Skill audit
Make AI Agents great again!
npx -y skills add MAHDTech/agent-skills --skill skill-auditAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Periodically audit the whole skill collection for health — validate each skill's frontmatter, clarity, and category, verify every cross-reference resolves, and surface duplicates, conflicts, retirement candidates, and missing-skill gaps. Use when you want to audit or health-check the skills, spring-clean the collection, confirm the router and cross-references are accurate, or find skills to merge, split, retire, or create. Hands findings to /skill-creator to fix or create and /deprecate-skill to retire.
SKILL.md
4.4 KB, 945 tokens by cl100k_base, as published. Nobody here has run it
Skill Audit
A periodic health sweep of the whole skills/ tree — run it on a cadence, not per change. Validating one skill you just wrote is /skill-creator's job; this walks the collection and judges it as a set. The output is a findings list, not silent edits: audit, report, then route each finding to the skill that fixes it.
The tree is the single source of truth; the generated README, agents/AGENTS.md, dashboard, and skills.sh.json are downstream of it.
Before you start
Two mechanical gates come first — they are cheap and catch drift a read-through would miss:
devenv shell -- skills --action lint— frontmatter, naming, placement. Record every error; these are findings.devenv shell -- skills --action sync, then checkgit status. A diff means the generated artifacts had drifted from the tree — the drift is itself a finding.
The audit
Walk the whole collection. Each pass carries an exhaustive bound — every skill, every reference, no sampling.
-
Inventory. List every promoted skill — one per
skills/<category>/<name>/, excluding thein-progress/anddeprecated/lifecycle buckets — grouped by category. This inventory is what the rest of the audit checks against. -
Per-skill review. Apply the checklist below to every skill in the inventory.
-
Cross-reference integrity. Collect every
/skill-namementioned in anySKILL.mdand confirm each resolves to a promoted skill of that name. A reference to a deprecated or nonexistent skill is a dangling reference — record it. Then confirm the/skill-routerindex names every promoted skill exactly once, and names nothing deprecated or gone.# promoted skill names (the inventory) ls -d skills/*/*/ | grep -vE '/(in-progress|deprecated)/' | xargs -n1 basename # every /skill-name reference to reconcile against it grep -rhoE '/[a-z][a-z0-9]+(-[a-z0-9]+)*' skills --include=SKILL.md | sort -u -
Collection-level review. Across the whole set, look for:
- Duplication or conflict — two skills covering the same branch, or giving contradictory guidance. Recommend a merge or a sharper boundary between them.
- Retirement candidates — a skill superseded, stale, or that no realistic task would reach. Route to
/deprecate-skill. - Gaps — a recurring task with no skill to serve it. Route to
/skill-creator.
-
Report. Emit one findings list. Each finding names the skill(s) it touches, the problem, and a recommended action — edit or create via
/skill-creator, retire via/deprecate-skill, fix a reference in place.
Per-skill checklist (reference)
For each skill in the inventory:
- Frontmatter valid —
nameequals the directory, kebab-case, prefix-free, ≤64 chars, no "claude"/"anthropic";descriptionis one line, ≤1024 chars, stating what it does and when to use it. Canonical keys only — no legacycustom:,triggers:,category:, ortype:. - Categorised right — sits in the topic bucket matching what it does, and is not stranded in
in-progress/ordeprecated/while still live. - Description earns its load — one trigger per branch, leading word front-loaded, no identity already stated in the body.
- Body is lean — no sediment (stale lines), no sprawl (simply too long), no duplication (one meaning, one place), no no-op (default behaviour restated), no negation (steer by the positive target).
- References resolve — its
/skill-namementions and sibling-file pointers all hit live targets.
Done when
Every skill in the inventory has been through the checklist, every /skill-name reference has been resolved to a live skill or recorded as dangling, the router has been checked against the inventory, and the findings list names each problem with a recommended action and the skill it belongs to.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.