What do I need to use GitHub Repo Vitals?

The repo; The stakes; How many repos.

Is GitHub Repo Vitals 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.

GitHub Repo Vitals

Q: How do I know the GitHub Repo Vitals output is good?

The skill verifies itself against its own quality checks: The archived flag was checked first and short-circuits everything; Responsiveness came from a sample, not the open-issues count; Activity age is read against the project's nature; Contributor concentration is noted as risk-with-nuance, not indictment.

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

Read a GitHub repository's vital signs with keyless curl — commit recency, release cadence, issue/PR responsiveness, and bus factor — interpreted into an is-this-project-alive verdict. Use when asked is this repo maintained, check this project before we build on it, how active is this library's development, or compare these repos' health. Produces the vitals with their reads, the responsiveness sampling, the rate-limit-aware command set, and the alive/coasting/abandoned verdict.

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

What to give it

▸The repo — owner/name; from a package check, the registry metadata's repository URL (chain from [package-health](../package-health/SKILL.md))

▸The stakes — building on it, contributing to it, or evaluating for a fork: the verdict calibrates ("coasting" blocks adoption of a framework, not of a finished parser)

▸How many repos — the anonymous budget is ~60 calls/hour; a comparison of five repos is fine, a screening of fifty needs a token (say so rather than degrade)

✅ 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 archived flag was checked first and short-circuits everything

✓Responsiveness came from a sample, not the open-issues count

✓Activity age is read against the project's nature

✓Contributor concentration is noted as risk-with-nuance, not indictment

✓The call budget stayed anonymous-friendly and rate limits are reported, never papered over

⚠️ What it refuses to do

Do not read stars as health — attention once ≠ maintenance now

Do not count open issues as a negative — sample how they're treated instead

Do not burn the rate budget on one repo's full history — five calls tell the story

Do not fabricate around a 403 — rate-limited is a reportable state

Do not condemn quiet-but-finished projects — the nature test applies before the verdict

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="github-repo-vitals"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

GitHub Repo Vitals 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