Reviews a pull request with independent parallel reviewers, verifies every finding, fixes the valid in-scope ones, and has an independent reviewer re-check the result. Use when invoked explicitly on a PR.
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
# review-pr
Autonomously review this PR, verify every finding, fix valid in-scope issues, and independently re-review the result.
The task is the text given with this invocation.
---
## Establish the review target
Resolve the PR, base, head, merge base, description, applicable instructions, full diff, changed files, and relevant tests. Review the exact current head SHA. Record staged, unstaged, and untracked user work; never overwrite, stash, reset, stage, commit, or push unrelated changes.
Invoking this skill authorizes local review-and-fix work without asking after each finding. It does not authorize merge, release, deployment, destructive actions, or behavior/product decisions outside the PR's intent.
## Adaptive independent review
Scale to the diff:
- trivial: direct review or 1 specialist;
- modest: 2-3 reviewers;
- normal: 4-7 reviewers;
- broad, cross-system, or high-risk: 8-12+ reviewers.
Orthogonality and independence matter more than reaching a count. Launch independent reviewers concurrently in one dispatch and never permit nested agents. Give each reviewer the exact head SHA, diff, relevant context, and a non-overlapping lens.
…
The line at the top of this page pins the label git:20260929.bdaf144, 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_jpvuldmpvi3gnsee
GET https://markdownregistry.com/api/v1/resolve?ref=geiserx/agent-skills/review-pr
GET https://markdownregistry.com/api/v1/blob/025bb14b1f8a06cd6569a5b386a72a8d493e4fb3f8887807356e56cd6f776686
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.
geiserx/agent-skills · codex/skills/docs-loop/SKILL.md · Audits repository documentation against current default-branch evidence, reports stale claims, and optionally applies…
geiserx/agent-skills · codex/skills/eli5/SKILL.md · Explain work, a system or a situation to Sergio in plain words with real names, so he understands it on one read. Use…
geiserx/agent-skills · codex/skills/file-pr/SKILL.md · Open a pull request whose title says why the change matters and whose body opens with the problem in the requester's…
geiserx/agent-skills · codex/skills/grow-my-repo/SKILL.md · Plan and carry out where an open-source repository gets listed so people find it, from GitHub itself to registries…
geiserx/agent-skills · codex/skills/help-decide/SKILL.md · Lay a decision out for Sergio so one word answers it, recommendation and pros and cons first, then how the thing works…
geiserx/agent-skills · codex/skills/implement/SKILL.md · Implements a requested change with the smallest complete diff, splitting genuinely independent work across parallel…
geiserx/agent-skills · codex/skills/investigate/SKILL.md · Investigates a bug or unexpected behavior from reproduction to root cause with a panel of independent hypothesis…
geiserx/agent-skills · codex/skills/kb-research/SKILL.md · Answers a question from the team's own record (chat archives, call transcripts, tickets, wiki pages, notes, any mix)…
geiserx/agent-skills · codex/skills/kb-review/SKILL.md · Reviews a pull request the way the team's reviewers do, grounded in reviewer learnings and past decisions captured in…
geiserx/agent-skills · codex/skills/refine-loop/SKILL.md · Runs a safe, resumable refinement loop over a working repository. It discovers behavior-preserving improvements through…
trailofbits/skills · plugins/code-improver/tests/fixtures/pr-review-toolkit/skills/review-pr/SKILL.md · Reviews the current branch's changes against its base branch as a pull request: correctness of new and modified code…
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…
