pr
An agent skill by mattpocock, from mattpocock/skills. Tags: copywriting, documentation, github, review, workflow.
What it does
Use when writing a PR body.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add mattpocock/skills --skill prOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/mattpocock/skills
cp -r skills/skills/engineering/pr ~/.claude/skills/prSafety box score
Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a plain-text template for drafting PR bodies; it does not run code, touch files, or contact external services. The main consideration is review quality, not machine or account risk, since it only shapes markdown content about the change.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No scripts, shell commands, or code evaluation are present; `SKILL.md` is only markdown guidance and `agents/openai.yaml` is metadata. |
| Network access | 0 (none) | The skill does not download from or send data to any host; there are no URLs used for fetches or API calls. |
| Filesystem reach | 0 (none) | It neither reads nor writes project, home, or system paths; it only tells the agent how to format a PR body. |
| Secrets & credentials | 0 (none) | There is no request for tokens, passwords, `.env` files, keychains, or browser sessions, and no secret-handling behavior. |
| Privilege & persistence | 0 (none) | No sudo, service registration, global installs, or shell/OS setting changes are described anywhere in the shipped files. |
| Instruction hijack surface | 0 (none) | The content does not ask the agent to ignore instructions, hide behavior, or follow remote text; it is static formatting guidance. |
| Irreversible actions | 0 (none) | It does not post, merge, deploy, send messages, or make decisions on the user's behalf; it only drafts a PR body. |
| Transparency | 0 (none) | All shipped files are readable plain text (`SKILL.md`, `CREDITS.md`, `agents/openai.yaml`); there are no binaries, minified blobs, or runtime-decoded content. |
Before installing
- Read `SKILL.md` to confirm it only formats PR body text and does not automate PR creation or posting.
- If you plan to pair it with a PR bot, verify the bot still requires a human review before merge.
- Check whether your team wants the exact template sections (`Summary`, `Evidence`, `Merge Danger`) before adopting it.
Rated 2026-10-16 by an automated review of 3 files from the skill's repository.
Source
- Repository
- mattpocock/skills (all skills from this repository)
- Path
- skills/engineering/pr/SKILL.md
- Branch
- main
- Updated
- 2026-10-05
Related skills
- get-pr-comments — Fetch and summarize review comments from the active pull request
- make-pr-easy-to-review — Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior.
- show-me-your-work — Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).
- code-review — Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes.
- analyzing-release-readiness — Trigger a pre-merge release readiness review on a GitHub PR, GitLab MR, or local branch.
- automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".