PR Review
Review a GitHub PR and post its CRITICAL findings as line-anchored inline comments with suggestion blocks after you confirm; INFORMATIONAL findings stay in chat. Adds a second pass from the other harness when the diff needs one, reuses CI results, and reviews only new commits on a re-run. Invoke only when the user explicitly asks for /pr-review or for a PR review that posts comments, or when bork:do runs a review batch; never on your own. For a local diff or branch without posting, use review.
Install
/plugin marketplace add borkweb/skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add borkweb/skills --skill pr-reviewgit clone --depth 1 https://github.com/borkweb/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/core/pr-review ~/.claude/skills/pr-reviewPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# PR Review (comment-first) You are running `/pr-review`, a **superset of `bork:review`**: same analysis, different disposition. `bork:review` reports findings and fixes them only when authorized. This skill puts the findings *on the PR* as comments with applyable suggestion blocks, where the author sees them, and asks up front whether to authorize local mechanical fixes. When the diff needs one, the other harness runs an independent second pass over the same tree. Neither pass sees the other's findings until they're merged. This file covers the common path. Some cases have their own file in `references/`. Each step says when to read one. Read it then, not before. | File | Read it when | |---|---| | [auto-fix.md](references/auto-fix.md) | Step 1 records AUTO-FIX | | [codex-host.md](references/codex-host.md) | Step 0 finds you are not in Claude Code | | [incremental.md](references/incremental.md) | Step 0 finds an earlier `/pr-review` review | | [peer.md](references/peer.md) | Step 2b records the peer as REQUIRED | | [checks.md](references/checks.md) | Step 3a maps the checks to CI (every run), Step 3c waits on a pending check, a CI check failed, or a check has to run on this machine | | [edge-cases.md](references/edge-cases.md) | No PR, wrong repo, fork PR, peer failure, a 422 | | [batch.md](references/batch.md) | Step 0 finds `--prepare-only` (a `bork:do` batch lane) |
Details
- Skill name
pr-review- Repository
- borkweb/skills
- Path
skills/core/pr-review/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the PR Review skill do?
Review a GitHub PR and post its CRITICAL findings as line-anchored inline comments with suggestion blocks after you confirm; INFORMATIONAL findings stay in chat. Adds a second pass from the other harness when the diff needs one, reuses CI results, and reviews only new commits on a re-run. Invoke only when the user explicitly asks for /pr-review or for a PR review that posts comments, or when bork:do runs a review batch; never on your own. For a local diff or branch without posting, use review.
How do I install the PR Review skill?
Claude Code plugin: /plugin marketplace add borkweb/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is PR Review popular?
It lives in borkweb/skills, which has 9 GitHub stars and 0 forks.
Related skills
Prototype
9borkweb/skills
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
Agents Md Lint
9borkweb/skills
Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files.
Auto Scope
9borkweb/skills
Scopes a coding task before implementation — names the handful of files actually relevant (read/edit these), the areas to leave alone, and any open scope questions, so work doesn't start by reading the whole repo. Fires proactively at the start of substantive, multi-file, or unfamiliar-area work; stays silent on single-file edits, one-line fixes, questions, and continued work in an area already scoped this session. Use when beginning a feature, bug fix, or refactor that could plausibly touch several files or an area not yet seen this session.
Review
9borkweb/skills
Pre-landing review of a local diff, branch or PR for concrete defects, scope gaps and landing readiness, ending in SAFE TO LAND, LAND WITH CAUTION or DO NOT LAND. Use for 'review this', 'review my branch', 'is this safe to land' or 'check this diff'. To post comments on a GitHub PR use pr-review; for a security audit use review-security.
Cmd PR Scope Sweep
9Olshansk/agent-skills
Final pass to identify missed items, edge cases, and risks before considering a scope done
App Store Changelog
9huytran1120/vietnam-agentic-skills
Generate user-facing App Store release notes from git history since the last tag.
Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.