What do I need to use PR Description?

The change; The why; Testing; Risk & rollout.

Is PR Description 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.

PR Description

Q: How do I know the PR Description output is good?

The skill verifies itself against its own quality checks: Title is concise and imperative; the why and linked issue are clear up front; Changes summarize intent, not a file-by-file dump; Testing is specific (what was run, which edge cases) — not "tested locally"; Risk, rollout, and rollback are addressed (even if "low risk, none").

🔵 Stable🕐 updated 2026-10-06 🔷 SkillSpec L3 pm-craft

Write a clear pull-request description that gets reviewed fast and merged with confidence, from a git diff, branch summary, or commit list. Use when opening a PR, summarizing a change for review, documenting code changes, or asked to write a PR/merge-request description. Produces a structured PR: what changed and why, how it was tested, risk and rollout, and a focused reviewer guide — so the reviewer understands intent before reading a single diff line.

▶ Run it free — no key needed 📝 Grade your existing draft ⬇ Add to Claude (works in Duet) 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“Open a PR.”“Summarize a change for review.”“Document code changes.”“Write a PR/merge-request description.”

What to give it

▸The change — what was done (the diff summary, commits, or a description).

▸The why — the problem/issue it solves (link the ticket).

▸Testing — how it was verified (tests added, manual steps, edge cases checked).

▸Risk & rollout — blast radius, migrations, flags, backward compatibility, how to roll back.

✅ 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.

✓Title is concise and imperative; the why and linked issue are clear up front

✓Changes summarize intent, not a file-by-file dump

✓Testing is specific (what was run, which edge cases) — not "tested locally"

✓Risk, rollout, and rollback are addressed (even if "low risk, none")

✓A reviewer guide points to where to focus and flags anything uncertain

✓Length is proportional to the size of the change

⚠️ What it refuses to do

Do not just paste the commit list — explain intent the diff can't convey

Do not say "tested" without saying how — give the reviewer something to trust

Do not hide risk or migrations — surface them so they're reviewed deliberately

Do not write a novel for a one-line change — match effort to size

Do not omit the "what to focus on" — undirected review is slow review

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

💬 Discussion

PR Description is one of 1326 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog