Agent skill
ce-skill-audit
Audit the skills catalog for frontmatter quality, trigger precision, structural hygiene, and registry synchronization.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/ce-skill-audit
SKILL.md
CE Skill Audit
Use this skill for a critical quality audit of repository skills.
Load these references first:
references/claude_skills_how_to_checklist.mdreferences/trigger_phrase_catalog.md
Audit workflow
- Inventory skills and required files:
Get-ChildItem .claude/skills -Directory | Select-Object -ExpandProperty Name
rg --files .claude/skills
- Structural checks (per skill):
SKILL.mdexists- YAML frontmatter exists
namematches directory namedescriptionexists and is specific- file length remains maintainable (
<500lines target)
- Trigger-quality checks:
- descriptions are specific enough to avoid accidental over-triggering
- overlapping skills have clear differentiation
- description length and style pass the strict checker:
pwsh .claude/skills/ce-skill-audit/scripts/check_skill_description_quality.ps1
- Content organization checks:
- long static templates live in
assets/ - large reference material lives in
references/ - deterministic generators live in
scripts/ - phrase-heavy trigger synonyms are extracted to references (not embedded in frontmatter descriptions)
- Registry consistency checks:
CONTRIBUTOR_INSTRUCTIONS.mdsection 6A.claude/skills/ce-onboard/SKILL.mdsection 4docs/contributor/agent_skills.md- filesystem set equality must hold
Output contract
Return findings first, grouped by severity:
- blocker (breaks discoverability/routing)
- high (likely mis-triggering or stale registry)
- medium (maintainability issues)
- low (style/clarity improvements)
Each finding must include:
- skill/file reference
- violated rule
- exact remediation
Constraints
- Do not propose evaluation-skill additions in this audit.
- Do not mark audit complete while registries and filesystem differ.
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?