| name | skill-standards |
| description | Use when creating, updating, reviewing, or auditing a skill or superskill and you need a concrete quality bar for triggers, project grounding, metadata, authorship, routing, context efficiency, scripts, and validation. |
| metadata | {"owner":"tze","authors":["tze","OpenAI Codex","Claude"],"status":"active","last_reviewed":"2026-07-19"} |
| compatibility | Requires uv to run scripts/audit_skill.py. |
Skill Standards
Review bar for new skills and updates to existing ones, including
router-style superskills.
The standard: easy to discover, cheap to load, grounded in the right source
of truth, explicit about who owns it.
Use This Skill When
- Creating a new skill; you want a quality bar before shipping it
- Reviewing or auditing a skill for discoverability, grounding, context
efficiency, and maintainability
- Updating a skill; checking for drift, bloat, or stale metadata
- Designing a superskill that routes to internal subskills without putting
every subskill in the global skill catalog
Example trigger phrasings: "review this skill", "is this SKILL.md well
designed", "audit our skills for quality", "should this be a superskill",
"clean up this skill package".
Do Not Use This Skill For
- Replacing
/skill-creator for initial scaffolding or end-to-end authoring
- Replacing project-specific doctrine or navigation skills such as
/th-projects
- Acting as the domain skill itself; this is a rubric for skill quality, not
domain guidance
