Files
antigravity-skills-reference/skills/agents-md/SKILL.md
Al-Garadi ef285b5c97 fix: sync upstream main with Windows validation and skill guidance cleanup (#457)
* fix: stabilize validation and tests on Windows

* test: add Windows smoke coverage for skill activation

* refactor: make setup_web script CommonJS

* fix: repair aegisops-ai frontmatter

* docs: add when-to-use guidance to core skills

* docs: add when-to-use guidance to Apify skills

* docs: add when-to-use guidance to Google and Expo skills

* docs: add when-to-use guidance to Makepad skills

* docs: add when-to-use guidance to git workflow skills

* docs: add when-to-use guidance to fp-ts skills

* docs: add when-to-use guidance to Three.js skills

* docs: add when-to-use guidance to n8n skills

* docs: add when-to-use guidance to health analysis skills

* docs: add when-to-use guidance to writing and review skills

* meta: sync generated catalog metadata

* docs: add when-to-use guidance to Robius skills

* docs: add when-to-use guidance to review and workflow skills

* docs: add when-to-use guidance to science and data skills

* docs: add when-to-use guidance to tooling and automation skills

* docs: add when-to-use guidance to remaining skills

* fix: gate bundle helper execution in Windows activation

* chore: drop generated artifacts from contributor PR

* docs(maintenance): Record PR 457 sweep

Document the open issue triage, PR supersedence decision, local verification, and source-only cleanup that prepared PR #457 for re-running CI.

---------

Co-authored-by: sickn33 <sickn33@users.noreply.github.com>
2026-04-05 21:04:39 +02:00

127 lines
4.3 KiB
Markdown

---
name: agents-md
description: This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
risk: unknown
source: community
---
# Maintaining AGENTS.md
AGENTS.md is the canonical agent-facing documentation. Keep it minimal—agents are capable and don't need hand-holding. Target under 60 lines; never exceed 100. Instruction-following quality degrades as document length increases.
## When to Use
- The user asks to create, update, or audit `AGENTS.md` or `CLAUDE.md`.
- The project needs concise, high-signal agent instructions derived from the actual toolchain and repo layout.
- Existing agent documentation is too long, duplicated, or drifting away from real project conventions.
## File Setup
1. Create `AGENTS.md` at project root
2. Create symlink: `ln -s AGENTS.md CLAUDE.md`
## Before Writing
Analyze the project to understand what belongs in the file:
1. **Package manager** — Check for lock files (`pnpm-lock.yaml`, `yarn.lock`, `package-lock.json`, `uv.lock`, `poetry.lock`)
2. **Linter/formatter configs** — Look for `.eslintrc`, `biome.json`, `ruff.toml`, `.prettierrc`, etc. (don't duplicate these in AGENTS.md)
3. **CI/build commands** — Check `Makefile`, `package.json` scripts, CI configs for canonical commands
4. **Monorepo indicators** — Check for `pnpm-workspace.yaml`, `nx.json`, Cargo workspace, or subdirectory `package.json` files
5. **Existing conventions** — Check for existing CONTRIBUTING.md, docs/, or README patterns
## Writing Rules
- **Headers + bullets** — No paragraphs
- **Code blocks** — For commands and templates
- **Reference, don't embed** — Point to existing docs: "See `CONTRIBUTING.md` for setup" or "Follow patterns in `src/api/routes/`"
- **No filler** — No intros, conclusions, or pleasantries
- **Trust capabilities** — Omit obvious context
- **Prefer file-scoped commands** — Per-file test/lint/typecheck commands over project-wide builds
- **Don't duplicate linters** — Code style lives in linter configs, not AGENTS.md
## Required Sections
### Package Manager
Which tool and key commands only:
```markdown
## Package Manager
Use **pnpm**: `pnpm install`, `pnpm dev`, `pnpm test`
```
### File-Scoped Commands
Per-file commands are faster and cheaper than full project builds. Always include when available:
```markdown
## File-Scoped Commands
| Task | Command |
|------|---------|
| Typecheck | `pnpm tsc --noEmit path/to/file.ts` |
| Lint | `pnpm eslint path/to/file.ts` |
| Test | `pnpm jest path/to/file.test.ts` |
```
### Commit Attribution
Always include this section. Agents should use their own identity:
```markdown
## Commit Attribution
AI commits MUST include:
```
Co-Authored-By: (the agent model's name and attribution byline)
```
Example: `Co-Authored-By: Claude Sonnet 4 <noreply@example.com>`
```
### Key Conventions
Project-specific patterns agents must follow. Keep brief.
## Optional Sections
Add only if truly needed:
- API route patterns (show template, not explanation)
- CLI commands (table format)
- File naming conventions
- Project structure hints (point to critical files, flag legacy code to avoid)
- Monorepo overrides (subdirectory `AGENTS.md` files override root)
## Anti-Patterns
Omit these:
- "Welcome to..." or "This document explains..."
- "You should..." or "Remember to..."
- Linter/formatter rules already in config files (`.eslintrc`, `biome.json`, `ruff.toml`)
- Listing installed skills or plugins (agents discover these automatically)
- Full project-wide build commands when file-scoped alternatives exist
- Obvious instructions ("run tests", "write clean code")
- Explanations of why (just say what)
- Long prose paragraphs
## Example Structure
```markdown
# Agent Instructions
## Package Manager
Use **pnpm**: `pnpm install`, `pnpm dev`
## Commit Attribution
AI commits MUST include:
```
Co-Authored-By: (the agent model's name and attribution byline)
```
## File-Scoped Commands
| Task | Command |
|------|---------|
| Typecheck | `pnpm tsc --noEmit path/to/file.ts` |
| Lint | `pnpm eslint path/to/file.ts` |
| Test | `pnpm jest path/to/file.test.ts` |
## API Routes
[Template code block]
## CLI
| Command | Description |
|---------|-------------|
| `pnpm cli sync` | Sync data |
```