Agent skill
meta__write_agents_md
Creates or updates AGENTS.md files with proper structure, skill references, and best practices. Use when adding AI assistant guidance to a project or subdirectory.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/meta-write-agents-md
SKILL.md
Create effective AGENTS.md files that delegate work to existing skills.
Key Principle: Keep under 150 lines, link to details, defer workflows to skills.
-
Identify Scope
- Root: Organization-wide standards, overall architecture
- Subdirectory: Context-specific guidance (e.g.,
src/ApiService/AGENTS.md) - Use nested files when root exceeds 150 lines
-
Use Template
- Copy templates/AGENTS.md as starting point
- Replace all
{placeholders}with actual values - Follow templates/BEST-PRACTICES.md for guidance
-
Reference Skills, Don't Explain
- ✅ "Scaffold:
/wolverine__create_operation" - ❌ "To add a write operation: 1. Create command... 2. Create event... 3. Add Apply..."
- Check
.claude/skills/for available skills
- ✅ "Scaffold:
-
Follow Structure
- Quick Reference (stack, commands)
- Key Rules (✅ good / ❌ bad)
- Common Mistakes (→ solutions)
- Project Layout (table)
- Skills (categorized)
- Quick Troubleshooting
- Documentation Index
// turbo 5. Verify Quality
- Use templates/CHECKLIST.md for validation
- Run:
wc -l AGENTS.md(should be < 150) - Check all skill references exist
- Ensure no sensitive information
Related Skills
Prerequisites:
- None - This skill is standalone
Next Steps:
- Test the AGENTS.md by asking an AI agent to perform common tasks
- Update AGENTS.md in pull requests when processes change
See Also:
/meta__create_skill- For creating new skills referenced in AGENTS.md
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?