菜单
Review current branch changes against a target branch. Use when the user asks to review a branch, review changed files, compare current work to main, origin HEAD, or master, or run a file-by-file code review with aggregated markdown results.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when executing implementation plans with independent tasks in the current session
Use when you have a spec or requirements for a multi-step task, before touching code
Fast, MVP-focused grilling session for plans, prototypes, designs, or feature ideas. Use when the user wants to stress-test direction, clarify assumptions, reduce scope, or get challenged without a long decision-tree interview.
Execute and orchestrate multiple AI agent CLIs (agy, Codex, Cursor, Claude Code, Pi) for getting alternative opinions, comparing approaches, or leveraging different AI models' strengths. Use when the user explicitly mentions agent names like "ask agy", "ask cursor", "ask codex", "ask pi", "use composer", "use pi", "try grok", or when needing diverse perspectives on complex problems, alternative implementation approaches, or multi-agent collaboration.
Summarize a video (URL or local path) by pulling captions first, falling back to audio-only transcription, and optionally extracting frames for visual summaries. Use when the user pastes a YouTube/Vimeo/X/etc URL, points at a local video file, or asks to summarize, watch, or extract takeaways from a video. Triggers on "summarize this video", "what's in this video", "watch this", URLs ending in /watch, /shorts, common video extensions (.mp4/.mov/.mkv/.webm).
| name | review-branch |
| description | Review current branch changes against a target branch. Use when the user asks to review a branch, review changed files, compare current work to main, origin HEAD, or master, or run a file-by-file code review with aggregated markdown results. |
Act as orchestrator.
Delegate actual code review to code-reviewer subagents when available.
If named subagents are unavailable, use the generic subagent mechanism and pass the code-reviewer constraints from local agent definitions when present.
origin/HEADUse three repo-root files:
| File | Purpose |
|---|---|
review_context.md | Shared context for subagents |
review_files.md | Todo list of files to review |
review_result.md | Aggregated review results |
If review_files.md exists with unchecked items, continue from it.
Otherwise ask whether to start fresh.
Before launching subagents, create review_context.md with:
Exclude images, lock files, binary files, and generated files.
Tell each subagent:
Review context available at: review_context.md
Format review_files.md exactly:
- [ ] relative/path/to/file1.ext
- [ ] relative/path/to/file2.ext
No extra content.
Format review_result.md:
# Code Review [date] [time] [branch name]review_result.md immediatelyFilter out: