Reviews the current branch's changes against its base branch as a pull request: correctness of new and modified code, test coverage for it, and documentation accuracy. Use when asked to review a branch, a diff, or a pull request.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# PR Review
Review the branch's change surface, not the whole repository.
1. Establish the diff: `git diff <base>...HEAD` (and `git diff <base>` when the working
tree carries uncommitted changes that belong to the branch). The base branch is named
by the caller; fall back to `main`.
2. Review every changed hunk for correctness: wrong results on edge inputs, unhandled
error paths, and behavior that contradicts the function's name or callers.
3. Check test coverage for the changed behavior: new logic without a test exercising its
edge cases is a finding.
4. Check documentation the diff made stale: statements in README or docs that were true
on the base branch and are false after the change.
5. Report every defect found, each with a severity; include minor and informational
findings. Do not report defects in files the branch did not touch — they are outside
the pull request.
The line at the top of this page pins the label git:20260824.1004934, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_6lb6gl2jojziqpqk
GET https://markdownregistry.com/api/v1/resolve?ref=trailofbits/skills/review-pr
GET https://markdownregistry.com/api/v1/blob/133b4e5a107b41260d4f7e4b91311a3758fb49d2089abbb7b8028f0b01e6495e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
trailofbits/skills · plugins/agentic-actions-auditor/skills/agentic-actions-auditor/SKILL.md · Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action…
trailofbits/skills · plugins/audit-context-building/skills/audit-context-building/SKILL.md · Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it…
trailofbits/skills · plugins/building-secure-contracts/skills/guidelines-advisor/SKILL.md · Smart contract development advisor based on Trail of Bits' best practices. Analyzes codebase to generate…
trailofbits/skills · plugins/building-secure-contracts/skills/secure-workflow-guide/SKILL.md · Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features…
openonion/connectonion · connectonion/useful_skills/review-pr/SKILL.md · Review GitHub pull requests. Use when user says "review PR", "review pull request", or "/review-pr".
fcakyon/claude-codex-settings · plugins/github-dev/skills/review-pr/SKILL.md · This skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this…
amd-agi/hyperloom · .claude/skills/review-pr/SKILL.md · Review a Hyperloom pull request. Invoke with a PR number whenever asked to review, re-review, or sanity-check a PR in…
thinkflowlab/system1-agents · .claude/skills/review-pr/SKILL.md · Review pull requests for system1-agents with high-confidence, evidence-based feedback. Use when the user asks to review…
lploc94/cross-review · skill-packs/cross-review/skills/review-pr/SKILL.md · Review someone else's pull request or branch with an external reviewer model (Codex CLI by default; Claude Code or…
