メニュー
Review a pull request or diff with a structured checklist — security, error handling, edge cases, test coverage, and code quality. Trigger on /code-review, or when asked to review a PR, diff, or merge request.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Control shell, filesystem, MCP, browser, external APIs, and risky tools. Enforce read-only-before-write, least-privilege, and verification discipline. Trigger on /agent-tool-safety, or when using shell commands, file operations, MCP tools, browser automation, or external APIs.
Final sanity check on AI-generated code before merging. Run the checklist to catch common failure modes. Trigger on /ai-coding-agent-review, or before finalizing any significant AI-generated change.
Review API design — endpoints, types, contracts, error handling, versioning, and consistency. Trigger on /api-design, or when designing or reviewing API specifications.
Implement backend API endpoints — routing, middleware, input validation, error handling, authentication, rate limiting, file upload. Trigger on /api-implementation, or when building endpoints, adding middleware, handling file uploads, or implementing API security.
Record architecture decisions as ADRs — compare options, document trade-offs, and track rationale. Trigger on /architecture-decision, or when choosing libraries, designing modules, splitting systems, or making significant technical decisions.
Make the agent continue work without asking unnecessary questions. Enforce the ask-less policy from CLAUDE.md. Trigger on /ask-less-execution, or when the agent is asking too many clarifying questions instead of discovering answers.
| name | code-review |
| description | Review a pull request or diff with a structured checklist — security, error handling, edge cases, test coverage, and code quality. Trigger on /code-review, or when asked to review a PR, diff, or merge request. |
| user-invocable | true |
| allowed-tools | Read, Grep, Glob, Bash |
Review a PR/diff with outsider skepticism. Focus on what matters — not style nits.
Correctness
Security
Code quality
console.log, print, TODO, FIXME, HACK)?catch { /* silent */ })?Testing
Side effects
Order by severity: blocker → major → nit.
## Findings
### Blocker
- ...
### Major
- ...
### Nits
- ...
## Verdict: ship / fix-then-ship / rework / reject
This skill learns from experience. Mechanism:
.claude/experience/code-review.md at skill start to benefit from past lessons..claude/experience/code-review.md after use if you learned something new.YYYY-MM-DD: <lesson> — one line per entry.