MoizIbnYousafMoizIbnYousaf/Ai-Agent-Skills/skills/audit-library-health/SKILL.md

audit-library-health

Skill1.1k starsChanged 8 months agoMITView on GitHub

Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 5 are distinctive, and 5 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Verify that a skills library is consistent, up-to-date, and ready to share or install from.
line 12
Very specific:
Always use --format json for structured output when automating health checks.
line 16
Very specific:
Always use --dry-run before running build-docs to check if docs are already in sync.
line 17
Very specific:
Never push a library to a shared repo without passing validate and doctor first.
line 18
Very specific:
Use --fields to limit output when inspecting large catalogs.
line 19
Distinctive:
Run the validation script to check catalog integrity.
line 23
Distinctive:
Run doctor to check installed skills health.
line 31
Distinctive:
Check for skills that may need updates.
line 37
Distinctive:
Verify generated docs are in sync.
line 43
Very specific:
If currentlyInSync is false, regenerate:
line 49

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Audit Library Health

Goal

Verify that a skills library is consistent, up-to-date, and ready to share or install from.

Guardrails

Always use --format json for structured output when automating health checks.
Always use --dry-run before running build-docs to check if docs are already in sync.
Never push a library to a shared repo without passing validate and doctor first.
Use --fields to limit output when inspecting large catalogs.

Workflow

Run the validation script to check catalog integrity.

npx ai-agent-skills validate

This checks: required fields, folder consistency, frontmatter validity, collection integrity, and generated doc sync.

Run doctor to check installed skills health.

npx ai-agent-skills doctor --format json

Check for skills that may need updates.

npx ai-agent-skills check --format json

Verify generated docs are in sync.

npx ai-agent-skills build-docs --dry-run --format json

If currentlyInSync is false, regenerate:

npx ai-agent-skills build-docs

Review the curation queue for skills needing attention.

npx ai-agent-skills curate review --format json

Health Checklist

validate passes with no errors
doctor reports no broken installs
build-docs --dry-run shows docs are in sync
No skills with empty whyHere fields
All house skills have matching folders in skills/
skills.json total matches actual skill count

Gotchas

validate and doctor are read-only — they never mutate the library.
check makes network requests to verify upstream sources. It may be slow or timeout on unreachable repos.
The curate review queue is derived from missing fields and stale verification dates — it is a heuristic, not a mandate.

Download now (ZIP)

Other versions2 projects use a version of this.
Word for word · 2
skillcreatorai/Ai-Agent-Skills★ 1.1k100% same
MoizIbnYousaf/ai-agent-skills★ 1.1k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository17 other files it gives its agents.
- ask-questions-if-underspecifiedSkill
- backend-developmentSkill
- best-practicesSkill
- browse-and-evaluateSkill
- build-workspace-docsSkill
- changelog-generatorSkill
- code-documentationSkill
- content-research-writerSkill
- curate-a-team-librarySkill
- database-designSkill
- install-from-remote-librarySkill
- llm-application-devSkill
- migrate-skills-between-librariesSkill
- review-a-skillSkill
- share-a-librarySkill
- update-installed-skillsSkill
- verification-agentSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free