Review a pull request, a proposed code change, for correctness, security, design, and test coverage. Check its explanation and existing feedback, then post findings on relevant code lines with severity labels.
Review a PR for correctness, security, code quality, and testing issues. TRIGGER when user asks to review a PR, check PR quality, or give feedback on a PR.
Run score Not tested
See how to installThis skill reviews a pull request, a proposal to change code, for correctness, security, code quality, design, and testing issues. It starts with the description to understand why the change is needed, what it changes, and how it works. It then examines the code diff and retrieves existing review comments. Findings receive severity labels and are posted on the relevant code lines, while avoiding points already raised in earlier comments.
Use it to check changes before merging or to make review criteria consistent. It examines edge cases, asynchronous processing, input validation, secrets appearing in logs, and missing tests. It also provides feedback when the description does not explain the reason, content, or approach behind the change.
The procedure uses GitHub CLI’s gh to post review comments on GitHub. Supply a PR number or URL; otherwise, it looks for the current branch’s PR. Some references and conventions are specific to one repository and need adjustment for other projects.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 23, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
gh pr list --head $(git branch --show-current) --repo Significant-Gravitas/AutoGPT
gh pr view {N}
Before reading code, understand the why, what, and how from the PR description:
gh pr view {N} --json body --jq '.body'
Every PR should have a Why / What / How structure. If any of these are missing, note it as feedback.
gh pr diff {N}
Before posting anything, fetch existing inline comments to avoid duplicates:
gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments --paginate
gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews
Description quality: Does the PR description cover Why (motivation/problem), What (summary of changes), and How (approach/implementation details)? If any are missing, request them — you can't judge the approach without understanding the problem and intent.
Correctness: logic errors, off-by-one, missing edge cases, race conditions (TOCTOU in file access, credit charging), error handling gaps, async correctness (missing await, unclosed resources).
Security: input validation at boundaries, no injection (command, XSS, SQL), secrets not logged, file paths sanitized (os.path.basename() in error messages).
Code quality: apply rules from backend/frontend CLAUDE.md files and root AGENTS.md, including its "User-facing copy" section (text a person reads says workflow, never agent or graph).
Architecture: DRY, single responsibility, modular functions. Security() vs Depends() for FastAPI auth. data: for SSE events, : comment for heartbeats. transaction=True for Redis pipelines.
Testing: edge cases covered, colocated *_test.py (backend) / __tests__/ (frontend), mocks target where symbol is used not defined, AsyncMock for async.
Every comment must be prefixed with 🤖 and a criticality badge:
| Tier | Badge | Meaning |
|---|---|---|
| Blocker | 🔴 **Blocker** | Must fix before merge |
| Should Fix | 🟠 **Should Fix** | Important improvement |
| Nice to Have | 🟡 **Nice to Have** | Minor suggestion |
| Nit | 🔵 **Nit** | Style / wording |
Example: 🤖 🔴 **Blocker**: Missing error handling for X — suggest wrapping in try/except.
For each finding, post an inline comment on the PR (do not just write a local report):
# Get the latest commit SHA for the PR
COMMIT_SHA=$(gh api repos/Significant-Gravitas/AutoGPT/pulls/{N} --jq '.head.sha')
# Post an inline comment on a specific file/line
gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments \
-f body="🤖 🔴 **Blocker**: <description>" \
-f commit_id="$COMMIT_SHA" \
-f path="<file path>" \
-F line=<line number>
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create a pull request that follows the project's template and title conventions. Check existing behavior and test coverage, document testing limits, and coordinate self-review or bot review with follow-up on reported issues.
Coordinate multiple Claude Code agents in separate Git worktrees and tmux windows. Assign tasks, inspect progress, help stalled agents resume, and verify PR checks and review feedback before treating work as complete.
Compare performance across releases, environments, or time windows using Sentry data. Report request counts, latency percentiles, and failure rates, with statistical checks that distinguish faster or slower behavior from noise and flag insufficient data.
Work through PR review feedback by fixing code, pushing commits, replying to reviewers, and resolving addressed threads. Monitor automated checks, merge conflicts, and new comments until checks pass and the review work is complete.
Prepare a pull request for merging by repeatedly reviewing changes and addressing feedback. Verify resolved discussions, passing automated checks, and mergeability, then check twice for late comments after the checks finish.
Test a PR or branch through a running application using browser actions and API calls. Compare expected behavior with actual state changes, include failure cases, and post a report with before-and-after screenshots to the PR.