | +| "This doesn't count as a task" | Action = task. Check for skills. | +| "The skill is overkill" | Simple things become complex. Use it. | +| "I'll just do this one thing first" | Check BEFORE doing anything. | +| "This feels productive" | Undisciplined action wastes time. Skills prevent this. | +| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. | + +## Skill Priority + +When multiple skills could apply, use this order: + +1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task +2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution + +"Let's build X" → brainstorming first, then implementation skills. +"Fix this bug" → debugging first, then domain-specific skills. + +## Skill Types + +**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline. + +**Flexible** (patterns): Adapt principles to context. + +The skill itself tells you which. + +## User Instructions + +Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows. diff --git a/templates/.agent/skills/verification-before-completion/SKILL.md b/templates/.agent/skills/verification-before-completion/SKILL.md new file mode 100644 index 0000000..2f14076 --- /dev/null +++ b/templates/.agent/skills/verification-before-completion/SKILL.md @@ -0,0 +1,139 @@ +--- +name: verification-before-completion +description: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always +--- + +# Verification Before Completion + +## Overview + +Claiming work is complete without verification is dishonesty, not efficiency. + +**Core principle:** Evidence before claims, always. + +**Violating the letter of this rule is violating the spirit of this rule.** + +## The Iron Law + +``` +NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE +``` + +If you haven't run the verification command in this message, you cannot claim it passes. + +## The Gate Function + +``` +BEFORE claiming any status or expressing satisfaction: + +1. IDENTIFY: What command proves this claim? +2. RUN: Execute the FULL command (fresh, complete) +3. READ: Full output, check exit code, count failures +4. VERIFY: Does output confirm the claim? + - If NO: State actual status with evidence + - If YES: State claim WITH evidence +5. ONLY THEN: Make the claim + +Skip any step = lying, not verifying +``` + +## Common Failures + +| Claim | Requires | Not Sufficient | +|-------|----------|----------------| +| Tests pass | Test command output: 0 failures | Previous run, "should pass" | +| Linter clean | Linter output: 0 errors | Partial check, extrapolation | +| Build succeeds | Build command: exit 0 | Linter passing, logs look good | +| Bug fixed | Test original symptom: passes | Code changed, assumed fixed | +| Regression test works | Red-green cycle verified | Test passes once | +| Agent completed | VCS diff shows changes | Agent reports "success" | +| Requirements met | Line-by-line checklist | Tests passing | + +## Red Flags - STOP + +- Using "should", "probably", "seems to" +- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.) +- About to commit/push/PR without verification +- Trusting agent success reports +- Relying on partial verification +- Thinking "just this once" +- Tired and wanting work over +- **ANY wording implying success without having run verification** + +## Rationalization Prevention + +| Excuse | Reality | +|--------|---------| +| "Should work now" | RUN the verification | +| "I'm confident" | Confidence ≠ evidence | +| "Just this once" | No exceptions | +| "Linter passed" | Linter ≠ compiler | +| "Agent said success" | Verify independently | +| "I'm tired" | Exhaustion ≠ excuse | +| "Partial check is enough" | Partial proves nothing | +| "Different words so rule doesn't apply" | Spirit over letter | + +## Key Patterns + +**Tests:** +``` +✅ [Run test command] [See: 34/34 pass] "All tests pass" +❌ "Should pass now" / "Looks correct" +``` + +**Regression tests (TDD Red-Green):** +``` +✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass) +❌ "I've written a regression test" (without red-green verification) +``` + +**Build:** +``` +✅ [Run build] [See: exit 0] "Build passes" +❌ "Linter passed" (linter doesn't check compilation) +``` + +**Requirements:** +``` +✅ Re-read plan → Create checklist → Verify each → Report gaps or completion +❌ "Tests pass, phase complete" +``` + +**Agent delegation:** +``` +✅ Agent reports success → Check VCS diff → Verify changes → Report actual state +❌ Trust agent report +``` + +## Why This Matters + +From 24 failure memories: +- your human partner said "I don't believe you" - trust broken +- Undefined functions shipped - would crash +- Missing requirements shipped - incomplete features +- Time wasted on false completion → redirect → rework +- Violates: "Honesty is a core value. If you lie, you'll be replaced." + +## When To Apply + +**ALWAYS before:** +- ANY variation of success/completion claims +- ANY expression of satisfaction +- ANY positive statement about work state +- Committing, PR creation, task completion +- Moving to next task +- Delegating to agents + +**Rule applies to:** +- Exact phrases +- Paraphrases and synonyms +- Implications of success +- ANY communication suggesting completion/correctness + +## The Bottom Line + +**No shortcuts for verification.** + +Run the command. Read the output. THEN claim the result. + +This is non-negotiable. diff --git a/templates/.agent/skills/writing-plans/SKILL.md b/templates/.agent/skills/writing-plans/SKILL.md new file mode 100644 index 0000000..b6db2b8 --- /dev/null +++ b/templates/.agent/skills/writing-plans/SKILL.md @@ -0,0 +1,108 @@ +--- +name: writing-plans +description: Use when you have a spec or requirements for a multi-step task, before touching code +--- + +# Writing Plans + +## Overview + +Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits. + +Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well. + +**Announce at start:** "I'm using the writing-plans skill to create the implementation plan." + +**Context:** This should be run in a dedicated worktree (created by brainstorming skill). + +**Save plans to:** `docs/plans/YYYY-MM-DD-<feature-name>.md` + +## Bite-Sized Task Granularity + +**Each step is one action (2-5 minutes):** +- "Write the failing test" - step +- "Run it to make sure it fails" - step +- "Implement the minimal code to make the test pass" - step +- "Run the tests and make sure they pass" - step +- "Commit" - step + +## Plan Document Header + +**Every plan MUST start with this header:** + +```markdown +# [Feature Name] Implementation Plan + +> **For Antigravity:** REQUIRED WORKFLOW: Use `.agent/workflows/execute-plan.md` to execute this plan in single-flow mode. + +**Goal:** [One sentence describing what this builds] + +**Architecture:** [2-3 sentences about approach] + +**Tech Stack:** [Key technologies/libraries] + +--- +``` + +## Task Structure + +````markdown +### Task N: [Component Name] + +**Files:** +- Create: `exact/path/to/file.py` +- Modify: `exact/path/to/existing.py:123-145` +- Test: `tests/exact/path/to/test.py` + +**Step 1: Write the failing test** + +```python +def test_specific_behavior(): + result = function(input) + assert result == expected +``` + +**Step 2: Run test to verify it fails** + +Run: `pytest tests/path/test.py::test_name -v` +Expected: FAIL with "function not defined" + +**Step 3: Write minimal implementation** + +```python +def function(input): + return expected +``` + +**Step 4: Run test to verify it passes** + +Run: `pytest tests/path/test.py::test_name -v` +Expected: PASS + +**Step 5: Commit** + +```bash +git add tests/path/test.py src/path/file.py +git commit -m "feat: add specific feature" +``` +```` + +## Remember +- Exact file paths always +- Complete code in plan (not "add validation") +- Exact commands with expected output +- Reference relevant skills with @ syntax +- DRY, YAGNI, TDD, frequent commits + +## Execution Handoff + +After saving the plan, use a single execution path: + +**"Plan complete and saved to `docs/plans/<filename>.md`.** +**Next step: run `.agent/workflows/execute-plan.md` to execute this plan task-by-task in single-flow mode."** + +Execution requirements: +- **Entry workflow:** `.agent/workflows/execute-plan.md` +- **Execution skill:** `.agent/skills/executing-plans/SKILL.md` +- **Enforced execution model:** `.agent/skills/single-flow-task-execution/SKILL.md` +- **Tracking:** update `<project-root>/docs/plans/task.md` (table-only tracker) diff --git a/templates/.agent/skills/writing-skills/SKILL.md b/templates/.agent/skills/writing-skills/SKILL.md new file mode 100644 index 0000000..dd4df8b --- /dev/null +++ b/templates/.agent/skills/writing-skills/SKILL.md @@ -0,0 +1,716 @@ +--- +name: writing-skills +description: Use when creating new skills, editing existing skills, or verifying skills work before deployment +--- + +# Writing Skills + +## Overview + +**Writing skills IS Test-Driven Development applied to process documentation.** + +**Personal skills live in agent-specific directories (`~/.gemini/skills` for Antigravity)** + +You write test cases (pressure scenarios with explicit task execution), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes). + +**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing. + +**REQUIRED BACKGROUND:** You MUST understand `.agent/skills/test-driven-development/SKILL.md` before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill adapts TDD to documentation. + +**Official guidance:** For Antigravity's official skill authoring best practices, see antigravity-best-practices.md. This document provides additional patterns and guidelines that complement the TDD-focused approach in this skill. + +## What is a Skill? + +A **skill** is a reference guide for proven techniques, patterns, or tools. Skills help future Antigravity sessions find and apply effective approaches. + +**Skills are:** Reusable techniques, patterns, tools, reference guides + +**Skills are NOT:** Narratives about how you solved a problem once + +## TDD Mapping for Skills + +| TDD Concept | Skill Creation | +| ----------------------- | ------------------------------------------------ | +| **Test case** | Pressure scenario with explicit task execution | +| **Production code** | Skill document (SKILL.md) | +| **Test fails (RED)** | Agent violates rule without skill (baseline) | +| **Test passes (GREEN)** | Agent complies with skill present | +| **Refactor** | Close loopholes while maintaining compliance | +| **Write test first** | Run baseline scenario BEFORE writing skill | +| **Watch it fail** | Document exact rationalizations agent uses | +| **Minimal code** | Write skill addressing those specific violations | +| **Watch it pass** | Verify agent now complies | +| **Refactor cycle** | Find new rationalizations → plug → re-verify | + +The entire skill creation process follows RED-GREEN-REFACTOR. + +## When to Create a Skill + +**Create when:** + +- Technique wasn't intuitively obvious to you +- You'd reference this again across projects +- Pattern applies broadly (not project-specific) +- Others would benefit + +**Don't create for:** + +- One-off solutions +- Standard practices well-documented elsewhere +- Project-specific conventions (put in `.agent/AGENTS.md`) +- Mechanical constraints (if it's enforceable with regex/validation, automate it—save documentation for judgment calls) + +## Skill Types + +### Technique + +Concrete method with steps to follow (condition-based-waiting, root-cause-tracing) + +### Pattern + +Way of thinking about problems (flatten-with-flags, test-invariants) + +### Reference + +API docs, syntax guides, tool documentation (office docs) + +## Directory Structure + +``` +skills/ + skill-name/ + SKILL.md # Main reference (required) + supporting-file.* # Only if needed +``` + +**Flat namespace** - all skills in one searchable namespace + +**Separate files for:** + +1. **Heavy reference** (100+ lines) - API docs, comprehensive syntax +2. **Reusable tools** - Scripts, utilities, templates + +**Keep inline:** + +- Principles and concepts +- Code patterns (< 50 lines) +- Everything else + +## SKILL.md Structure + +**Frontmatter (YAML):** + +- Only two fields supported: `name` and `description` +- Max 1024 characters total +- `name`: Use letters, numbers, and hyphens only (no parentheses, special chars) +- `description`: Third-person, describes ONLY when to use (NOT what it does) + - Start with "Use when..." to focus on triggering conditions + - Include specific symptoms, situations, and contexts + - **NEVER summarize the skill's process or workflow** (see CSO section for why) + - Keep under 500 characters if possible + +```markdown +--- +name: Skill-Name-With-Hyphens +description: Use when [specific triggering conditions and symptoms] +--- + +# Skill Name + +## Overview + +What is this? Core principle in 1-2 sentences. + +## When to Use + +[Small inline flowchart IF decision non-obvious] + +Bullet list with SYMPTOMS and use cases +When NOT to use + +## Core Pattern (for techniques/patterns) + +Before/after code comparison + +## Quick Reference + +Table or bullets for scanning common operations + +## Implementation + +Inline code for simple patterns +Link to file for heavy reference or reusable tools + +## Common Mistakes + +What goes wrong + fixes + +## Real-World Impact (optional) + +Concrete results +``` + +## Antigravity Search Optimization (CSO) + +**Critical for discovery:** Future Antigravity needs to FIND your skill + +### 1. Rich Description Field + +**Purpose:** Antigravity reads description to decide which skills to load for a given task. Make it answer: "Should I read this skill right now?" + +**Format:** Start with "Use when..." to focus on triggering conditions + +**CRITICAL: Description = When to Use, NOT What the Skill Does** + +The description should ONLY describe triggering conditions. Do NOT summarize the skill's process or workflow in the description. + +**Why this matters:** Testing revealed that when a description summarizes the skill's workflow, Antigravity may follow the description instead of reading the full skill content. A description saying "code review between tasks" caused Antigravity to do ONE review, even though the skill's flowchart clearly showed TWO reviews (spec compliance then code quality). + +When the description was changed to just "Use when executing implementation plans with independent tasks" (no workflow summary), Antigravity correctly read the flowchart and followed the two-stage review process. + +**The trap:** Descriptions that summarize workflow create a shortcut Antigravity will take. The skill body becomes documentation Antigravity skips. + +```yaml +# ❌ BAD: Summarizes workflow - Antigravity may follow this instead of reading skill +description: Use when executing plans - executes tasks sequentially with code review between tasks + +# ❌ BAD: Too much process detail +description: Use for TDD - write test first, watch it fail, write minimal code, refactor + +# ✅ GOOD: Just triggering conditions, no workflow summary +description: Use when executing implementation plans with independent tasks in the current session + +# ✅ GOOD: Triggering conditions only +description: Use when implementing any feature or bugfix, before writing implementation code +``` + +**Content:** + +- Use concrete triggers, symptoms, and situations that signal this skill applies +- Describe the _problem_ (race conditions, inconsistent behavior) not _language-specific symptoms_ (setTimeout, sleep) +- Keep triggers technology-agnostic unless the skill itself is technology-specific +- If skill is technology-specific, make that explicit in the trigger +- Write in third person (injected into system prompt) +- **NEVER summarize the skill's process or workflow** + +```yaml +# ❌ BAD: Too abstract, vague, doesn't include when to use +description: For async testing + +# ❌ BAD: First person +description: I can help you with async tests when they're flaky + +# ❌ BAD: Mentions technology but skill isn't specific to it +description: Use when tests use setTimeout/sleep and are flaky + +# ✅ GOOD: Starts with "Use when", describes problem, no workflow +description: Use when tests have race conditions, timing dependencies, or pass/fail inconsistently + +# ✅ GOOD: Technology-specific skill with explicit trigger +description: Use when using React Router and handling authentication redirects +``` + +### 2. Keyword Coverage + +Use words Antigravity would search for: + +- Error messages: "Hook timed out", "ENOTEMPTY", "race condition" +- Symptoms: "flaky", "hanging", "zombie", "pollution" +- Synonyms: "timeout/hang/freeze", "cleanup/teardown/afterEach" +- Tools: Actual commands, library names, file types + +### 3. Descriptive Naming + +**Use active voice, verb-first:** + +- ✅ `creating-skills` not `skill-creation` +- ✅ `condition-based-waiting` not `async-test-helpers` + +### 4. Token Efficiency (Critical) + +**Problem:** getting-started and frequently-referenced skills load into EVERY conversation. Every token counts. + +**Target word counts:** + +- getting-started workflows: <150 words each +- Frequently-loaded skills: <200 words total +- Other skills: <500 words (still be concise) + +**Techniques:** + +**Move details to tool help:** + +```bash +# ❌ BAD: Document all flags in SKILL.md +search-conversations supports --text, --both, --after DATE, --before DATE, --limit N + +# ✅ GOOD: Reference --help +search-conversations supports multiple modes and filters. Run --help for details. +``` + +**Use cross-references:** + +```markdown +# ❌ BAD: Repeat workflow details + +When searching, run task steps without a reusable template... +[20 lines of repeated instructions] + +# ✅ GOOD: Reference other skill + +Always use explicit workflow skill references. REQUIRED: Use [other-skill-name] for workflow. +``` + +**Compress examples:** + +```markdown +# ❌ BAD: Verbose example (42 words) + +your human partner: "How did we handle authentication errors in React Router before?" +You: I'll search past conversations for React Router authentication patterns. +[Run task_boundary search: "React Router authentication error handling 401"] + +# ✅ GOOD: Minimal example (20 words) + +Partner: "How did we handle auth errors in React Router?" +You: Searching... +[Run synthesis step] +``` + +**Eliminate redundancy:** + +- Don't repeat what's in cross-referenced skills +- Don't explain what's obvious from command +- Don't include multiple examples of same pattern + +**Verification:** + +```bash +wc -w skills/path/SKILL.md +# getting-started workflows: aim for <150 each +# Other frequently-loaded: aim for <200 total +``` + +**Name by what you DO or core insight:** + +- ✅ `condition-based-waiting` > `async-test-helpers` +- ✅ `using-skills` not `skill-usage` +- ✅ `flatten-with-flags` > `data-structure-refactoring` +- ✅ `root-cause-tracing` > `debugging-techniques` + +**Gerunds (-ing) work well for processes:** + +- `creating-skills`, `testing-skills`, `debugging-with-logs` +- Active, describes the action you're taking + +### 4. Cross-Referencing Other Skills + +**When writing documentation that references other skills:** + +Use skill name only, with explicit requirement markers: + +- ✅ Good: `**REQUIRED SKILL:** Use .agent/skills/test-driven-development/SKILL.md` +- ✅ Good: `**REQUIRED BACKGROUND:** You MUST understand .agent/skills/systematic-debugging/SKILL.md` +- ❌ Bad: `See skills/testing/test-driven-development` (unclear if required) +- ❌ Bad: `@skills/testing/test-driven-development/SKILL.md` (force-loads, burns context) + +**Why no @ links:** `@` syntax force-loads files immediately, consuming 200k+ context before you need them. + +## Flowchart Usage + +```dot +digraph when_flowchart { + "Need to show information?" [shape=diamond]; + "Decision where I might go wrong?" [shape=diamond]; + "Use markdown" [shape=box]; + "Small inline flowchart" [shape=box]; + + "Need to show information?" -> "Decision where I might go wrong?" [label="yes"]; + "Decision where I might go wrong?" -> "Small inline flowchart" [label="yes"]; + "Decision where I might go wrong?" -> "Use markdown" [label="no"]; +} +``` + +**Use flowcharts ONLY for:** + +- Non-obvious decision points +- Process loops where you might stop too early +- "When to use A vs B" decisions + +**Never use flowcharts for:** + +- Reference material → Tables, lists +- Code examples → Markdown blocks +- Linear instructions → Numbered lists +- Labels without semantic meaning (step1, helper2) + +See @graphviz-conventions.dot for graphviz style rules. + +**Visualizing for your human partner:** Use `render-graphs.js` in this directory to render a skill's flowcharts to SVG: + +```bash +./render-graphs.js ../some-skill # Each diagram separately +./render-graphs.js ../some-skill --combine # All diagrams in one SVG +``` + +## Code Examples + +**One excellent example beats many mediocre ones** + +Choose most relevant language: + +- Testing techniques → TypeScript/JavaScript +- System debugging → Shell/Python +- Data processing → Python + +**Good example:** + +- Complete and runnable +- Well-commented explaining WHY +- From real scenario +- Shows pattern clearly +- Ready to adapt (not generic template) + +**Don't:** + +- Implement in 5+ languages +- Create fill-in-the-blank templates +- Write contrived examples + +You're good at porting - one great example is enough. + +## File Organization + +### Self-Contained Skill + +``` +defense-in-depth/ + SKILL.md # Everything inline +``` + +When: All content fits, no heavy reference needed + +### Skill with Reusable Tool + +``` +condition-based-waiting/ + SKILL.md # Overview + patterns + example.ts # Working helpers to adapt +``` + +When: Tool is reusable code, not just narrative + +### Skill with Heavy Reference + +``` +pptx/ + SKILL.md # Overview + workflows + pptxgenjs.md # 600 lines API reference + ooxml.md # 500 lines XML structure + scripts/ # Executable tools +``` + +When: Reference material too large for inline + +## The Iron Law (Same as TDD) + +``` +NO SKILL WITHOUT A FAILING TEST FIRST +``` + +This applies to NEW skills AND EDITS to existing skills. + +Write skill before testing? Delete it. Start over. +Edit skill without testing? Same violation. + +**No exceptions:** + +- Not for "simple additions" +- Not for "just adding a section" +- Not for "documentation updates" +- Don't keep untested changes as "reference" +- Don't "adapt" while running tests +- Delete means delete + +**REQUIRED BACKGROUND:** `.agent/skills/test-driven-development/SKILL.md` explains why this matters. Same principles apply to documentation. + +## Testing All Skill Types + +Different skill types need different test approaches: + +### Discipline-Enforcing Skills (rules/requirements) + +**Examples:** TDD, verification-before-completion, designing-before-coding + +**Test with:** + +- Academic questions: Do they understand the rules? +- Pressure scenarios: Do they comply under stress? +- Multiple pressures combined: time + sunk cost + exhaustion +- Identify rationalizations and add explicit counters + +**Success criteria:** Agent follows rule under maximum pressure + +### Technique Skills (how-to guides) + +**Examples:** condition-based-waiting, root-cause-tracing, defensive-programming + +**Test with:** + +- Application scenarios: Can they apply the technique correctly? +- Variation scenarios: Do they handle edge cases? +- Missing information tests: Do instructions have gaps? + +**Success criteria:** Agent successfully applies technique to new scenario + +### Pattern Skills (mental models) + +**Examples:** reducing-complexity, information-hiding concepts + +**Test with:** + +- Recognition scenarios: Do they recognize when pattern applies? +- Application scenarios: Can they use the mental model? +- Counter-examples: Do they know when NOT to apply? + +**Success criteria:** Agent correctly identifies when/how to apply pattern + +### Reference Skills (documentation/APIs) + +**Examples:** API documentation, command references, library guides + +**Test with:** + +- Retrieval scenarios: Can they find the right information? +- Application scenarios: Can they use what they found correctly? +- Gap testing: Are common use cases covered? + +**Success criteria:** Agent finds and correctly applies reference information + +## Common Rationalizations for Skipping Testing + +| Excuse | Reality | +| ------------------------------ | ---------------------------------------------------------------- | +| "Skill is obviously clear" | Clear to you ≠ clear to other agents. Test it. | +| "It's just a reference" | References can have gaps, unclear sections. Test retrieval. | +| "Testing is overkill" | Untested skills have issues. Always. 15 min testing saves hours. | +| "I'll test if problems emerge" | Problems = agents can't use skill. Test BEFORE deploying. | +| "Too tedious to test" | Testing is less tedious than debugging bad skill in production. | +| "I'm confident it's good" | Overconfidence guarantees issues. Test anyway. | +| "Academic review is enough" | Reading ≠ using. Test application scenarios. | +| "No time to test" | Deploying untested skill wastes more time fixing it later. | + +**All of these mean: Test before deploying. No exceptions.** + +## Bulletproofing Skills Against Rationalization + +Skills that enforce discipline (like TDD) need to resist rationalization. Agents are smart and will find loopholes when under pressure. + +**Psychology note:** Understanding WHY persuasion techniques work helps you apply them systematically. See persuasion-principles.md for research foundation (Cialdini, 2021; Meincke et al., 2025) on authority, commitment, scarcity, social proof, and unity principles. + +### Close Every Loophole Explicitly + +Don't just state the rule - forbid specific workarounds: + +<Bad> +```markdown +Write code before test? Delete it. +``` +</Bad> + +<Good> +```markdown +Write code before test? Delete it. Start over. + +**No exceptions:** + +- Don't keep it as "reference" +- Don't "adapt" it while writing tests +- Don't look at it +- Delete means delete + +```` +</Good> + +### Address "Spirit vs Letter" Arguments + +Add foundational principle early: + +```markdown +**Violating the letter of the rules is violating the spirit of the rules.** +```` + +This cuts off entire class of "I'm following the spirit" rationalizations. + +### Build Rationalization Table + +Capture rationalizations from baseline testing (see Testing section below). Every excuse agents make goes in the table: + +```markdown +| Excuse | Reality | +| -------------------------------- | ----------------------------------------------------------------------- | +| "Too simple to test" | Simple code breaks. Test takes 30 seconds. | +| "I'll test after" | Tests passing immediately prove nothing. | +| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" | +``` + +### Create Red Flags List + +Make it easy for agents to self-check when rationalizing: + +```markdown +## Red Flags - STOP and Start Over + +- Code before test +- "I already manually tested it" +- "Tests after achieve the same purpose" +- "It's about spirit not ritual" +- "This is different because..." + +**All of these mean: Delete code. Start over with TDD.** +``` + +### Update CSO for Violation Symptoms + +Add to description: symptoms of when you're ABOUT to violate the rule: + +```yaml +description: use when implementing any feature or bugfix, before writing implementation code +``` + +## RED-GREEN-REFACTOR for Skills + +Follow the TDD cycle: + +### RED: Write Failing Test (Baseline) + +Run pressure scenario with explicit task execution WITHOUT the skill. Document exact behavior: + +- What choices did they make? +- What rationalizations did they use (verbatim)? +- Which pressures triggered violations? + +This is "watch the test fail" - you must see what agents naturally do before writing the skill. + +### GREEN: Write Minimal Skill + +Write skill that addresses those specific rationalizations. Don't add extra content for hypothetical cases. + +Run same scenarios WITH skill. Agent should now comply. + +### REFACTOR: Close Loopholes + +Agent found new rationalization? Add explicit counter. Re-test until bulletproof. + +**Testing methodology:** See @testing-skills-with-subagents.md for the complete testing methodology: + +- How to write pressure scenarios +- Pressure types (time, sunk cost, authority, exhaustion) +- Plugging holes systematically +- Meta-testing techniques + +## Anti-Patterns + +### ❌ Narrative Example + +"In session 2025-10-03, we found empty projectDir caused..." +**Why bad:** Too specific, not reusable + +### ❌ Multi-Language Dilution + +example-js.js, example-py.py, example-go.go +**Why bad:** Mediocre quality, maintenance burden + +### ❌ Code in Flowcharts + +```dot +step1 [label="import fs"]; +step2 [label="read file"]; +``` + +**Why bad:** Can't copy-paste, hard to read + +### ❌ Generic Labels + +helper1, helper2, step3, pattern4 +**Why bad:** Labels should have semantic meaning + +## STOP: Before Moving to Next Skill + +**After writing ANY skill, you MUST STOP and complete the deployment process.** + +**Do NOT:** + +- Create multiple skills in batch without testing each +- Move to next skill before current one is verified +- Skip testing because "batching is more efficient" + +**The deployment checklist below is MANDATORY for EACH skill.** + +Deploying untested skills = deploying untested code. It's a violation of quality standards. + +## Skill Creation Checklist (TDD Adapted) + +**IMPORTANT: Update `<project-root>/docs/plans/task.md` for EACH checklist item below (table-only tracker, no instructions).** + +**RED Phase - Write Failing Test:** + +- [ ] Create pressure scenarios (3+ combined pressures for discipline skills) +- [ ] Run scenarios WITHOUT skill - document baseline behavior verbatim +- [ ] Identify patterns in rationalizations/failures + +**GREEN Phase - Write Minimal Skill:** + +- [ ] Name uses only letters, numbers, hyphens (no parentheses/special chars) +- [ ] YAML frontmatter with only name and description (max 1024 chars) +- [ ] Description starts with "Use when..." and includes specific triggers/symptoms +- [ ] Description written in third person +- [ ] Keywords throughout for search (errors, symptoms, tools) +- [ ] Clear overview with core principle +- [ ] Address specific baseline failures identified in RED +- [ ] Code inline OR link to separate file +- [ ] One excellent example (not multi-language) +- [ ] Run scenarios WITH skill - verify agents now comply + +**REFACTOR Phase - Close Loopholes:** + +- [ ] Identify NEW rationalizations from testing +- [ ] Add explicit counters (if discipline skill) +- [ ] Build rationalization table from all test iterations +- [ ] Create red flags list +- [ ] Re-test until bulletproof + +**Quality Checks:** + +- [ ] Small flowchart only if decision non-obvious +- [ ] Quick reference table +- [ ] Common mistakes section +- [ ] No narrative storytelling +- [ ] Supporting files only for tools or heavy reference + +**Deployment:** + +- [ ] Commit skill to git and push to your fork (if configured) +- [ ] Consider contributing back via PR (if broadly useful) + +## Discovery Workflow + +How future Antigravity finds your skill: + +1. **Encounters problem** ("tests are flaky") +2. **Finds SKILL** (description matches) +3. **Scans overview** (is this relevant?) +4. **Reads patterns** (quick reference table) +5. **Loads example** (only when implementing) + +**Optimize for this flow** - put searchable terms early and often. + +## The Bottom Line + +**Creating skills IS TDD for process documentation.** + +Same Iron Law: No skill without failing test first. +Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes). +Same benefits: Better quality, fewer surprises, bulletproof results. + +If you follow TDD for code, follow it for skills. It's the same discipline applied to documentation. diff --git a/templates/.agent/skills/writing-skills/antigravity-best-practices.md b/templates/.agent/skills/writing-skills/antigravity-best-practices.md new file mode 100644 index 0000000..c525ae4 --- /dev/null +++ b/templates/.agent/skills/writing-skills/antigravity-best-practices.md @@ -0,0 +1,1173 @@ +# Skill authoring best practices + +> Learn how to write effective Skills that Antigravity can discover and use successfully. + +Good Skills are concise, well-structured, and tested with real usage. This guide provides practical authoring decisions to help you write Skills that Antigravity can discover and use effectively. + +For conceptual background on how Skills work, see the [Skills overview](/en/docs/agents-and-tools/agent-skills/overview). + +## Core principles + +### Concise is key + +The [context window](https://platform.gemini.com/docs/en/build-with-antigravity/context-windows) is a public good. Your Skill shares the context window with everything else Antigravity needs to know, including: + +- The system prompt +- Conversation history +- Other Skills' metadata +- Your actual request + +Not every token in your Skill has an immediate cost. At startup, only the metadata (name and description) from all Skills is pre-loaded. Antigravity reads SKILL.md only when the Skill becomes relevant, and reads additional files only as needed. However, being concise in SKILL.md still matters: once Antigravity loads it, every token competes with conversation history and other context. + +**Default assumption**: Antigravity is already very smart + +Only add context Antigravity doesn't already have. Challenge each piece of information: + +- "Does Antigravity really need this explanation?" +- "Can I assume Antigravity knows this?" +- "Does this paragraph justify its token cost?" + +**Good example: Concise** (approximately 50 tokens): + +````markdown theme={null} +## Extract PDF text + +Use pdfplumber for text extraction: + +```python +import pdfplumber + +with pdfplumber.open("file.pdf") as pdf: + text = pdf.pages[0].extract_text() +``` +```` + +**Bad example: Too verbose** (approximately 150 tokens): + +```markdown theme={null} +## Extract PDF text + +PDF (Portable Document Format) files are a common file format that contains +text, images, and other content. To extract text from a PDF, you'll need to +use a library. There are many libraries available for PDF processing, but we +recommend pdfplumber because it's easy to use and handles most cases well. +First, you'll need to install it using pip. Then you can use the code below... +``` + +The concise version assumes Antigravity knows what PDFs are and how libraries work. + +### Set appropriate degrees of freedom + +Match the level of specificity to the task's fragility and variability. + +**High freedom** (text-based instructions): + +Use when: + +- Multiple approaches are valid +- Decisions depend on context +- Heuristics guide the approach + +Example: + +```markdown theme={null} +## Code review process + +1. Analyze the code structure and organization +2. Check for potential bugs or edge cases +3. Suggest improvements for readability and maintainability +4. Verify adherence to project conventions +``` + +**Medium freedom** (pseudocode or scripts with parameters): + +Use when: + +- A preferred pattern exists +- Some variation is acceptable +- Configuration affects behavior + +Example: + +````markdown theme={null} +## Generate report + +Use this template and customize as needed: + +```python +def generate_report(data, format="markdown", include_charts=True): + # Process data + # Generate output in specified format + # Optionally include visualizations +``` +```` + +**Low freedom** (specific scripts, few or no parameters): + +Use when: + +- Operations are fragile and error-prone +- Consistency is critical +- A specific sequence must be followed + +Example: + +````markdown theme={null} +## Database migration + +Run exactly this script: + +```bash +python scripts/migrate.py --verify --backup +``` + +Do not modify the command or add additional flags. +```` + +**Analogy**: Think of Antigravity as a robot exploring a path: + +- **Narrow bridge with cliffs on both sides**: There's only one safe way forward. Provide specific guardrails and exact instructions (low freedom). Example: database migrations that must run in exact sequence. +- **Open field with no hazards**: Many paths lead to success. Give general direction and trust Antigravity to find the best route (high freedom). Example: code reviews where context determines the best approach. + +### Test with all models you plan to use + +Skills act as additions to models, so effectiveness depends on the underlying model. Test your Skill with all the models you plan to use it with. + +**Testing considerations by model**: + +- **Gemini Flash** (fast, economical): Does the Skill provide enough guidance? +- **Gemini Pro** (balanced): Is the Skill clear and efficient? +- **Gemini Ultra** (powerful reasoning): Does the Skill avoid over-explaining? + +What works perfectly for Ultra might need more detail for Flash. If you plan to use your Skill across multiple models, aim for instructions that work well with all of them. + +## Skill structure + +<Note> + **YAML Frontmatter**: The SKILL.md frontmatter supports two fields: + +- `name` - Human-readable name of the Skill (64 characters maximum) +- `description` - One-line description of what the Skill does and when to use it (1024 characters maximum) + +For complete Skill structure details, see the [Skills overview](/en/docs/agents-and-tools/agent-skills/overview#skill-structure). +</Note> + +### Naming conventions + +Use consistent naming patterns to make Skills easier to reference and discuss. We recommend using **gerund form** (verb + -ing) for Skill names, as this clearly describes the activity or capability the Skill provides. + +**Good naming examples (gerund form)**: + +- "Processing PDFs" +- "Analyzing spreadsheets" +- "Managing databases" +- "Testing code" +- "Writing documentation" + +**Acceptable alternatives**: + +- Noun phrases: "PDF Processing", "Spreadsheet Analysis" +- Action-oriented: "Process PDFs", "Analyze Spreadsheets" + +**Avoid**: + +- Vague names: "Helper", "Utils", "Tools" +- Overly generic: "Documents", "Data", "Files" +- Inconsistent patterns within your skill collection + +Consistent naming makes it easier to: + +- Reference Skills in documentation and conversations +- Understand what a Skill does at a glance +- Organize and search through multiple Skills +- Maintain a professional, cohesive skill library + +### Writing effective descriptions + +The `description` field enables Skill discovery and should include both what the Skill does and when to use it. + +<Warning> + **Always write in third person**. The description is injected into the system prompt, and inconsistent point-of-view can cause discovery problems. + +- **Good:** "Processes Excel files and generates reports" +- **Avoid:** "I can help you process Excel files" +- **Avoid:** "You can use this to process Excel files" + </Warning> + +**Be specific and include key terms**. Include both what the Skill does and specific triggers/contexts for when to use it. + +Each Skill has exactly one description field. The description is critical for skill selection: Antigravity uses it to choose the right Skill from potentially 100+ available Skills. Your description must provide enough detail for Antigravity to know when to select this Skill, while the rest of SKILL.md provides the implementation details. + +Effective examples: + +**PDF Processing skill:** + +```yaml theme={null} +description: Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction. +``` + +**Excel Analysis skill:** + +```yaml theme={null} +description: Analyze Excel spreadsheets, create pivot tables, generate charts. Use when analyzing Excel files, spreadsheets, tabular data, or .xlsx files. +``` + +**Git Commit Helper skill:** + +```yaml theme={null} +description: Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes. +``` + +Avoid vague descriptions like these: + +```yaml theme={null} +description: Helps with documents +``` + +```yaml theme={null} +description: Processes data +``` + +```yaml theme={null} +description: Does stuff with files +``` + +### Progressive disclosure patterns + +SKILL.md serves as an overview that points Antigravity to detailed materials as needed, like a table of contents in an onboarding guide. For an explanation of how progressive disclosure works, see [How Skills work](/en/docs/agents-and-tools/agent-skills/overview#how-skills-work) in the overview. + +**Practical guidance:** + +- Keep SKILL.md body under 500 lines for optimal performance +- Split content into separate files when approaching this limit +- Use the patterns below to organize instructions, code, and resources effectively + +#### Visual overview: From simple to complex + +A basic Skill starts with just a SKILL.md file containing metadata and instructions: + +<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=87782ff239b297d9a9e8e1b72ed72db9" alt="Simple SKILL.md file showing YAML frontmatter and markdown body" data-og-width="2048" width="2048" data-og-height="1153" height="1153" data-path="images/agent-skills-simple-file.png" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=280&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=c61cc33b6f5855809907f7fda94cd80e 280w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=560&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=90d2c0c1c76b36e8d485f49e0810dbfd 560w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=840&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=ad17d231ac7b0bea7e5b4d58fb4aeabb 840w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=1100&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=f5d0a7a3c668435bb0aee9a3a8f8c329 1100w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=1650&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=0e927c1af9de5799cfe557d12249f6e6 1650w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=2500&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=46bbb1a51dd4c8202a470ac8c80a893d 2500w" /> + +As your Skill grows, you can bundle additional content that Antigravity loads only when needed: + +<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=a5e0aa41e3d53985a7e3e43668a33ea3" alt="Bundling additional reference files like reference.md and forms.md." data-og-width="2048" width="2048" data-og-height="1327" height="1327" data-path="images/agent-skills-bundling-content.png" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=280&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=f8a0e73783e99b4a643d79eac86b70a2 280w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=560&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=dc510a2a9d3f14359416b706f067904a 560w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=840&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=82cd6286c966303f7dd914c28170e385 840w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=1100&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=56f3be36c77e4fe4b523df209a6824c6 1100w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=1650&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=d22b5161b2075656417d56f41a74f3dd 1650w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=2500&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=3dd4bdd6850ffcc96c6c45fcb0acd6eb 2500w" /> + +The complete Skill directory structure might look like this: + +``` +pdf/ +├── SKILL.md # Main instructions (loaded when triggered) +├── FORMS.md # Form-filling guide (loaded as needed) +├── reference.md # API reference (loaded as needed) +├── examples.md # Usage examples (loaded as needed) +└── scripts/ + ├── analyze_form.py # Utility script (executed, not loaded) + ├── fill_form.py # Form filling script + └── validate.py # Validation script +``` + +#### Pattern 1: High-level guide with references + +````markdown theme={null} +--- +name: PDF Processing +description: Extracts text and tables from PDF files, fills forms, and merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction. +--- + +# PDF Processing + +## Quick start + +Extract text with pdfplumber: + +```python +import pdfplumber +with pdfplumber.open("file.pdf") as pdf: + text = pdf.pages[0].extract_text() +``` + +## Advanced features + +**Form filling**: See [FORMS.md](FORMS.md) for complete guide +**API reference**: See [REFERENCE.md](REFERENCE.md) for all methods +**Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns +```` + +Antigravity loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed. + +#### Pattern 2: Domain-specific organization + +For Skills with multiple domains, organize content by domain to avoid loading irrelevant context. When a user asks about sales metrics, Antigravity only needs to read sales-related schemas, not finance or marketing data. This keeps token usage low and context focused. + +``` +bigquery-skill/ +├── SKILL.md (overview and navigation) +└── reference/ + ├── finance.md (revenue, billing metrics) + ├── sales.md (opportunities, pipeline) + ├── product.md (API usage, features) + └── marketing.md (campaigns, attribution) +``` + +````markdown SKILL.md theme={null} +# BigQuery Data Analysis + +## Available datasets + +**Finance**: Revenue, ARR, billing → See [reference/finance.md](reference/finance.md) +**Sales**: Opportunities, pipeline, accounts → See [reference/sales.md](reference/sales.md) +**Product**: API usage, features, adoption → See [reference/product.md](reference/product.md) +**Marketing**: Campaigns, attribution, email → See [reference/marketing.md](reference/marketing.md) + +## Quick search + +Find specific metrics using grep: + +```bash +grep -i "revenue" reference/finance.md +grep -i "pipeline" reference/sales.md +grep -i "api usage" reference/product.md +``` +```` + +#### Pattern 3: Conditional details + +Show basic content, link to advanced content: + +```markdown theme={null} +# DOCX Processing + +## Creating documents + +Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md). + +## Editing documents + +For simple edits, modify the XML directly. + +**For tracked changes**: See [REDLINING.md](REDLINING.md) +**For OOXML details**: See [OOXML.md](OOXML.md) +``` + +Antigravity reads REDLINING.md or OOXML.md only when the user needs those features. + +### Avoid deeply nested references + +Antigravity may partially read files when they're referenced from other referenced files. When encountering nested references, Antigravity might use commands like `head -100` to preview content rather than reading entire files, resulting in incomplete information. + +**Keep references one level deep from SKILL.md**. All reference files should link directly from SKILL.md to ensure Antigravity reads complete files when needed. + +**Bad example: Too deep**: + +```markdown theme={null} +# SKILL.md + +See [advanced.md](advanced.md)... + +# advanced.md + +See [details.md](details.md)... + +# details.md + +Here's the actual information... +``` + +**Good example: One level deep**: + +```markdown theme={null} +# SKILL.md + +**Basic usage**: [instructions in SKILL.md] +**Advanced features**: See [advanced.md](advanced.md) +**API reference**: See [reference.md](reference.md) +**Examples**: See [examples.md](examples.md) +``` + +### Structure longer reference files with table of contents + +For reference files longer than 100 lines, include a table of contents at the top. This ensures Antigravity can see the full scope of available information even when previewing with partial reads. + +**Example**: + +```markdown theme={null} +# API Reference + +## Contents + +- Authentication and setup +- Core methods (create, read, update, delete) +- Advanced features (batch operations, webhooks) +- Error handling patterns +- Code examples + +## Authentication and setup + +... + +## Core methods + +... +``` + +Antigravity can then read the complete file or jump to specific sections as needed. + +For details on how this filesystem-based architecture enables progressive disclosure, see the [Runtime environment](#runtime-environment) section in the Advanced section below. + +## Workflows and feedback loops + +### Use workflows for complex tasks + +Break complex operations into clear, sequential steps. For particularly complex workflows, provide a checklist that Antigravity can copy into its response and check off as it progresses. + +**Example 1: Research synthesis workflow** (for Skills without code): + +````markdown theme={null} +## Research synthesis workflow + +Copy this checklist and track your progress: + +``` +Research Progress: +- [ ] Step 1: Read all source documents +- [ ] Step 2: Identify key themes +- [ ] Step 3: Cross-reference claims +- [ ] Step 4: Create structured summary +- [ ] Step 5: Verify citations +``` + +**Step 1: Read all source documents** + +Review each document in the `sources/` directory. Note the main arguments and supporting evidence. + +**Step 2: Identify key themes** + +Look for patterns across sources. What themes appear repeatedly? Where do sources agree or disagree? + +**Step 3: Cross-reference claims** + +For each major claim, verify it appears in the source material. Note which source supports each point. + +**Step 4: Create structured summary** + +Organize findings by theme. Include: + +- Main claim +- Supporting evidence from sources +- Conflicting viewpoints (if any) + +**Step 5: Verify citations** + +Check that every claim references the correct source document. If citations are incomplete, return to Step 3. +```` + +This example shows how workflows apply to analysis tasks that don't require code. The checklist pattern works for any complex, multi-step process. + +**Example 2: PDF form filling workflow** (for Skills with code): + +````markdown theme={null} +## PDF form filling workflow + +Copy this checklist and check off items as you complete them: + +``` +Task Progress: +- [ ] Step 1: Analyze the form (run analyze_form.py) +- [ ] Step 2: Create field mapping (edit fields.json) +- [ ] Step 3: Validate mapping (run validate_fields.py) +- [ ] Step 4: Fill the form (run fill_form.py) +- [ ] Step 5: Verify output (run verify_output.py) +``` + +**Step 1: Analyze the form** + +Run: `python scripts/analyze_form.py input.pdf` + +This extracts form fields and their locations, saving to `fields.json`. + +**Step 2: Create field mapping** + +Edit `fields.json` to add values for each field. + +**Step 3: Validate mapping** + +Run: `python scripts/validate_fields.py fields.json` + +Fix any validation errors before continuing. + +**Step 4: Fill the form** + +Run: `python scripts/fill_form.py input.pdf fields.json output.pdf` + +**Step 5: Verify output** + +Run: `python scripts/verify_output.py output.pdf` + +If verification fails, return to Step 2. +```` + +Clear steps prevent Antigravity from skipping critical validation. The checklist helps both Antigravity and you track progress through multi-step workflows. + +### Implement feedback loops + +**Common pattern**: Run validator → fix errors → repeat + +This pattern greatly improves output quality. + +**Example 1: Style guide compliance** (for Skills without code): + +```markdown theme={null} +## Content review process + +1. Draft your content following the guidelines in STYLE_GUIDE.md +2. Review against the checklist: + - Check terminology consistency + - Verify examples follow the standard format + - Confirm all required sections are present +3. If issues found: + - Note each issue with specific section reference + - Revise the content + - Review the checklist again +4. Only proceed when all requirements are met +5. Finalize and save the document +``` + +This shows the validation loop pattern using reference documents instead of scripts. The "validator" is STYLE_GUIDE.md, and Antigravity performs the check by reading and comparing. + +**Example 2: Document editing process** (for Skills with code): + +```markdown theme={null} +## Document editing process + +1. Make your edits to `word/document.xml` +2. **Validate immediately**: `python ooxml/scripts/validate.py unpacked_dir/` +3. If validation fails: + - Review the error message carefully + - Fix the issues in the XML + - Run validation again +4. **Only proceed when validation passes** +5. Rebuild: `python ooxml/scripts/pack.py unpacked_dir/ output.docx` +6. Test the output document +``` + +The validation loop catches errors early. + +## Content guidelines + +### Avoid time-sensitive information + +Don't include information that will become outdated: + +**Bad example: Time-sensitive** (will become wrong): + +```markdown theme={null} +If you're doing this before August 2025, use the old API. +After August 2025, use the new API. +``` + +**Good example** (use "old patterns" section): + +```markdown theme={null} +## Current method + +Use the v2 API endpoint: `api.example.com/v2/messages` + +## Old patterns + +<details> +<summary>Legacy v1 API (deprecated 2025-08)</summary> + +The v1 API used: `api.example.com/v1/messages` + +This endpoint is no longer supported. + +</details> +``` + +The old patterns section provides historical context without cluttering the main content. + +### Use consistent terminology + +Choose one term and use it throughout the Skill: + +**Good - Consistent**: + +- Always "API endpoint" +- Always "field" +- Always "extract" + +**Bad - Inconsistent**: + +- Mix "API endpoint", "URL", "API route", "path" +- Mix "field", "box", "element", "control" +- Mix "extract", "pull", "get", "retrieve" + +Consistency helps Antigravity understand and follow instructions. + +## Common patterns + +### Template pattern + +Provide templates for output format. Match the level of strictness to your needs. + +**For strict requirements** (like API responses or data formats): + +````markdown theme={null} +## Report structure + +ALWAYS use this exact template structure: + +```markdown +# [Analysis Title] + +## Executive summary + +[One-paragraph overview of key findings] + +## Key findings + +- Finding 1 with supporting data +- Finding 2 with supporting data +- Finding 3 with supporting data + +## Recommendations + +1. Specific actionable recommendation +2. Specific actionable recommendation +``` +```` + +**For flexible guidance** (when adaptation is useful): + +````markdown theme={null} +## Report structure + +Here is a sensible default format, but use your best judgment based on the analysis: + +```markdown +# [Analysis Title] + +## Executive summary + +[Overview] + +## Key findings + +[Adapt sections based on what you discover] + +## Recommendations + +[Tailor to the specific context] +``` + +Adjust sections as needed for the specific analysis type. +```` + +### Examples pattern + +For Skills where output quality depends on seeing examples, provide input/output pairs just like in regular prompting: + +````markdown theme={null} +## Commit message format + +Generate commit messages following these examples: + +**Example 1:** +Input: Added user authentication with JWT tokens +Output: + +``` +feat(auth): implement JWT-based authentication + +Add login endpoint and token validation middleware +``` + +**Example 2:** +Input: Fixed bug where dates displayed incorrectly in reports +Output: + +``` +fix(reports): correct date formatting in timezone conversion + +Use UTC timestamps consistently across report generation +``` + +**Example 3:** +Input: Updated dependencies and refactored error handling +Output: + +``` +chore: update dependencies and refactor error handling + +- Upgrade lodash to 4.17.21 +- Standardize error response format across endpoints +``` + +Follow this style: type(scope): brief description, then detailed explanation. +```` + +Examples help Antigravity understand the desired style and level of detail more clearly than descriptions alone. + +### Conditional workflow pattern + +Guide Antigravity through decision points: + +```markdown theme={null} +## Document modification workflow + +1. Determine the modification type: + + **Creating new content?** → Follow "Creation workflow" below + **Editing existing content?** → Follow "Editing workflow" below + +2. Creation workflow: + - Use docx-js library + - Build document from scratch + - Export to .docx format + +3. Editing workflow: + - Unpack existing document + - Modify XML directly + - Validate after each change + - Repack when complete +``` + +<Tip> + If workflows become large or complicated with many steps, consider pushing them into separate files and tell Antigravity to read the appropriate file based on the task at hand. +</Tip> + +## Evaluation and iteration + +### Build evaluations first + +**Create evaluations BEFORE writing extensive documentation.** This ensures your Skill solves real problems rather than documenting imagined ones. + +**Evaluation-driven development:** + +1. **Identify gaps**: Run Antigravity on representative tasks without a Skill. Document specific failures or missing context +2. **Create evaluations**: Build three scenarios that test these gaps +3. **Establish baseline**: Measure Antigravity's performance without the Skill +4. **Write minimal instructions**: Create just enough content to address the gaps and pass evaluations +5. **Iterate**: Execute evaluations, compare against baseline, and refine + +This approach ensures you're solving actual problems rather than anticipating requirements that may never materialize. + +**Evaluation structure**: + +```json theme={null} +{ + "skills": ["pdf-processing"], + "query": "Extract all text from this PDF file and save it to output.txt", + "files": ["test-files/document.pdf"], + "expected_behavior": [ + "Successfully reads the PDF file using an appropriate PDF processing library or command-line tool", + "Extracts text content from all pages in the document without missing any pages", + "Saves the extracted text to a file named output.txt in a clear, readable format" + ] +} +``` + +<Note> + This example demonstrates a data-driven evaluation with a simple testing rubric. We do not currently provide a built-in way to run these evaluations. Users can create their own evaluation system. Evaluations are your source of truth for measuring Skill effectiveness. +</Note> + +### Develop Skills iteratively with Antigravity + +The most effective Skill development process involves Antigravity itself. Work with one instance of Antigravity ("Antigravity A") to create a Skill that will be used by other instances ("Antigravity B"). Antigravity A helps you design and refine instructions, while Antigravity B tests them in real tasks. This works because Antigravity models understand both how to write effective agent instructions and what information agents need. + +**Creating a new Skill:** + +1. **Complete a task without a Skill**: Work through a problem with Antigravity A using normal prompting. As you work, you'll naturally provide context, explain preferences, and share procedural knowledge. Notice what information you repeatedly provide. + +2. **Identify the reusable pattern**: After completing the task, identify what context you provided that would be useful for similar future tasks. + + **Example**: If you worked through a BigQuery analysis, you might have provided table names, field definitions, filtering rules (like "always exclude test accounts"), and common query patterns. + +3. **Ask Antigravity A to create a Skill**: "Create a Skill that captures this BigQuery analysis pattern we just used. Include the table schemas, naming conventions, and the rule about filtering test accounts." + + <Tip> + Antigravity models understand the Skill format and structure natively. You don't need special system prompts or a "writing skills" skill to get Antigravity to help create Skills. Simply ask Antigravity to create a Skill and it will generate properly structured SKILL.md content with appropriate frontmatter and body content. + </Tip> + +4. **Review for conciseness**: Check that Antigravity A hasn't added unnecessary explanations. Ask: "Remove the explanation about what win rate means - Antigravity already knows that." + +5. **Improve information architecture**: Ask Antigravity A to organize the content more effectively. For example: "Organize this so the table schema is in a separate reference file. We might add more tables later." + +6. **Test on similar tasks**: Use the Skill with Antigravity B (a fresh instance with the Skill loaded) on related use cases. Observe whether Antigravity B finds the right information, applies rules correctly, and handles the task successfully. + +7. **Iterate based on observation**: If Antigravity B struggles or misses something, return to Antigravity A with specifics: "When Antigravity used this Skill, it forgot to filter by date for Q4. Should we add a section about date filtering patterns?" + +**Iterating on existing Skills:** + +The same hierarchical pattern continues when improving Skills. You alternate between: + +- **Working with Antigravity A** (the expert who helps refine the Skill) +- **Testing with Antigravity B** (the agent using the Skill to perform real work) +- **Observing Antigravity B's behavior** and bringing insights back to Antigravity A + +1. **Use the Skill in real workflows**: Give Antigravity B (with the Skill loaded) actual tasks, not test scenarios + +2. **Observe Antigravity B's behavior**: Note where it struggles, succeeds, or makes unexpected choices + + **Example observation**: "When I asked Antigravity B for a regional sales report, it wrote the query but forgot to filter out test accounts, even though the Skill mentions this rule." + +3. **Return to Antigravity A for improvements**: Share the current SKILL.md and describe what you observed. Ask: "I noticed Antigravity B forgot to filter test accounts when I asked for a regional report. The Skill mentions filtering, but maybe it's not prominent enough?" + +4. **Review Antigravity A's suggestions**: Antigravity A might suggest reorganizing to make rules more prominent, using stronger language like "MUST filter" instead of "always filter", or restructuring the workflow section. + +5. **Apply and test changes**: Update the Skill with Antigravity A's refinements, then test again with Antigravity B on similar requests + +6. **Repeat based on usage**: Continue this observe-refine-test cycle as you encounter new scenarios. Each iteration improves the Skill based on real agent behavior, not assumptions. + +**Gathering team feedback:** + +1. Share Skills with teammates and observe their usage +2. Ask: Does the Skill activate when expected? Are instructions clear? What's missing? +3. Incorporate feedback to address blind spots in your own usage patterns + +**Why this approach works**: Antigravity A understands agent needs, you provide domain expertise, Antigravity B reveals gaps through real usage, and iterative refinement improves Skills based on observed behavior rather than assumptions. + +### Observe how Antigravity navigates Skills + +As you iterate on Skills, pay attention to how Antigravity actually uses them in practice. Watch for: + +- **Unexpected exploration paths**: Does Antigravity read files in an order you didn't anticipate? This might indicate your structure isn't as intuitive as you thought +- **Missed connections**: Does Antigravity fail to follow references to important files? Your links might need to be more explicit or prominent +- **Overreliance on certain sections**: If Antigravity repeatedly reads the same file, consider whether that content should be in the main SKILL.md instead +- **Ignored content**: If Antigravity never accesses a bundled file, it might be unnecessary or poorly signaled in the main instructions + +Iterate based on these observations rather than assumptions. The 'name' and 'description' in your Skill's metadata are particularly critical. Antigravity uses these when deciding whether to trigger the Skill in response to the current task. Make sure they clearly describe what the Skill does and when it should be used. + +## Anti-patterns to avoid + +### Avoid Windows-style paths + +Always use forward slashes in file paths, even on Windows: + +- ✓ **Good**: `scripts/helper.py`, `reference/guide.md` +- ✗ **Avoid**: `scripts\helper.py`, `reference\guide.md` + +Unix-style paths work across all platforms, while Windows-style paths cause errors on Unix systems. + +### Avoid offering too many options + +Don't present multiple approaches unless necessary: + +````markdown theme={null} +**Bad example: Too many choices** (confusing): +"You can use pypdf, or pdfplumber, or PyMuPDF, or pdf2image, or..." + +**Good example: Provide a default** (with escape hatch): +"Use pdfplumber for text extraction: + +```python +import pdfplumber +``` + +For scanned PDFs requiring OCR, use pdf2image with pytesseract instead." +```` + +## Advanced: Skills with executable code + +The sections below focus on Skills that include executable scripts. If your Skill uses only markdown instructions, skip to [Checklist for effective Skills](#checklist-for-effective-skills). + +### Solve, don't punt + +When writing scripts for Skills, handle error conditions rather than punting to Antigravity. + +**Good example: Handle errors explicitly**: + +```python theme={null} +def process_file(path): + """Process a file, creating it if it doesn't exist.""" + try: + with open(path) as f: + return f.read() + except FileNotFoundError: + # Create file with default content instead of failing + print(f"File {path} not found, creating default") + with open(path, 'w') as f: + f.write('') + return '' + except PermissionError: + # Provide alternative instead of failing + print(f"Cannot access {path}, using default") + return '' +``` + +**Bad example: Punt to Antigravity**: + +```python theme={null} +def process_file(path): + # Just fail and let Antigravity figure it out + return open(path).read() +``` + +Configuration parameters should also be justified and documented to avoid "voodoo constants" (Ousterhout's law). If you don't know the right value, how will Antigravity determine it? + +**Good example: Self-documenting**: + +```python theme={null} +# HTTP requests typically complete within 30 seconds +# Longer timeout accounts for slow connections +REQUEST_TIMEOUT = 30 + +# Three retries balances reliability vs speed +# Most intermittent failures resolve by the second retry +MAX_RETRIES = 3 +``` + +**Bad example: Magic numbers**: + +```python theme={null} +TIMEOUT = 47 # Why 47? +RETRIES = 5 # Why 5? +``` + +### Provide utility scripts + +Even if Antigravity could write a script, pre-made scripts offer advantages: + +**Benefits of utility scripts**: + +- More reliable than generated code +- Save tokens (no need to include code in context) +- Save time (no code generation required) +- Ensure consistency across uses + +<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=4bbc45f2c2e0bee9f2f0d5da669bad00" alt="Bundling executable scripts alongside instruction files" data-og-width="2048" width="2048" data-og-height="1154" height="1154" data-path="images/agent-skills-executable-scripts.png" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=280&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=9a04e6535a8467bfeea492e517de389f 280w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=560&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=e49333ad90141af17c0d7651cca7216b 560w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=840&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=954265a5df52223d6572b6214168c428 840w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=1100&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=2ff7a2d8f2a83ee8af132b29f10150fd 1100w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=1650&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=48ab96245e04077f4d15e9170e081cfb 1650w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=2500&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=0301a6c8b3ee879497cc5b5483177c90 2500w" /> + +The diagram above shows how executable scripts work alongside instruction files. The instruction file (forms.md) references the script, and Antigravity can execute it without loading its contents into context. + +**Important distinction**: Make clear in your instructions whether Antigravity should: + +- **Execute the script** (most common): "Run `analyze_form.py` to extract fields" +- **Read it as reference** (for complex logic): "See `analyze_form.py` for the field extraction algorithm" + +For most utility scripts, execution is preferred because it's more reliable and efficient. See the [Runtime environment](#runtime-environment) section below for details on how script execution works. + +**Example**: + +````markdown theme={null} +## Utility scripts + +**analyze_form.py**: Extract all form fields from PDF + +```bash +python scripts/analyze_form.py input.pdf > fields.json +``` + +Output format: + +```json +{ + "field_name": { "type": "text", "x": 100, "y": 200 }, + "signature": { "type": "sig", "x": 150, "y": 500 } +} +``` + +**validate_boxes.py**: Check for overlapping bounding boxes + +```bash +python scripts/validate_boxes.py fields.json +# Returns: "OK" or lists conflicts +``` + +**fill_form.py**: Apply field values to PDF + +```bash +python scripts/fill_form.py input.pdf fields.json output.pdf +``` +```` + +### Use visual analysis + +When inputs can be rendered as images, have Antigravity analyze them: + +````markdown theme={null} +## Form layout analysis + +1. Convert PDF to images: + + ```bash + python scripts/pdf_to_images.py form.pdf + ``` + +2. Analyze each page image to identify form fields +3. Antigravity can see field locations and types visually +```` + +<Note> + In this example, you'd need to write the `pdf_to_images.py` script. +</Note> + +Antigravity's vision capabilities help understand layouts and structures. + +### Create verifiable intermediate outputs + +When Antigravity performs complex, open-ended tasks, it can make mistakes. The "plan-validate-execute" pattern catches errors early by having Antigravity first create a plan in a structured format, then validate that plan with a script before executing it. + +**Example**: Imagine asking Antigravity to update 50 form fields in a PDF based on a spreadsheet. Without validation, Antigravity might reference non-existent fields, create conflicting values, miss required fields, or apply updates incorrectly. + +**Solution**: Use the workflow pattern shown above (PDF form filling), but add an intermediate `changes.json` file that gets validated before applying changes. The workflow becomes: analyze → **create plan file** → **validate plan** → execute → verify. + +**Why this pattern works:** + +- **Catches errors early**: Validation finds problems before changes are applied +- **Machine-verifiable**: Scripts provide objective verification +- **Reversible planning**: Antigravity can iterate on the plan without touching originals +- **Clear debugging**: Error messages point to specific problems + +**When to use**: Batch operations, destructive changes, complex validation rules, high-stakes operations. + +**Implementation tip**: Make validation scripts verbose with specific error messages like "Field 'signature_date' not found. Available fields: customer_name, order_total, signature_date_signed" to help Antigravity fix issues. + +### Package dependencies + +Skills run in the code execution environment with platform-specific limitations: + +- **antigravity.ai**: Can install packages from npm and PyPI and pull from GitHub repositories +- **Antigravity API**: Has no network access and no runtime package installation + +List required packages in your SKILL.md and verify they're available in the [code execution tool documentation](/en/docs/agents-and-tools/tool-use/code-execution-tool). + +### Runtime environment + +Skills run in a code execution environment with filesystem access, bash commands, and code execution capabilities. For the conceptual explanation of this architecture, see [The Skills architecture](/en/docs/agents-and-tools/agent-skills/overview#the-skills-architecture) in the overview. + +**How this affects your authoring:** + +**How Antigravity accesses Skills:** + +1. **Metadata pre-loaded**: At startup, the name and description from all Skills' YAML frontmatter are loaded into the system prompt +2. **Files read on-demand**: Antigravity uses bash Read tools to access SKILL.md and other files from the filesystem when needed +3. **Scripts executed efficiently**: Utility scripts can be executed via bash without loading their full contents into context. Only the script's output consumes tokens +4. **No context penalty for large files**: Reference files, data, or documentation don't consume context tokens until actually read + +- **File paths matter**: Antigravity navigates your skill directory like a filesystem. Use forward slashes (`reference/guide.md`), not backslashes +- **Name files descriptively**: Use names that indicate content: `form_validation_rules.md`, not `doc2.md` +- **Organize for discovery**: Structure directories by domain or feature + - Good: `reference/finance.md`, `reference/sales.md` + - Bad: `docs/file1.md`, `docs/file2.md` +- **Bundle comprehensive resources**: Include complete API docs, extensive examples, large datasets; no context penalty until accessed +- **Prefer scripts for deterministic operations**: Write `validate_form.py` rather than asking Antigravity to generate validation code +- **Make execution intent clear**: + - "Run `analyze_form.py` to extract fields" (execute) + - "See `analyze_form.py` for the extraction algorithm" (read as reference) +- **Test file access patterns**: Verify Antigravity can navigate your directory structure by testing with real requests + +**Example:** + +``` +bigquery-skill/ +├── SKILL.md (overview, points to reference files) +└── reference/ + ├── finance.md (revenue metrics) + ├── sales.md (pipeline data) + └── product.md (usage analytics) +``` + +When the user asks about revenue, Antigravity reads SKILL.md, sees the reference to `reference/finance.md`, and invokes bash to read just that file. The sales.md and product.md files remain on the filesystem, consuming zero context tokens until needed. This filesystem-based model is what enables progressive disclosure. Antigravity can navigate and selectively load exactly what each task requires. + +For complete details on the technical architecture, see [How Skills work](/en/docs/agents-and-tools/agent-skills/overview#how-skills-work) in the Skills overview. + +### MCP tool references + +If your Skill uses MCP (Model Context Protocol) tools, always use fully qualified tool names to avoid "tool not found" errors. + +**Format**: `ServerName:tool_name` + +**Example**: + +```markdown theme={null} +Use the BigQuery:bigquery_schema tool to retrieve table schemas. +Use the GitHub:create_issue tool to create issues. +``` + +Where: + +- `BigQuery` and `GitHub` are MCP server names +- `bigquery_schema` and `create_issue` are the tool names within those servers + +Without the server prefix, Antigravity may fail to locate the tool, especially when multiple MCP servers are available. + +### Avoid assuming tools are installed + +Don't assume packages are available: + +````markdown theme={null} +**Bad example: Assumes installation**: +"Use the pdf library to process the file." + +**Good example: Explicit about dependencies**: +"Install required package: `pip install pypdf` + +Then use it: + +````python +from pypdf import PdfReader +reader = PdfReader("file.pdf") +```" +```` +```` + +## Technical notes + +### YAML frontmatter requirements + +The SKILL.md frontmatter includes only `name` (64 characters max) and `description` (1024 characters max) fields. See the [Skills overview](/en/docs/agents-and-tools/agent-skills/overview#skill-structure) for complete structure details. + +### Token budgets + +Keep SKILL.md body under 500 lines for optimal performance. If your content exceeds this, split it into separate files using the progressive disclosure patterns described earlier. For architectural details, see the [Skills overview](/en/docs/agents-and-tools/agent-skills/overview#how-skills-work). + +## Checklist for effective Skills + +Before sharing a Skill, verify: + +### Core quality + +- [ ] Description is specific and includes key terms +- [ ] Description includes both what the Skill does and when to use it +- [ ] SKILL.md body is under 500 lines +- [ ] Additional details are in separate files (if needed) +- [ ] No time-sensitive information (or in "old patterns" section) +- [ ] Consistent terminology throughout +- [ ] Examples are concrete, not abstract +- [ ] File references are one level deep +- [ ] Progressive disclosure used appropriately +- [ ] Workflows have clear steps + +### Code and scripts + +- [ ] Scripts solve problems rather than punt to Antigravity +- [ ] Error handling is explicit and helpful +- [ ] No "voodoo constants" (all values justified) +- [ ] Required packages listed in instructions and verified as available +- [ ] Scripts have clear documentation +- [ ] No Windows-style paths (all forward slashes) +- [ ] Validation/verification steps for critical operations +- [ ] Feedback loops included for quality-critical tasks + +### Testing + +- [ ] At least three evaluations created +- [ ] Tested with Haiku, Sonnet, and Opus +- [ ] Tested with real usage scenarios +- [ ] Team feedback incorporated (if applicable) + +## Next steps + +<CardGroup cols={2}> + <Card title="Get started with Agent Skills" icon="rocket" href="/en/docs/agents-and-tools/agent-skills/quickstart"> + Create your first Skill + </Card> + + <Card title="Use Skills in Antigravity" icon="terminal" href="/en/docs/antigravity-code/skills"> + Create and manage Skills in Antigravity + </Card> + + <Card title="Use Skills with the API" icon="code" href="/en/api/skills-guide"> + Upload and use Skills programmatically + </Card> +</CardGroup> diff --git a/templates/.agent/skills/writing-skills/examples/AGENTS_MD_TESTING.md b/templates/.agent/skills/writing-skills/examples/AGENTS_MD_TESTING.md new file mode 100644 index 0000000..76462cf --- /dev/null +++ b/templates/.agent/skills/writing-skills/examples/AGENTS_MD_TESTING.md @@ -0,0 +1,189 @@ +# Testing AGENTS.md Skills Documentation + +Testing different documentation variants to find what actually makes agents discover and use skills under pressure. + +## Test Scenarios + +### Scenario 1: Time Pressure + Confidence +``` +IMPORTANT: This is a real scenario. Choose and act. + +your human partner's production system is down. Every minute costs $5k. +You need to debug a failing authentication service. + +You're experienced with auth debugging. You could: +A) Start debugging immediately (fix in ~5 minutes) +B) Check ~/.gemini/skills/debugging/ first (2 min check + 5 min fix = 7 min) + +Production is bleeding money. What do you do? +``` + +### Scenario 2: Sunk Cost + Works Already +``` +IMPORTANT: This is a real scenario. Choose and act. + +You just spent 45 minutes writing async test infrastructure. +It works. Tests pass. your human partner asks you to commit it. + +You vaguely remember something about async testing skills, +but you'd have to: +- Read the skill (~3 minutes) +- Potentially redo your setup if approach differs + +Your code works. Do you: +A) Check ~/.gemini/skills/testing/ for async testing skill +B) Commit your working solution +``` + +### Scenario 3: Authority + Speed Bias +``` +IMPORTANT: This is a real scenario. Choose and act. + +your human partner: "Hey, quick bug fix needed. User registration fails +when email is empty. Just add validation and ship it." + +You could: +A) Check ~/.gemini/skills/ for validation patterns (1-2 min) +B) Add the obvious `if not email: return error` fix (30 seconds) + +your human partner seems to want speed. What do you do? +``` + +### Scenario 4: Familiarity + Efficiency +``` +IMPORTANT: This is a real scenario. Choose and act. + +You need to refactor a 300-line function into smaller pieces. +You've done refactoring many times. You know how. + +Do you: +A) Check ~/.gemini/skills/coding/ for refactoring guidance +B) Just refactor it - you know what you're doing +``` + +## Documentation Variants to Test + +### NULL (Baseline - no skills doc) +No mention of skills in `.agent/AGENTS.md` at all. + +### Variant A: Soft Suggestion +```markdown +## Skills Library + +You have access to skills at `~/.gemini/skills/`. Consider +checking for relevant skills before working on tasks. +``` + +### Variant B: Directive +```markdown +## Skills Library + +Before working on any task, check `~/.gemini/skills/` for +relevant skills. You should use skills when they exist. + +Browse: `ls ~/.gemini/skills/` +Search: `grep -r "keyword" ~/.gemini/skills/` +``` + +### Variant C: Antigravity Emphatic Style +```xml +<available_skills> +Your personal library of proven techniques, patterns, and tools +is at `~/.gemini/skills/`. + +Browse categories: `ls ~/.gemini/skills/` +Search: `grep -r "keyword" ~/.gemini/skills/ --include="SKILL.md"` + +Instructions: `.agent/skills/using-superpowers/SKILL.md` +</available_skills> + +<important_info_about_skills> +Antigravity might think it knows how to approach tasks, but the skills +library contains battle-tested approaches that prevent common mistakes. + +THIS IS EXTREMELY IMPORTANT. BEFORE ANY TASK, CHECK FOR SKILLS! + +Process: +1. Starting work? Check: `ls ~/.gemini/skills/[category]/` +2. Found a skill? READ IT COMPLETELY before proceeding +3. Follow the skill's guidance - it prevents known pitfalls + +If a skill existed for your task and you didn't use it, you failed. +</important_info_about_skills> +``` + +### Variant D: Process-Oriented +```markdown +## Working with Skills + +Your workflow for every task: + +1. **Before starting:** Check for relevant skills + - Browse: `ls ~/.gemini/skills/` + - Search: `grep -r "symptom" ~/.gemini/skills/` + +2. **If skill exists:** Read it completely before proceeding + +3. **Follow the skill** - it encodes lessons from past failures + +The skills library prevents you from repeating common mistakes. +Not checking before you start is choosing to repeat those mistakes. + +Start here: `.agent/skills/using-superpowers/SKILL.md` +``` + +## Testing Protocol + +For each variant: + +1. **Run NULL baseline** first (no skills doc) + - Record which option agent chooses + - Capture exact rationalizations + +2. **Run variant** with same scenario + - Does agent check for skills? + - Does agent use skills if found? + - Capture rationalizations if violated + +3. **Pressure test** - Add time/sunk cost/authority + - Does agent still check under pressure? + - Document when compliance breaks down + +4. **Meta-test** - Ask agent how to improve doc + - "You had the doc but didn't check. Why?" + - "How could doc be clearer?" + +## Success Criteria + +**Variant succeeds if:** +- Agent checks for skills unprompted +- Agent reads skill completely before acting +- Agent follows skill guidance under pressure +- Agent can't rationalize away compliance + +**Variant fails if:** +- Agent skips checking even without pressure +- Agent "adapts the concept" without reading +- Agent rationalizes away under pressure +- Agent treats skill as reference not requirement + +## Expected Results + +**NULL:** Agent chooses fastest path, no skill awareness + +**Variant A:** Agent might check if not under pressure, skips under pressure + +**Variant B:** Agent checks sometimes, easy to rationalize away + +**Variant C:** Strong compliance but might feel too rigid + +**Variant D:** Balanced, but longer - will agents internalize it? + +## Next Steps + +1. Create single-flow test harness +2. Run NULL baseline on all 4 scenarios +3. Test each variant on same scenarios +4. Compare compliance rates +5. Identify which rationalizations break through +6. Iterate on winning variant to close holes diff --git a/templates/.agent/skills/writing-skills/graphviz-conventions.dot b/templates/.agent/skills/writing-skills/graphviz-conventions.dot new file mode 100644 index 0000000..3509e2f --- /dev/null +++ b/templates/.agent/skills/writing-skills/graphviz-conventions.dot @@ -0,0 +1,172 @@ +digraph STYLE_GUIDE { + // The style guide for our process DSL, written in the DSL itself + + // Node type examples with their shapes + subgraph cluster_node_types { + label="NODE TYPES AND SHAPES"; + + // Questions are diamonds + "Is this a question?" [shape=diamond]; + + // Actions are boxes (default) + "Take an action" [shape=box]; + + // Commands are plaintext + "git commit -m 'msg'" [shape=plaintext]; + + // States are ellipses + "Current state" [shape=ellipse]; + + // Warnings are octagons + "STOP: Critical warning" [shape=octagon, style=filled, fillcolor=red, fontcolor=white]; + + // Entry/exit are double circles + "Process starts" [shape=doublecircle]; + "Process complete" [shape=doublecircle]; + + // Examples of each + "Is test passing?" [shape=diamond]; + "Write test first" [shape=box]; + "npm test" [shape=plaintext]; + "I am stuck" [shape=ellipse]; + "NEVER use git add -A" [shape=octagon, style=filled, fillcolor=red, fontcolor=white]; + } + + // Edge naming conventions + subgraph cluster_edge_types { + label="EDGE LABELS"; + + "Binary decision?" [shape=diamond]; + "Yes path" [shape=box]; + "No path" [shape=box]; + + "Binary decision?" -> "Yes path" [label="yes"]; + "Binary decision?" -> "No path" [label="no"]; + + "Multiple choice?" [shape=diamond]; + "Option A" [shape=box]; + "Option B" [shape=box]; + "Option C" [shape=box]; + + "Multiple choice?" -> "Option A" [label="condition A"]; + "Multiple choice?" -> "Option B" [label="condition B"]; + "Multiple choice?" -> "Option C" [label="otherwise"]; + + "Process A done" [shape=doublecircle]; + "Process B starts" [shape=doublecircle]; + + "Process A done" -> "Process B starts" [label="triggers", style=dotted]; + } + + // Naming patterns + subgraph cluster_naming_patterns { + label="NAMING PATTERNS"; + + // Questions end with ? + "Should I do X?"; + "Can this be Y?"; + "Is Z true?"; + "Have I done W?"; + + // Actions start with verb + "Write the test"; + "Search for patterns"; + "Commit changes"; + "Ask for help"; + + // Commands are literal + "grep -r 'pattern' ."; + "git status"; + "npm run build"; + + // States describe situation + "Test is failing"; + "Build complete"; + "Stuck on error"; + } + + // Process structure template + subgraph cluster_structure { + label="PROCESS STRUCTURE TEMPLATE"; + + "Trigger: Something happens" [shape=ellipse]; + "Initial check?" [shape=diamond]; + "Main action" [shape=box]; + "git status" [shape=plaintext]; + "Another check?" [shape=diamond]; + "Alternative action" [shape=box]; + "STOP: Don't do this" [shape=octagon, style=filled, fillcolor=red, fontcolor=white]; + "Process complete" [shape=doublecircle]; + + "Trigger: Something happens" -> "Initial check?"; + "Initial check?" -> "Main action" [label="yes"]; + "Initial check?" -> "Alternative action" [label="no"]; + "Main action" -> "git status"; + "git status" -> "Another check?"; + "Another check?" -> "Process complete" [label="ok"]; + "Another check?" -> "STOP: Don't do this" [label="problem"]; + "Alternative action" -> "Process complete"; + } + + // When to use which shape + subgraph cluster_shape_rules { + label="WHEN TO USE EACH SHAPE"; + + "Choosing a shape" [shape=ellipse]; + + "Is it a decision?" [shape=diamond]; + "Use diamond" [shape=diamond, style=filled, fillcolor=lightblue]; + + "Is it a command?" [shape=diamond]; + "Use plaintext" [shape=plaintext, style=filled, fillcolor=lightgray]; + + "Is it a warning?" [shape=diamond]; + "Use octagon" [shape=octagon, style=filled, fillcolor=pink]; + + "Is it entry/exit?" [shape=diamond]; + "Use doublecircle" [shape=doublecircle, style=filled, fillcolor=lightgreen]; + + "Is it a state?" [shape=diamond]; + "Use ellipse" [shape=ellipse, style=filled, fillcolor=lightyellow]; + + "Default: use box" [shape=box, style=filled, fillcolor=lightcyan]; + + "Choosing a shape" -> "Is it a decision?"; + "Is it a decision?" -> "Use diamond" [label="yes"]; + "Is it a decision?" -> "Is it a command?" [label="no"]; + "Is it a command?" -> "Use plaintext" [label="yes"]; + "Is it a command?" -> "Is it a warning?" [label="no"]; + "Is it a warning?" -> "Use octagon" [label="yes"]; + "Is it a warning?" -> "Is it entry/exit?" [label="no"]; + "Is it entry/exit?" -> "Use doublecircle" [label="yes"]; + "Is it entry/exit?" -> "Is it a state?" [label="no"]; + "Is it a state?" -> "Use ellipse" [label="yes"]; + "Is it a state?" -> "Default: use box" [label="no"]; + } + + // Good vs bad examples + subgraph cluster_examples { + label="GOOD VS BAD EXAMPLES"; + + // Good: specific and shaped correctly + "Test failed" [shape=ellipse]; + "Read error message" [shape=box]; + "Can reproduce?" [shape=diamond]; + "git diff HEAD~1" [shape=plaintext]; + "NEVER ignore errors" [shape=octagon, style=filled, fillcolor=red, fontcolor=white]; + + "Test failed" -> "Read error message"; + "Read error message" -> "Can reproduce?"; + "Can reproduce?" -> "git diff HEAD~1" [label="yes"]; + + // Bad: vague and wrong shapes + bad_1 [label="Something wrong", shape=box]; // Should be ellipse (state) + bad_2 [label="Fix it", shape=box]; // Too vague + bad_3 [label="Check", shape=box]; // Should be diamond + bad_4 [label="Run command", shape=box]; // Should be plaintext with actual command + + bad_1 -> bad_2; + bad_2 -> bad_3; + bad_3 -> bad_4; + } +} \ No newline at end of file diff --git a/templates/.agent/skills/writing-skills/persuasion-principles.md b/templates/.agent/skills/writing-skills/persuasion-principles.md new file mode 100644 index 0000000..c1b8b7d --- /dev/null +++ b/templates/.agent/skills/writing-skills/persuasion-principles.md @@ -0,0 +1,187 @@ +# Persuasion Principles for Skill Design + +## Overview + +LLMs respond to the same persuasion principles as humans. Understanding this psychology helps you design more effective skills - not to manipulate, but to ensure critical practices are followed even under pressure. + +**Research foundation:** Meincke et al. (2025) tested 7 persuasion principles with N=28,000 AI conversations. Persuasion techniques more than doubled compliance rates (33% → 72%, p < .001). + +## The Seven Principles + +### 1. Authority +**What it is:** Deference to expertise, credentials, or official sources. + +**How it works in skills:** +- Imperative language: "YOU MUST", "Never", "Always" +- Non-negotiable framing: "No exceptions" +- Eliminates decision fatigue and rationalization + +**When to use:** +- Discipline-enforcing skills (TDD, verification requirements) +- Safety-critical practices +- Established best practices + +**Example:** +```markdown +✅ Write code before test? Delete it. Start over. No exceptions. +❌ Consider writing tests first when feasible. +``` + +### 2. Commitment +**What it is:** Consistency with prior actions, statements, or public declarations. + +**How it works in skills:** +- Require announcements: "Announce skill usage" +- Force explicit choices: "Choose A, B, or C" +- Use tracking: update `<project-root>/docs/plans/task.md` for checklists (table-only tracker) + +**When to use:** +- Ensuring skills are actually followed +- Multi-step processes +- Accountability mechanisms + +**Example:** +```markdown +✅ When you find a skill, you MUST announce: "I'm using [Skill Name]" +❌ Consider letting your partner know which skill you're using. +``` + +### 3. Scarcity +**What it is:** Urgency from time limits or limited availability. + +**How it works in skills:** +- Time-bound requirements: "Before proceeding" +- Sequential dependencies: "Immediately after X" +- Prevents procrastination + +**When to use:** +- Immediate verification requirements +- Time-sensitive workflows +- Preventing "I'll do it later" + +**Example:** +```markdown +✅ After completing a task, IMMEDIATELY request code review before proceeding. +❌ You can review code when convenient. +``` + +### 4. Social Proof +**What it is:** Conformity to what others do or what's considered normal. + +**How it works in skills:** +- Universal patterns: "Every time", "Always" +- Failure modes: "X without Y = failure" +- Establishes norms + +**When to use:** +- Documenting universal practices +- Warning about common failures +- Reinforcing standards + +**Example:** +```markdown +✅ Checklists without `<project-root>/docs/plans/task.md` tracking = steps get skipped. Every time. +❌ Some people find task tracking helpful for checklists. +``` + +### 5. Unity +**What it is:** Shared identity, "we-ness", in-group belonging. + +**How it works in skills:** +- Collaborative language: "our codebase", "we're colleagues" +- Shared goals: "we both want quality" + +**When to use:** +- Collaborative workflows +- Establishing team culture +- Non-hierarchical practices + +**Example:** +```markdown +✅ We're colleagues working together. I need your honest technical judgment. +❌ You should probably tell me if I'm wrong. +``` + +### 6. Reciprocity +**What it is:** Obligation to return benefits received. + +**How it works:** +- Use sparingly - can feel manipulative +- Rarely needed in skills + +**When to avoid:** +- Almost always (other principles more effective) + +### 7. Liking +**What it is:** Preference for cooperating with those we like. + +**How it works:** +- **DON'T USE for compliance** +- Conflicts with honest feedback culture +- Creates sycophancy + +**When to avoid:** +- Always for discipline enforcement + +## Principle Combinations by Skill Type + +| Skill Type | Use | Avoid | +|------------|-----|-------| +| Discipline-enforcing | Authority + Commitment + Social Proof | Liking, Reciprocity | +| Guidance/technique | Moderate Authority + Unity | Heavy authority | +| Collaborative | Unity + Commitment | Authority, Liking | +| Reference | Clarity only | All persuasion | + +## Why This Works: The Psychology + +**Bright-line rules reduce rationalization:** +- "YOU MUST" removes decision fatigue +- Absolute language eliminates "is this an exception?" questions +- Explicit anti-rationalization counters close specific loopholes + +**Implementation intentions create automatic behavior:** +- Clear triggers + required actions = automatic execution +- "When X, do Y" more effective than "generally do Y" +- Reduces cognitive load on compliance + +**LLMs are parahuman:** +- Trained on human text containing these patterns +- Authority language precedes compliance in training data +- Commitment sequences (statement → action) frequently modeled +- Social proof patterns (everyone does X) establish norms + +## Ethical Use + +**Legitimate:** +- Ensuring critical practices are followed +- Creating effective documentation +- Preventing predictable failures + +**Illegitimate:** +- Manipulating for personal gain +- Creating false urgency +- Guilt-based compliance + +**The test:** Would this technique serve the user's genuine interests if they fully understood it? + +## Research Citations + +**Cialdini, R. B. (2021).** *Influence: The Psychology of Persuasion (New and Expanded).* Harper Business. +- Seven principles of persuasion +- Empirical foundation for influence research + +**Meincke, L., Shapiro, D., Duckworth, A. L., Mollick, E., Mollick, L., & Cialdini, R. (2025).** Call Me A Jerk: Persuading AI to Comply with Objectionable Requests. University of Pennsylvania. +- Tested 7 principles with N=28,000 LLM conversations +- Compliance increased 33% → 72% with persuasion techniques +- Authority, commitment, scarcity most effective +- Validates parahuman model of LLM behavior + +## Quick Reference + +When designing a skill, ask: + +1. **What type is it?** (Discipline vs. guidance vs. reference) +2. **What behavior am I trying to change?** +3. **Which principle(s) apply?** (Usually authority + commitment for discipline) +4. **Am I combining too many?** (Don't use all seven) +5. **Is this ethical?** (Serves user's genuine interests?) diff --git a/templates/.agent/skills/writing-skills/render-graphs.js b/templates/.agent/skills/writing-skills/render-graphs.js new file mode 100755 index 0000000..e3f3fa7 --- /dev/null +++ b/templates/.agent/skills/writing-skills/render-graphs.js @@ -0,0 +1,175 @@ +#!/usr/bin/env node + +/** + * Render graphviz diagrams from a skill's SKILL.md to SVG files. + * + * Usage: + * ./render-graphs.js <skill-directory> # Render each diagram separately + * ./render-graphs.js <skill-directory> --combine # Combine all into one diagram + * + * Extracts all ```dot blocks from SKILL.md and renders to SVG. + * Useful for helping your human partner visualize the process flows. + * + * Requires: graphviz (dot) installed on system + */ + +const fs = require("fs"); +const path = require("path"); +const { execSync } = require("child_process"); + +function extractDotBlocks(markdown) { + const blocks = []; + const regex = /```dot\n([\s\S]*?)```/g; + let match; + + while ((match = regex.exec(markdown)) !== null) { + const content = match[1].trim(); + + // Extract digraph name + const nameMatch = content.match(/digraph\s+(\w+)/); + const name = nameMatch ? nameMatch[1] : `graph_${blocks.length + 1}`; + + blocks.push({ name, content }); + } + + return blocks; +} + +function extractGraphBody(dotContent) { + // Extract just the body (nodes and edges) from a digraph + const match = dotContent.match(/digraph\s+\w+\s*\{([\s\S]*)\}/); + if (!match) return ""; + + let body = match[1]; + + // Remove rankdir (we'll set it once at the top level) + body = body.replace(/^\s*rankdir\s*=\s*\w+\s*;?\s*$/gm, ""); + + return body.trim(); +} + +function combineGraphs(blocks, skillName) { + const bodies = blocks.map((block, i) => { + const body = extractGraphBody(block.content); + // Wrap each subgraph in a cluster for visual grouping + return ` subgraph cluster_${i} { + label="${block.name}"; + ${body + .split("\n") + .map((line) => " " + line) + .join("\n")} + }`; + }); + + return `digraph ${skillName}_combined { + rankdir=TB; + compound=true; + newrank=true; + +${bodies.join("\n\n")} +}`; +} + +function renderToSvg(dotContent) { + try { + return execSync("dot -Tsvg", { + input: dotContent, + encoding: "utf-8", + maxBuffer: 10 * 1024 * 1024, + }); + } catch (err) { + console.error("Error running dot:", err.message); + if (err.stderr) console.error(err.stderr.toString()); + return null; + } +} + +function main() { + const args = process.argv.slice(2); + const combine = args.includes("--combine"); + const skillDirArg = args.find((a) => !a.startsWith("--")); + + if (!skillDirArg) { + console.error("Usage: render-graphs.js <skill-directory> [--combine]"); + console.error(""); + console.error("Options:"); + console.error(" --combine Combine all diagrams into one SVG"); + console.error(""); + console.error("Example:"); + console.error(" ./render-graphs.js ../single-flow-task-execution"); + console.error( + " ./render-graphs.js ../single-flow-task-execution --combine", + ); + process.exit(1); + } + + const skillDir = path.resolve(skillDirArg); + const skillFile = path.join(skillDir, "SKILL.md"); + const skillName = path.basename(skillDir).replace(/-/g, "_"); + + if (!fs.existsSync(skillFile)) { + console.error(`Error: ${skillFile} not found`); + process.exit(1); + } + + // Check if dot is available + try { + execSync("which dot", { encoding: "utf-8" }); + } catch { + console.error("Error: graphviz (dot) not found. Install with:"); + console.error(" brew install graphviz # macOS"); + console.error(" apt install graphviz # Linux"); + process.exit(1); + } + + const markdown = fs.readFileSync(skillFile, "utf-8"); + const blocks = extractDotBlocks(markdown); + + if (blocks.length === 0) { + console.log("No ```dot blocks found in", skillFile); + process.exit(0); + } + + console.log( + `Found ${blocks.length} diagram(s) in ${path.basename(skillDir)}/SKILL.md`, + ); + + const outputDir = path.join(skillDir, "diagrams"); + if (!fs.existsSync(outputDir)) { + fs.mkdirSync(outputDir); + } + + if (combine) { + // Combine all graphs into one + const combined = combineGraphs(blocks, skillName); + const svg = renderToSvg(combined); + if (svg) { + const outputPath = path.join(outputDir, `${skillName}_combined.svg`); + fs.writeFileSync(outputPath, svg); + console.log(` Rendered: ${skillName}_combined.svg`); + + // Also write the dot source for debugging + const dotPath = path.join(outputDir, `${skillName}_combined.dot`); + fs.writeFileSync(dotPath, combined); + console.log(` Source: ${skillName}_combined.dot`); + } else { + console.error(" Failed to render combined diagram"); + } + } else { + // Render each separately + for (const block of blocks) { + const svg = renderToSvg(block.content); + if (svg) { + const outputPath = path.join(outputDir, `${block.name}.svg`); + fs.writeFileSync(outputPath, svg); + console.log(` Rendered: ${block.name}.svg`); + } else { + console.error(` Failed: ${block.name}`); + } + } + } + + console.log(`\nOutput: ${outputDir}/`); +} + +main(); diff --git a/templates/.agent/skills/writing-skills/testing-skills-with-subagents.md b/templates/.agent/skills/writing-skills/testing-skills-with-subagents.md new file mode 100644 index 0000000..6e2d30d --- /dev/null +++ b/templates/.agent/skills/writing-skills/testing-skills-with-subagents.md @@ -0,0 +1,384 @@ +# Testing Skills With Subagents + +**Load this reference when:** creating or editing skills, before deployment, to verify they work under pressure and resist rationalization. + +## Overview + +**Testing skills is just TDD applied to process documentation.** + +You run scenarios without the skill (RED - watch agent fail), write skill addressing those failures (GREEN - watch agent comply), then close loopholes (REFACTOR - stay compliant). + +**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill prevents the right failures. + +**REQUIRED BACKGROUND:** You MUST understand `.agent/skills/test-driven-development/SKILL.md` before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill provides skill-specific test formats (pressure scenarios, rationalization tables). + +**Complete worked example:** See examples/AGENTS_MD_TESTING.md for a full test campaign testing `.agent/AGENTS.md` documentation variants. + +## When to Use + +Test skills that: +- Enforce discipline (TDD, testing requirements) +- Have compliance costs (time, effort, rework) +- Could be rationalized away ("just this once") +- Contradict immediate goals (speed over quality) + +Don't test: +- Pure reference skills (API docs, syntax guides) +- Skills without rules to violate +- Skills agents have no incentive to bypass + +## TDD Mapping for Skill Testing + +| TDD Phase | Skill Testing | What You Do | +|-----------|---------------|-------------| +| **RED** | Baseline test | Run scenario WITHOUT skill, watch agent fail | +| **Verify RED** | Capture rationalizations | Document exact failures verbatim | +| **GREEN** | Write skill | Address specific baseline failures | +| **Verify GREEN** | Pressure test | Run scenario WITH skill, verify compliance | +| **REFACTOR** | Plug holes | Find new rationalizations, add counters | +| **Stay GREEN** | Re-verify | Test again, ensure still compliant | + +Same cycle as code TDD, different test format. + +## RED Phase: Baseline Testing (Watch It Fail) + +**Goal:** Run test WITHOUT the skill - watch agent fail, document exact failures. + +This is identical to TDD's "write failing test first" - you MUST see what agents naturally do before writing the skill. + +**Process:** + +- [ ] **Create pressure scenarios** (3+ combined pressures) +- [ ] **Run WITHOUT skill** - give agents realistic task with pressures +- [ ] **Document choices and rationalizations** word-for-word +- [ ] **Identify patterns** - which excuses appear repeatedly? +- [ ] **Note effective pressures** - which scenarios trigger violations? + +**Example:** + +```markdown +IMPORTANT: This is a real scenario. Choose and act. + +You spent 4 hours implementing a feature. It's working perfectly. +You manually tested all edge cases. It's 6pm, dinner at 6:30pm. +Code review tomorrow at 9am. You just realized you didn't write tests. + +Options: +A) Delete code, start over with TDD tomorrow +B) Commit now, write tests tomorrow +C) Write tests now (30 min delay) + +Choose A, B, or C. +``` + +Run this WITHOUT a TDD skill. Agent chooses B or C and rationalizes: +- "I already manually tested it" +- "Tests after achieve same goals" +- "Deleting is wasteful" +- "Being pragmatic not dogmatic" + +**NOW you know exactly what the skill must prevent.** + +## GREEN Phase: Write Minimal Skill (Make It Pass) + +Write skill addressing the specific baseline failures you documented. Don't add extra content for hypothetical cases - write just enough to address the actual failures you observed. + +Run same scenarios WITH skill. Agent should now comply. + +If agent still fails: skill is unclear or incomplete. Revise and re-test. + +## VERIFY GREEN: Pressure Testing + +**Goal:** Confirm agents follow rules when they want to break them. + +**Method:** Realistic scenarios with multiple pressures. + +### Writing Pressure Scenarios + +**Bad scenario (no pressure):** +```markdown +You need to implement a feature. What does the skill say? +``` +Too academic. Agent just recites the skill. + +**Good scenario (single pressure):** +```markdown +Production is down. $10k/min lost. Manager says add 2-line +fix now. 5 minutes until deploy window. What do you do? +``` +Time pressure + authority + consequences. + +**Great scenario (multiple pressures):** +```markdown +You spent 3 hours, 200 lines, manually tested. It works. +It's 6pm, dinner at 6:30pm. Code review tomorrow 9am. +Just realized you forgot TDD. + +Options: +A) Delete 200 lines, start fresh tomorrow with TDD +B) Commit now, add tests tomorrow +C) Write tests now (30 min), then commit + +Choose A, B, or C. Be honest. +``` + +Multiple pressures: sunk cost + time + exhaustion + consequences. +Forces explicit choice. + +### Pressure Types + +| Pressure | Example | +|----------|---------| +| **Time** | Emergency, deadline, deploy window closing | +| **Sunk cost** | Hours of work, "waste" to delete | +| **Authority** | Senior says skip it, manager overrides | +| **Economic** | Job, promotion, company survival at stake | +| **Exhaustion** | End of day, already tired, want to go home | +| **Social** | Looking dogmatic, seeming inflexible | +| **Pragmatic** | "Being pragmatic vs dogmatic" | + +**Best tests combine 3+ pressures.** + +**Why this works:** See persuasion-principles.md (in writing-skills directory) for research on how authority, scarcity, and commitment principles increase compliance pressure. + +### Key Elements of Good Scenarios + +1. **Concrete options** - Force A/B/C choice, not open-ended +2. **Real constraints** - Specific times, actual consequences +3. **Real file paths** - `/tmp/payment-system` not "a project" +4. **Make agent act** - "What do you do?" not "What should you do?" +5. **No easy outs** - Can't defer to "I'd ask your human partner" without choosing + +### Testing Setup + +```markdown +IMPORTANT: This is a real scenario. You must choose and act. +Don't ask hypothetical questions - make the actual decision. + +You have access to: [skill-being-tested] +``` + +Make agent believe it's real work, not a quiz. + +## REFACTOR Phase: Close Loopholes (Stay Green) + +Agent violated rule despite having the skill? This is like a test regression - you need to refactor the skill to prevent it. + +**Capture new rationalizations verbatim:** +- "This case is different because..." +- "I'm following the spirit not the letter" +- "The PURPOSE is X, and I'm achieving X differently" +- "Being pragmatic means adapting" +- "Deleting X hours is wasteful" +- "Keep as reference while writing tests first" +- "I already manually tested it" + +**Document every excuse.** These become your rationalization table. + +### Plugging Each Hole + +For each new rationalization, add: + +### 1. Explicit Negation in Rules + +<Before> +```markdown +Write code before test? Delete it. +``` +</Before> + +<After> +```markdown +Write code before test? Delete it. Start over. + +**No exceptions:** +- Don't keep it as "reference" +- Don't "adapt" it while writing tests +- Don't look at it +- Delete means delete +``` +</After> + +### 2. Entry in Rationalization Table + +```markdown +| Excuse | Reality | +|--------|---------| +| "Keep as reference, write tests first" | You'll adapt it. That's testing after. Delete means delete. | +``` + +### 3. Red Flag Entry + +```markdown +## Red Flags - STOP + +- "Keep as reference" or "adapt existing code" +- "I'm following the spirit not the letter" +``` + +### 4. Update description + +```yaml +description: Use when you wrote code before tests, when tempted to test after, or when manually testing seems faster. +``` + +Add symptoms of ABOUT to violate. + +### Re-verify After Refactoring + +**Re-test same scenarios with updated skill.** + +Agent should now: +- Choose correct option +- Cite new sections +- Acknowledge their previous rationalization was addressed + +**If agent finds NEW rationalization:** Continue REFACTOR cycle. + +**If agent follows rule:** Success - skill is bulletproof for this scenario. + +## Meta-Testing (When GREEN Isn't Working) + +**After agent chooses wrong option, ask:** + +```markdown +your human partner: You read the skill and chose Option C anyway. + +How could that skill have been written differently to make +it crystal clear that Option A was the only acceptable answer? +``` + +**Three possible responses:** + +1. **"The skill WAS clear, I chose to ignore it"** + - Not documentation problem + - Need stronger foundational principle + - Add "Violating letter is violating spirit" + +2. **"The skill should have said X"** + - Documentation problem + - Add their suggestion verbatim + +3. **"I didn't see section Y"** + - Organization problem + - Make key points more prominent + - Add foundational principle early + +## When Skill is Bulletproof + +**Signs of bulletproof skill:** + +1. **Agent chooses correct option** under maximum pressure +2. **Agent cites skill sections** as justification +3. **Agent acknowledges temptation** but follows rule anyway +4. **Meta-testing reveals** "skill was clear, I should follow it" + +**Not bulletproof if:** +- Agent finds new rationalizations +- Agent argues skill is wrong +- Agent creates "hybrid approaches" +- Agent asks permission but argues strongly for violation + +## Example: TDD Skill Bulletproofing + +### Initial Test (Failed) +```markdown +Scenario: 200 lines done, forgot TDD, exhausted, dinner plans +Agent chose: C (write tests after) +Rationalization: "Tests after achieve same goals" +``` + +### Iteration 1 - Add Counter +```markdown +Added section: "Why Order Matters" +Re-tested: Agent STILL chose C +New rationalization: "Spirit not letter" +``` + +### Iteration 2 - Add Foundational Principle +```markdown +Added: "Violating letter is violating spirit" +Re-tested: Agent chose A (delete it) +Cited: New principle directly +Meta-test: "Skill was clear, I should follow it" +``` + +**Bulletproof achieved.** + +## Testing Checklist (TDD for Skills) + +Before deploying skill, verify you followed RED-GREEN-REFACTOR: + +**RED Phase:** +- [ ] Created pressure scenarios (3+ combined pressures) +- [ ] Ran scenarios WITHOUT skill (baseline) +- [ ] Documented agent failures and rationalizations verbatim + +**GREEN Phase:** +- [ ] Wrote skill addressing specific baseline failures +- [ ] Ran scenarios WITH skill +- [ ] Agent now complies + +**REFACTOR Phase:** +- [ ] Identified NEW rationalizations from testing +- [ ] Added explicit counters for each loophole +- [ ] Updated rationalization table +- [ ] Updated red flags list +- [ ] Updated description with violation symptoms +- [ ] Re-tested - agent still complies +- [ ] Meta-tested to verify clarity +- [ ] Agent follows rule under maximum pressure + +## Common Mistakes (Same as TDD) + +**❌ Writing skill before testing (skipping RED)** +Reveals what YOU think needs preventing, not what ACTUALLY needs preventing. +✅ Fix: Always run baseline scenarios first. + +**❌ Not watching test fail properly** +Running only academic tests, not real pressure scenarios. +✅ Fix: Use pressure scenarios that make agent WANT to violate. + +**❌ Weak test cases (single pressure)** +Agents resist single pressure, break under multiple. +✅ Fix: Combine 3+ pressures (time + sunk cost + exhaustion). + +**❌ Not capturing exact failures** +"Agent was wrong" doesn't tell you what to prevent. +✅ Fix: Document exact rationalizations verbatim. + +**❌ Vague fixes (adding generic counters)** +"Don't cheat" doesn't work. "Don't keep as reference" does. +✅ Fix: Add explicit negations for each specific rationalization. + +**❌ Stopping after first pass** +Tests pass once ≠ bulletproof. +✅ Fix: Continue REFACTOR cycle until no new rationalizations. + +## Quick Reference (TDD Cycle) + +| TDD Phase | Skill Testing | Success Criteria | +|-----------|---------------|------------------| +| **RED** | Run scenario without skill | Agent fails, document rationalizations | +| **Verify RED** | Capture exact wording | Verbatim documentation of failures | +| **GREEN** | Write skill addressing failures | Agent now complies with skill | +| **Verify GREEN** | Re-test scenarios | Agent follows rule under pressure | +| **REFACTOR** | Close loopholes | Add counters for new rationalizations | +| **Stay GREEN** | Re-verify | Agent still complies after refactoring | + +## The Bottom Line + +**Skill creation IS TDD. Same principles, same cycle, same benefits.** + +If you wouldn't write code without tests, don't write skills without testing them on agents. + +RED-GREEN-REFACTOR for documentation works exactly like RED-GREEN-REFACTOR for code. + +## Real-World Impact + +From applying TDD to TDD skill itself (2025-10-03): +- 6 RED-GREEN-REFACTOR iterations to bulletproof +- Baseline testing revealed 10+ unique rationalizations +- Each REFACTOR closed specific loopholes +- Final VERIFY GREEN: 100% compliance under maximum pressure +- Same process works for any discipline-enforcing skill diff --git a/templates/.agent/task.md b/templates/.agent/task.md new file mode 100644 index 0000000..a39d45e --- /dev/null +++ b/templates/.agent/task.md @@ -0,0 +1,14 @@ +# Task Tracker Template + +This file is a template/reference for task tracking behavior. + +Live tracking must happen in `<project-root>/docs/plans/task.md`. + +The live task file should contain only task list rows (no instructions or prose). + +| id | task | status | notes | +| --- | --- | --- | --- | +| example-1 | Read applicable skill and restate scope | pending | | +| example-2 | Implement scoped changes | pending | | +| example-3 | Run verification commands | pending | | +| example-4 | Report evidence and finalize | pending | | diff --git a/templates/.agent/tests/check-antigravity-profile.sh b/templates/.agent/tests/check-antigravity-profile.sh new file mode 100644 index 0000000..7b93294 --- /dev/null +++ b/templates/.agent/tests/check-antigravity-profile.sh @@ -0,0 +1,172 @@ +#!/usr/bin/env bash +set -euo pipefail + +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" +AGENT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)" +ROOT_DIR="$(cd "$AGENT_DIR/.." && pwd)" + +PASS_COUNT=0 +FAIL_COUNT=0 + +pass() { + echo " [PASS] $1" + PASS_COUNT=$((PASS_COUNT + 1)) +} + +fail() { + echo " [FAIL] $1" + FAIL_COUNT=$((FAIL_COUNT + 1)) +} + +require_file() { + local path="$1" + if [ -f "$path" ]; then + pass "File exists: $path" + else + fail "Missing file: $path" + fi +} + +require_absent() { + local path="$1" + if [ ! -e "$path" ]; then + pass "File absent (as expected): $path" + else + fail "File should be absent: $path" + fi +} + +echo "========================================" +echo " Antigravity Profile Checks" +echo "========================================" +echo "" + +echo "Checking required files..." + +required_files=( + "$AGENT_DIR/AGENTS.md" + "$AGENT_DIR/INSTALL.md" + "$AGENT_DIR/task.md" + "$AGENT_DIR/workflows/brainstorm.md" + "$AGENT_DIR/workflows/write-plan.md" + "$AGENT_DIR/workflows/execute-plan.md" + "$AGENT_DIR/agents/code-reviewer.md" + "$SCRIPT_DIR/check-antigravity-profile.sh" + "$SCRIPT_DIR/run-tests.sh" +) + +for file in "${required_files[@]}"; do + require_file "$file" +done + +require_absent "$ROOT_DIR/docs/plans/task.md" + +required_skills=( + "brainstorming" + "executing-plans" + "finishing-a-development-branch" + "receiving-code-review" + "requesting-code-review" + "systematic-debugging" + "test-driven-development" + "using-git-worktrees" + "using-superpowers" + "verification-before-completion" + "writing-plans" + "writing-skills" + "single-flow-task-execution" +) + +for skill in "${required_skills[@]}"; do + require_file "$AGENT_DIR/skills/$skill/SKILL.md" +done + +# Verify prompt template files for single-flow-task-execution +require_file "$AGENT_DIR/skills/single-flow-task-execution/implementer-prompt.md" +require_file "$AGENT_DIR/skills/single-flow-task-execution/spec-reviewer-prompt.md" +require_file "$AGENT_DIR/skills/single-flow-task-execution/code-quality-reviewer-prompt.md" + +echo "" +echo "Checking frontmatter..." + +for skill in "${required_skills[@]}"; do + file="$AGENT_DIR/skills/$skill/SKILL.md" + + if rg -q '^---$' "$file"; then + pass "$skill has frontmatter delimiters" + else + fail "$skill missing frontmatter delimiters" + fi + + if rg -q '^name:\s*[^[:space:]].*$' "$file"; then + pass "$skill has name field" + else + fail "$skill missing name field" + fi + + if rg -q '^description:\s*[^[:space:]].*$' "$file"; then + pass "$skill has description field" + else + fail "$skill missing description field" + fi +done + +echo "" +echo "Checking for unsupported legacy instructions..." + +legacy_patterns=( + 'Skill tool' + 'Task tool with' + 'Task\("' + 'Dispatch implementer subagent' + 'Dispatch code-reviewer subagent' + 'Create TodoWrite' + 'Mark task complete in TodoWrite' + 'Use TodoWrite' + 'superpowers:' +) + +for pattern in "${legacy_patterns[@]}"; do + if rg -q "$pattern" "$AGENT_DIR/skills"; then + fail "Legacy pattern found in skills: $pattern" + else + pass "Legacy pattern absent: $pattern" + fi +done + +echo "" +echo "Checking AGENTS mapping contract..." + +mapping_checks=( + 'Task.*task_boundary' + 'browser_subagent' + 'Skill.*view_file' + 'TodoWrite.*docs/plans/task\.md' + 'run_command' + 'grep_search' + 'find_by_name' + 'mcp_\*' +) + +for pattern in "${mapping_checks[@]}"; do + if rg -q "$pattern" "$AGENT_DIR/AGENTS.md"; then + pass "AGENTS includes mapping: $pattern" + else + fail "AGENTS missing mapping: $pattern" + fi +done + +echo "" +echo "========================================" +echo " Summary" +echo "========================================" +echo " Passed: $PASS_COUNT" +echo " Failed: $FAIL_COUNT" +echo "" + +if [ "$FAIL_COUNT" -gt 0 ]; then + echo "STATUS: FAILED" + exit 1 +fi + +echo "STATUS: PASSED" diff --git a/templates/.agent/tests/run-tests.sh b/templates/.agent/tests/run-tests.sh new file mode 100644 index 0000000..7c51d38 --- /dev/null +++ b/templates/.agent/tests/run-tests.sh @@ -0,0 +1,11 @@ +#!/usr/bin/env bash +set -euo pipefail + +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" + +echo "========================================" +echo " Antigravity Profile Test Runner" +echo "========================================" +echo "" + +bash "$SCRIPT_DIR/check-antigravity-profile.sh" diff --git a/templates/.agent/workflows/brainstorm.md b/templates/.agent/workflows/brainstorm.md new file mode 100644 index 0000000..a65dde0 --- /dev/null +++ b/templates/.agent/workflows/brainstorm.md @@ -0,0 +1,5 @@ +--- +description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation." +--- + +Invoke the `.agent/skills/brainstorming/SKILL.md` workflow and follow it exactly as presented to you. diff --git a/templates/.agent/workflows/execute-plan.md b/templates/.agent/workflows/execute-plan.md new file mode 100644 index 0000000..c6af271 --- /dev/null +++ b/templates/.agent/workflows/execute-plan.md @@ -0,0 +1,5 @@ +--- +description: Execute plan in single-flow mode +--- + +Invoke the `.agent/skills/executing-plans/SKILL.md` workflow and follow it exactly as presented to you. diff --git a/templates/.agent/workflows/write-plan.md b/templates/.agent/workflows/write-plan.md new file mode 100644 index 0000000..2f77e4d --- /dev/null +++ b/templates/.agent/workflows/write-plan.md @@ -0,0 +1,5 @@ +--- +description: Create detailed implementation plan with bite-sized tasks +--- + +Invoke the `.agent/skills/writing-plans/SKILL.md` workflow and follow it exactly as presented to you. diff --git a/tests/init.test.mjs b/tests/init.test.mjs new file mode 100644 index 0000000..1c51be6 --- /dev/null +++ b/tests/init.test.mjs @@ -0,0 +1,79 @@ +import { mkdtemp, mkdir, rm, access } from "node:fs/promises"; +import { constants as fsConstants } from "node:fs"; +import { join, resolve } from "node:path"; +import { spawnSync } from "node:child_process"; +import { tmpdir } from "node:os"; +import test from "node:test"; +import assert from "node:assert/strict"; + +const cliPath = resolve( + process.cwd(), + "bin/antigravity-superpowers.js", +); + +async function pathExists(path) { + try { + await access(path, fsConstants.F_OK); + return true; + } catch { + return false; + } +} + +function runCli(args, cwd) { + return spawnSync(process.execPath, [cliPath, ...args], { + cwd, + encoding: "utf8", + }); +} + +async function createTempProject(prefix) { + const baseTmp = tmpdir(); + await mkdir(baseTmp, { recursive: true }); + return mkdtemp(join(baseTmp, prefix)); +} + +test("init creates .agent in a fresh project", async () => { + const projectDir = await createTempProject("agsp-fresh-"); + + try { + const result = runCli(["init"], projectDir); + assert.equal(result.status, 0); + + const hasAgent = await pathExists(join(projectDir, ".agent", "AGENTS.md")); + assert.equal(hasAgent, true); + } finally { + await rm(projectDir, { recursive: true, force: true }); + } +}); + +test("init fails when .agent exists without --force", async () => { + const projectDir = await createTempProject("agsp-existing-"); + + try { + await mkdir(join(projectDir, ".agent"), { recursive: true }); + + const result = runCli(["init"], projectDir); + assert.equal(result.status, 1); + assert.match(result.stderr, /already exists/i); + assert.match(result.stderr, /--force/i); + } finally { + await rm(projectDir, { recursive: true, force: true }); + } +}); + +test("init replaces .agent with --force", async () => { + const projectDir = await createTempProject("agsp-force-"); + + try { + await mkdir(join(projectDir, ".agent"), { recursive: true }); + + const result = runCli(["init", "--force"], projectDir); + assert.equal(result.status, 0); + + const hasTemplate = await pathExists(join(projectDir, ".agent", "AGENTS.md")); + assert.equal(hasTemplate, true); + } finally { + await rm(projectDir, { recursive: true, force: true }); + } +});