PierceS1/PS1 / .claude/skills/code-review
code-review
UnverifiedUse this skill for code review and PR review tasks. Covers review methodology, what to flag, what to skip, and output structure.
Code Review
Review a GitHub pull request for substantive issues. Focus on what matters, skip what doesn't.
Steps
- Run
gh pr view {pr_number} --json title,body,filesto understand the PR's purpose and scope. - Run
gh pr diff {pr_number}to read the full diff. - Before commenting, read surrounding code to understand full context — a pattern that looks wrong in isolation may be an established convention.
Focus Areas (priority order)
- Correctness — Logic bugs, edge cases, error handling
- Security — Input validation, injection risks, secrets exposure
- Reliability — Race conditions, failure modes, resource leaks
- Performance — Inefficient algorithms, N+1 queries, unnecessary work
- Breaking changes — API/behavior changes affecting callers
- Test coverage — Are new code paths tested?
Skip style/formatting unless it materially impacts readability. Do not nitpick naming, style preferences, or issues linters catch.
Severity Levels
- Blocking: Must fix before merge (bugs, security, significant reliability/performance issues, breaking changes)
- Non-blocking: Suggestions for improvement (optional)
Output Format
Findings
For each issue found:
[Issue Title]
- Severity: blocking | non-blocking
- Location:
file_path:line_number - Description: What the issue is and why it matters
- Suggested Fix: Concrete code change or approach
If no issues found, state that the changes look correct and explain why.
Summary
Overall assessment: is the PR ready to merge, or does it need changes? List the most important issues if any.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |