Check GitHub pull request review comments against the actual code. Classify findings as valid, invalid, or partially valid, identify similar issues elsewhere, and produce recommended actions, with optional replies after user approval.
Analyze PR review comments from a GitHub PR URL. Fetch review comments, verify each finding against the actual codebase, assess validity (correct/incorrect/partial), present a structured summary with recommended actions, and optionally reply to each comment on GitHub. Use when given a PR review URL or when asked to check/analyze PR feedback.
Review the instructions the agent will receive before you install.
GitHub PR のレビューコメントを取得・分析し、各指摘の妥当性を検証してレポートを出力する。
gh api を使ってレビューコメントを取得する:
gh api repos/{owner}/{repo}/pulls/{number}/reviews
gh api repos/{owner}/{repo}/pulls/{number}/comments
各レビューコメントについて:
指摘が参照するパターン（バグ、アンチパターン等）が他のファイルにも存在するか Grep ツールで確認する。 同一パターンが複数箇所にある場合、それらも報告に含める。
以下の形式でまとめを出力する:
## PR Review Analysis: #{PR番号}
### Summary
- Total comments: {件数}
- Valid: {件数} | Partial: {件数} | Invalid: {件数}
### Details
| # | File | Severity | Validity | Summary | Action |
|---|------|----------|----------|---------|--------|
| 1 | path/to/file.ts:L42 | Major | ✅ Valid | 説明 | 修正必要 |
| 2 | path/to/file.ts:L100 | Minor | ⚠️ Partial | 説明 | 検討 |
### Detailed Analysis
#### Comment 1: [タイトル]
- **File**: `path/to/file.ts:L42`
- **Reviewer's point**: 指摘内容の要約
- **Verification**: 検証結果の説明
- **Verdict**: ✅ Valid
- **Recommended action**: 具体的な修正方針
- **Same pattern found in**: (該当する場合) 他のファイルパス
...
レポート出力後、修正対応が完了している場合はレビューコメントへの返信を提案する。
gh api で各コメントに返信する:
gh api repos/{owner}/{repo}/pulls/{number}/comments \
-f body='{返信内容}' \
-F in_reply_to={comment_id}
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 and edit visual AI agent workflows in CC Workflow Studio through conversation. Add or remove steps and connections, update individual nodes, and organize related steps into visual groups on the canvas.
Use ccwf to validate workflow JSON files, preview their steps in a browser, and produce Mermaid flowcharts. Export workflows as skill files for supported agents, or generate the files and launch Claude Code to proceed with execution.
Turn previously retrieved Jira requirements and Confluence documents into a structured implementation plan. Tasks are grouped into frontend, backend, and infrastructure work, with architectural reasoning, blocking dependencies, and risks paired with mitigation measures.
Develop user-visible improvements for cc-wf-studio, verify their basis in the code, and assess their value. Record qualifying proposals as locked GitHub issues, creating a queue of concrete ideas for later implementation without changing code.
Advance one queued QA task by adding tests or test tooling, recording the work, and opening a pull request. The skill also manages its in-flight QA requests and merges into auto-qa after CI passes.
Find a valuable gap in test coverage by checking code, existing tests, and QA priorities. The skill creates at most one locked GitHub issue with concrete test cases, ready for later implementation.