一键导入
agents-md
Create AGENTS.md files with production-ready best practices. Use when creating new AGENTS.md or implementing quality gates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Create AGENTS.md files with production-ready best practices. Use when creating new AGENTS.md or implementing quality gates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Coordinate multiple agents for software development across any language. Use for parallel execution of independent tasks, sequential chains with dependencies, swarm analysis from multiple perspectives, or iterative refinement loops. Handles Python, JavaScript, Java, Go, Rust, C#, and other languages.
Multi-step GOAP planning for complex audio pipeline development. Orchestrates analysis, decomposition, strategy selection, and execution with state persistence in plans/.
Generates DORA metrics and agent delivery reports from structured events.
Records agent execution events for lead time, success rate, and human intervention tracking.
Generic TRIZ analysis for identifying technical and physical contradictions in software architecture and pipelines.
Generic TRIZ solver for resolving architectural and technical contradictions using inventive principles.
| 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.
AGENTS.md from scratch.Basic:
cat > AGENTS.md << 'EOF'
# AGENTS.md
## Named Constants
readonly MAX_FILE_SIZE=500
## Setup
- Install: npm install
- Test: npm 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
npm run typecheck
npm run lint
npm run test
npm 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/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/SKILLS.md` - Skill framework
- `agents-docs/SUB-AGENTS.md` - Sub-agent patterns
- https://agents.md - Official spec