メニュー
Create AGENTS.md files with production-ready best practices. Use when creating new AGENTS.md or implementing quality gates.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | agents-md |
| description | Create AGENTS.md files with production-ready best practices. Use when creating new AGENTS.md or implementing quality gates. |
| license | MIT |
Create production-ready AGENTS.md files following best practices below.
Basic:
cat > AGENTS.md << 'EOF'
# AGENTS.md
## Named Constants
readonly MAX_FILE_SIZE=500
## Setup
- Install: pnpm install
- Test: pnpm test
## Code Style
- TypeScript strict
- Max line: 100
EOF
Production: See guide in agents-docs/ folder
## Named Constants
readonly MAX_FILE_SIZE=500
readonly TIMEOUT_SECONDS=30
readonly MAX_RETRIES=3
## Pre-existing Issues
**Fix ALL before completing:**
- [ ] Lint warnings
- [ ] Test failures
- [ ] Security vulnerabilities
## Quality Gate
```bash
pnpm run typecheck
pnpm run lint
pnpm run test
pnpm audit
## Tier Structure
- **Tier 1 (Essential):** Constants, setup, style, testing
- **Tier 2 (Professional):** Add quality gate, atomic commit, security
- **Tier 3 (Enterprise):** Add skills, sub-agents, nested AGENTS.md
See `agents-docs/AVAILABLE_SKILLS.md` for tier details.
## Best Practices
### DO:
- Define named constants at top
- Include pre-existing issue policy
- Specify quality gate commands
- Reference @agents-docs/ for detail
### DON'T:
- Use magic numbers
- Skip pre-existing issues
- Write vague commands ("run tests")
- Duplicate README content
## Quality Criteria
- [ ] Named constants defined
- [ ] Pre-existing issue policy included
- [ ] Quality gate specified
- [ ] < 160 lines (progressive disclosure)
## References
- `agents-docs/AVAILABLE_SKILLS.md` - Skill framework
- `agents-docs/SUB-AGENTS.md` - Sub-agent patterns
- https://agents.md - Official spec
Retrieve semantically relevant past learnings and analysis outputs using the csm CLI (HDC encoder with hybrid BM25 retrieval)
Execute tests, analyze results, and diagnose failures across any testing framework. Use when running test suites, debugging failing tests, or configuring CI/CD testing pipelines.
Use this skill for Turso (LibSQL/Limbo) database development, including scaffolding, querying, migrations, and maintenance. Supports vector search, full-text search, CDC, MVCC, encryption, and bidirectional remote sync. Use when working with Turso SDKs for JavaScript, Rust, Python, Go, and React Native. Provides current API guidance to avoid stale "libsql" legacy knowledge.
Atomic git workflow - validates, commits, pushes, creates PR, and verifies CI with zero-warnings policy. Orchestrates complete code submission as state machine with rollback on failure.
Automated code review with PR analysis, change summaries, and quality checks. Use for reviewing pull requests, generating review comments, checking against best practices, and identifying potential issues. Includes style guide compliance, security issue detection, and review automation.
Unified atomic git workflow with GitHub integration - commits all changes, checks GitHub issues, creates PR, validates all Actions pass including pre-existing, uses swarm coordination with web research on failures. Post-merge validation of all files and docs.