What do I need to use Package Health?

The package(s) and ecosystem; The role it would play; The runtime context.

Is Package Health free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Package Health

Q: How do I know the Package Health output is good?

The skill verifies itself against its own quality checks: The exact package name was verified — near-miss names flagged, never auto-corrected; The read interprets age against the package's purpose, not against a universal freshness bar; Warning shapes (riding-a-corpse, bus-factor, registry deprecation) are checked; The repo-vitals chain is offered when the registry signals are ambiguous.

🔵 Stable🕐 updated 2026-07-18 🔷 SkillSpec L3 pm-live

Check a package's health before you depend on it — npm and PyPI registry APIs via keyless curl: downloads, release recency, maintenance signals, and the dependency-decision read. Use when asked is this npm package maintained, check this PyPI library before we adopt it, compare these two packages, or is this dependency abandoned. Produces the health read with the signals interpreted (not just listed), the numbers with their commands, and the adopt/avoid/vendor recommendation framing.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The package(s) and ecosystem — npm or PyPI; exact names (typosquats are a real hazard — the exact-name check is part of the job, and a near-miss name is a 🔴 finding, not a typo to auto-correct)

▸The role it would play — a core dependency, a dev tool, a one-function utility: the stakes calibrate the read ("finished" is fine for a slugify; concerning for a crypto library)

▸The runtime context — versions/platforms that matter for compatibility checking

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓The exact package name was verified — near-miss names flagged, never auto-corrected

✓The read interprets age against the package's purpose, not against a universal freshness bar

✓Warning shapes (riding-a-corpse, bus-factor, registry deprecation) are checked

✓The repo-vitals chain is offered when the registry signals are ambiguous

✓Security audit is scoped out explicitly, not implied

⚠️ What it refuses to do

Do not present a stats dump as a health check — the read is the product

Do not treat "old" as "dead" without the purpose test — finished software exists

Do not auto-correct package names — typosquats are the attack this check can catch

Do not extrapolate download counts into quality — popularity is a signal about forks and eyes, not correctness

Do not answer from memory — versions and deprecations are live facts; fetch or hand over the commands

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="package-health"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Package Health is one of 750 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog