Skip to content
Automation
Skill

/review-pr

Review GitHub pull requests with structured code analysis. Use when asked to review a PR, check a pull request, or audit code changes.

From plugin
dorabot
24710 skills

Claude Code

$ npx -y skills add suitedaces/dorabot --skill review-pr --agent claude-code

SKILL.md

review-pr.SKILL.md
name: review-pr
description: "Review GitHub pull requests with structured code analysis. Use when asked to review a PR, check a pull request, or audit code changes."
metadata:
  { "requires": { "bins": ["gh", "jq"] } }

PR Review Skill

Review GitHub pull requests with structured analysis covering correctness, security, performance, and style.

Invocation

Triggered by: `/review-pr <url-or-number>`, "review this PR", "review PR #123", or a GitHub PR URL.

Parse the input:

  • Full URL: `https://github.com/owner/repo/pull/123` -> extract owner, repo, number
  • Number only: `#123` or `123` -> use current repo from `gh repo view --json nameWithOwner -q .nameWithOwner`
  • If ambiguous, ask for the repo.

Step 1: Gather Context

Run these in parallel:

# PR metadata
gh pr view <number> --repo <owner/repo> --json title,body,author,baseRefName,headRefName,createdAt,additions,deletions,changedFiles,labels,reviewRequests,mergeable,state

# Full diff
gh pr diff <number> --repo <owner/repo>

# File list with stats
gh pr view <number> --repo <owner/repo> --json files --jq '.files[] | "\(.additions)+/\(.deletions)- \(.path)"'

# CI status
gh pr checks <number> --repo <owner/repo> 2>/dev/null || echo "No checks"

# Existing review comments (avoid duplicating feedback)
gh api repos/<owner>/<repo>/pulls/<number>/comments --jq '.[] | "[\(.path):\(.line // .original_line)] @\(.user.login): \(.body)"' 2>/dev/null | head -50

Step 2: Analyze the Diff

Read the full diff carefully. For each file, evaluate:

Correctness

  • Logic errors, off-by-one, null/undefined handling
  • Missing error handling or edge cases
  • Broken contracts (function signatures changed without updating callers)
  • Race conditions or concurrency issues

Security

  • User input flowing to SQL, shell commands, file paths, or HTML without sanitization
  • Hardcoded secrets, API keys, or credentials
  • Overly broad permissions or missing auth checks
  • Unsafe deserialization or eval usage

Performance

  • O(n^2) or worse algorithms where O(n) is possible
  • Unnecessary re-renders in React (missing memo/useMemo/useCallback)
  • N+1 queries or unbounded data fetching
  • Large allocations in hot paths

Architecture

  • Does this change belong in this file/module?
  • Are abstractions appropriate (not too much, not too little)?
  • Does it follow existing patterns in the codebase?
  • Will this be maintainable?

Style

  • Naming clarity
  • Dead code or TODOs left behind
  • Missing types (in TypeScript)
  • Inconsistent formatting (only flag if egregious)

Step 3: Write the Review

Output a structured review in this format:

## PR Review: <title>

**Summary**: 1-3 sentence overview of what this PR does and whether it's ready.

**Verdict**: APPROVE | REQUEST_CHANGES | COMMENT

### Findings

#### <severity-emoji> <category>: <short description>
**File**: `path/to/file.ts` L<line>-L<line>
<explanation of the issue and why it matters>

**Suggested fix**:
\`\`\`diff
- old code
+ new code
\`\`\`

---
(repeat for each finding)

Severity emojis:

  • `[blocker]` - Must fix before merge. Bugs, security issues, data loss risks.
  • `[warning]` - Should fix. Performance problems, poor patterns, missing edge cases.
  • `[nit]` - Optional. Style, naming, minor improvements.
  • `[praise]` - Good stuff. Call out well-written code (do this at least once).

Guidelines

  • Be specific. Quote the code, give line numbers, explain why.
  • Suggest fixes, not just problems. Include diff snippets.
  • Don't nitpick formatting if there's a formatter configured.
  • If the PR is large (>500 lines), focus on the riskiest files first.
  • If the PR description explains a deliberate tradeoff, don't re-litigate it.
  • Check the test coverage: are new code paths tested? Are edge cases covered?

Step 4: Post the Review (Optional)

Only post to GitHub if the user explicitly asks. Use:

# Post a review comment (not individual line comments)
gh pr review <number> --repo <owner/repo> --comment --body "<review body>"

# Or approve/request changes
gh pr review <number> --repo <owner/repo> --approve --body "<review body>"
gh pr review <number> --repo <owner/repo> --request-changes --body "<review body>"

For inline comments on specific lines:

gh api repos/<owner>/<repo>/pulls/<number>/comments \
  -f body="<comment>" \
  -f path="<file>" \
  -f commit_id="$(gh pr view <number> --repo <owner/repo> --json headRefOid -q .headRefOid)" \
  -F line=<line_number> \
  -f side="RIGHT"

Always show the review to the user first and get confirmation before posting to GitHub.

Quick Mode

For small PRs (<100 lines changed), skip the full structure. Give a concise paragraph covering the key points and verdict.

Batch Review

When reviewing multiple PRs (e.g., "review all open PRs"):

gh pr list --repo <owner/repo> --json number,title,author,additions,deletions --jq '.[] | "#\(.number) \(.title) by @\(.author.login) (+\(.additions)/-\(.deletions))"'

Triage by size and risk, review the largest/riskiest first.

Read more
@suitedaces
Ships withdorabot

A 24/7 self-learning AI agent with an integrated IDE workspace that runs itself. Works with your existing Claude Code or OpenAI Codex subscription. No extra API key needed.

Stars on GitHub

Momentum

stars in total
247
Star history of suitedaces/dorabot on GitHub, a chart by star-history.com

Other skills on dorabot.

agent-swarm-orchestation

agent-swarm-orchestati…

Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running…

@suitedaces@suitedacesInstall Skill
github

github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced…

@suitedaces@suitedacesInstall Skill
himalaya

himalaya

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the…

@suitedaces@suitedacesInstall Skill
macos

macos

Control macOS via AppleScript/osascript. Manage windows (move, resize, tile), apps (launch, quit, focus), system (volume, dark…

@suitedaces@suitedacesInstall Skill
meme

meme

Generate memes using the free memegen.link API. Create image memes from 200+ templates with custom top/bottom text, or use…

@suitedaces@suitedacesInstall Skill
nano-banana

nano-banana

Generate and edit images using the Gemini API. Text-to-image, image editing, multi-turn iteration, 4K resolution, search…

@suitedaces@suitedacesInstall Skill

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, and…

n8n10d209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…

@browser-use@browser-useInstall Skill
agent-browser

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…

@vercel-labs-2@vercel-labs-2Install Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when…

@nanocoai@nanocoaiInstall Skill

Questions about review-pr.

Which coding agents can use review-pr?
review-pr installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.