
Before you push changes to a shared skills library or hand it off to a team, run this to make sure everything's actually consistent. It chains together validate, doctor, check, and a dry run of build-docs to catch missing fields, broken installs, stale skills, and out-of-sync generated documentation. The checklist format is helpful because library health isn't one command, it's a routine. One thing to know: the check step hits the network to verify upstream sources, so it can be slow if repos are unreachable. Think of this as pre-flight before you commit or publish.
$ npx -y skills add moizibnyousaf/ai-agent-skills --skill audit-library-health --agent claude-codeInstalls into .claude/skills of the current project.
Verify that a skills library is consistent, up-to-date, and ready to share or install from.
--format json for structured output when automating health checks.--dry-run before running build-docs to check if docs are already in sync.validate and doctor first.--fields to limit output when inspecting large catalogs.npx ai-agent-skills validate
This checks: required fields, folder consistency, frontmatter validity, collection integrity, and generated doc sync.
npx ai-agent-skills doctor --format json
npx ai-agent-skills check --format json
npx ai-agent-skills build-docs --dry-run --format json
If currentlyInSync is false, regenerate:
npx ai-agent-skills build-docs
Sponsors