skills/github-review-pr/SKILL.md
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Also trigger when the user wants feedback on code changes, wants to approve or request changes on a PR, or asks to review someone's contribution.
npx skillsauth add feiskyer/claude-code-settings github-review-prInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
A structured, multi-agent workflow for thorough code reviews on GitHub PRs. The approach uses parallel specialized reviewers, confidence scoring, and false positive filtering to produce high-signal, actionable feedback.
Use gh for all GitHub interactions. Do not use web fetch or attempt to build/typecheck the app — CI handles that separately.
Use a subagent to verify the PR is eligible for review. Skip the review if any of these are true:
If no PR number is provided, run gh pr list to show open PRs and ask which one to review.
Launch two subagents in parallel:
Subagent A — Project guidance discovery: Find all relevant CLAUDE.md and AGENTS.md files — check the repo root and any directories whose files the PR modified. Return a list of file paths (not contents).
Subagent B — PR summary: View the PR with gh pr view and gh pr diff, then return a concise summary of what changed.
Launch 5 parallel subagents, each reviewing the PR from a different angle. Each agent should return a list of issues found, with a reason tag for why it was flagged (e.g., "CLAUDE.md adherence", "bug", "historical git context", "past PR feedback", "code comment violation").
| Agent | Focus | Approach |
|-------|-------|----------|
| #1 CLAUDE.md / AGENTS.md compliance | Check changes against project guidance | Read the CLAUDE.md and AGENTS.md files from step 2. Note that these files are guidance for AI agents as they write code, so not all instructions apply during code review. |
| #2 Shallow bug scan | Obvious bugs in the diff | Read only the changed lines (avoid extra context beyond the diff). Focus on significant bugs, not nitpicks. Ignore likely false positives. |
| #3 Git history context | Bugs visible through historical context | Read git blame and history of modified code. Identify issues that become apparent in light of how the code evolved. |
| #4 Past PR feedback | Recurring issues | Find previous PRs that touched these files. Check their comments for feedback that may also apply here. |
| #5 Code comment compliance | Respect inline guidance | Read code comments in modified files. Verify the PR changes comply with any guidance expressed in those comments. |
For each issue found in step 3, launch a parallel subagent that receives the PR context, the issue description, and the CLAUDE.md/AGENTS.md file list. The subagent scores the issue on a 0-100 confidence scale:
| Score | Meaning | |-------|---------| | 0 | False positive that doesn't stand up to light scrutiny, or a pre-existing issue. | | 25 | Might be real, but could be a false positive. Couldn't verify. If stylistic, not explicitly called out in CLAUDE.md or AGENTS.md. | | 50 | Verified as real, but may be a nitpick or unlikely to hit in practice. Not very important relative to the rest of the PR. | | 75 | Double-checked and very likely real. Will be hit in practice. The existing approach is insufficient. Important for functionality, or directly mentioned in CLAUDE.md/AGENTS.md. | | 100 | Definitely real and confirmed. Will happen frequently. Evidence directly confirms the issue. |
For issues flagged due to CLAUDE.md/AGENTS.md instructions, the scoring agent should double-check that the relevant file actually calls out that issue specifically.
Discard any issues scoring below 80. If no issues meet this threshold, skip to posting the "no issues found" comment.
Before posting, use a subagent to repeat the eligibility check from step 1. PRs can be closed or updated while the review runs.
Use gh to comment on the PR with findings. Follow these rules:
$(git rev-parse HEAD) — the comment renders as Markdown)### Code review
Found 3 issues:
1. <brief description> (CLAUDE.md says "<quote>")
https://github.com/OWNER/REPO/blob/FULL_SHA/path/to/file.ts#L12-L16
2. <brief description> (AGENTS.md says "<quote>")
https://github.com/OWNER/REPO/blob/FULL_SHA/path/to/file.ts#L30-L35
3. <brief description> (bug due to <file and code snippet>)
https://github.com/OWNER/REPO/blob/FULL_SHA/path/to/file.ts#L50-L55
<sub>- If this code review was useful, please react with a thumbs up. Otherwise, react with a thumbs down.</sub>
### Code review
No issues found. Checked for bugs, CLAUDE.md, and AGENTS.md compliance.
Links must follow this exact format for Markdown rendering to work:
https://github.com/OWNER/REPO/blob/FULL_SHA/path/to/file.ext#L[start]-L[end]
# after the file nameL[start]-L[end]L4-L7)These should be filtered out during steps 3-5. Share this context with the review and scoring agents:
# List open PRs
gh pr list
# View PR description and metadata
gh pr view 78
# View PR code changes
gh pr diff 78
# Get repo owner/name
gh repo view --json nameWithOwner --jq '.nameWithOwner'
# Get PR head commit SHA (full 40-char)
gh api repos/OWNER/REPO/pulls/78 --jq '.head.sha'
# Post a comment on the PR
gh pr comment 78 --body "### Code review ..."
# Post inline review comment on a specific file/line
gh api repos/OWNER/REPO/pulls/78/comments \
--method POST \
--field body="[your-comment]" \
--field commit_id="[full-sha]" \
--field path="path/to/file" \
--field line=42 \
--field side="RIGHT"
development
Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Triggers: "gpt image", "openai image", "generate image with openai", "draw image", "create image", "image generation", "AI drawing", "图片生成", "AI绘图", "生成图片", "画图". Use this skill whenever the user wants to generate or edit images and mentions OpenAI, GPT, or when OPENAI_API_KEY is available.
development
Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.
development
Generate or edit images using Google Gemini API via nanobanana. Triggers: "nanobanana", "generate image", "create image", "edit image", "AI drawing", "图片生成", "AI绘图", "图片编辑", "生成图片".
development
Execute long-running, multi-session tasks autonomously using Claude Code headless mode or in-session hook-based loops. Supports structured task decomposition (for complex projects) and lightweight Ralph-style iteration (for TDD, bug fixing, refactoring). Use this skill whenever the user says "autonomous", "long-running task", "multi-session", "run this in the background", "keep working on this", "batch process", "iterate until done", "ralph loop", or wants any task that requires sustained, unattended execution.