Audit Library Health

Kører ai-agent-skills doctor, check og curate review for at auditere et skills library workspace

Af MoizIbnYousaf · MoizIbnYousaf/Ai-Agent-Skills

Virker med opsætning ★ 5.6/10

Audit Library Health — Kører ai-agent-skills doctor, check og curate review for at auditere et skills library workspace

Hvad det gør

En fem-trins tjekliste til auditering af et ai-agent-skills library workspace: valider kataloget, kør doctor på installerede skills, tjek upstream-kilder for opdateringer, bekræft at genererede README/WORK_AREAS docs er synkroniserede, og gennemgå curation-køen. Udløses, når du spørger, om et skills library er sundt, konsistent eller sikkert at pushe til et delt repo. Det er en tynd wrapper over `npx ai-agent-skills` CLI'en og gør intet uden den CLI og et initialiseret workspace.

Testrapport

Installerede ai-agent-skills@4.3.2 fra npm og kørte alle fem workflow-trin for alvor, først i en tom mappe og derefter inde i et workspace oprettet med `init-library`. Tre trin virker som skrevet (`doctor --format json` markerede 3 ødelagte poster i min ~/.claude/skills; `check --format json` scannede 249 installationer; `curate review` udskrev en tom kø), men to gør ikke: bare `npx ai-agent-skills validate` ved bibliotekets rod returnerer status "error / No SKILL.md found", fordi den medfølgende `validate` er en per-skill-directory validator, not the catalog check the body describes, and `build-docs --dry-run --format json` dies with ENOENT on `node_modules/ai-agent-skills/WORK_AREAS.md` (cli.js passes the workspace context into `generatedDocsAreInSync`'s options slot, so it falls back to the bundled package dir, and WORK_AREAS.md is excluded from package.json `files`) — so the `currentlyInSync` value the skill tells you to branch on is unreachable, while plain `build-docs` succeeds. Baseline-sammenligning: `npx ai-agent-skills help` lister allerede doctor/check/validate/build-docs/curate review plus `--format json` og `--dry-run`, og beskriver validate korrekt, so an agent with no skill produced a 5-for-5 clean audit while the skill body produced one false failure and one crash; the Gotchas and Health Checklist sections are accurate and are the skill's only real added value. No security smells found — no curl|sh, no base64 blobs, no secret exfiltration, no injection text; `check` does make outbound GitHub requests, which the skill discloses.

Testet: 2026-07-21 · Claude Code 2.x (agent harness)

Installation

mkdir -p ~/.claude/skills/audit-library-health
curl -sL https://raw.githubusercontent.com/MoizIbnYousaf/Ai-Agent-Skills/HEAD/skills/audit-library-health/SKILL.md \
  -o ~/.claude/skills/audit-library-health/SKILL.md

# Required runtime — the skill is only CLI invocations:
npm i -g ai-agent-skills   # or use npx per-command

# Steps 1/4/5 need an initialized workspace, not just an install:
npx ai-agent-skills init-library my-library
cd my-library

Kommandoer og eksempelprompter

  • /audit-library-healthKører ai-agent-skills doctor, check og curate review for at auditere et skills library workspace

Skills udløses af almindelige forespørgsler — ingen kommandoer at huske. Efter installationen aktiverer prompter som disse skillen (på engelsk):

  • Check the health of our skills library
  • Validate all skills and flag stale ones
  • Verify our generated docs are in sync