菜单
Submit code review requests to multiple AI providers (GitHub Copilot, Anthropic Claude, OpenAI Codex, Google Gemini) and get patches back. Use when user says "code review", "review this code", "get a patch for", or needs AI-generated unified diffs for code fixes.
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
File-based inter-agent messaging. Check inbox, send bugs/requests to other projects, acknowledge resolved issues. Use for cross-project agent communication.
Search arXiv for academic papers. Use when user says "find papers on", "search arxiv", "look up research", "academic papers about", "what papers exist on", "use your arxiv tool", or asks about scientific/ML research topics.
Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", or "evaluate what's working". Offer to run after major changes (don't auto-run).
Free web and local search via Brave Search API. Use when user says "brave search", "search with brave", "brave web search", "brave local search", "local search", "find businesses near", or "near me".
Fetch up-to-date library documentation from Context7 API. Use when user asks "how do I use this library", "show me docs for", "library documentation", "API reference for", or needs current documentation for any code library.
Distill PDF, URL, or text into Q&A pairs stored in memory. Use --context for domain-focused extraction.
| name | code-review |
| description | Submit code review requests to multiple AI providers (GitHub Copilot, Anthropic Claude, OpenAI Codex, Google Gemini) and get patches back. Use when user says "code review", "review this code", "get a patch for", or needs AI-generated unified diffs for code fixes. |
| allowed-tools | Bash, Read |
| triggers | ["code review","review this code","get a patch","copilot review","generate diff","review request","full review"] |
| metadata | {"short-description":"Multi-provider AI code review CLI"} |
Submit structured code review requests to multiple AI providers and get unified diffs back.
| Provider | CLI | Default Model | Notes |
|---|---|---|---|
github | copilot | gpt-5 | GitHub Copilot (default) |
anthropic | claude | sonnet | Claude CLI |
openai | codex | gpt-5.2-codex | OpenAI Codex (high reasoning default) |
google | gemini | gemini-2.5-flash | Gemini CLI |
# Check provider CLI availability
python .agents/skills/code-review/code_review.py check
python .agents/skills/code-review/code_review.py check --provider anthropic
python .agents/skills/code-review/code_review.py check --provider openai
python .agents/skills/code-review/code_review.py check --provider google
# Single-step review (default: github/copilot)
python .agents/skills/code-review/code_review.py review --file request.md
# Use different provider
python .agents/skills/code-review/code_review.py review --file request.md --provider anthropic
# OpenAI with high reasoning
python .agents/skills/code-review/code_review.py review --file request.md --provider openai --reasoning high
# Include uncommitted local files via workspace
python .agents/skills/code-review/code_review.py review --file request.md --workspace ./src --workspace ./tests
# Full 3-step pipeline (generate -> judge -> finalize)
python .agents/skills/code-review/code_review.py review-full --file request.md
Verify provider CLI and authentication.
| Option | Short | Description |
|---|---|---|
--provider | -P | Provider to check (default: github) |
Submit a single code review request.
| Option | Short | Description |
|---|---|---|
--file | -f | Markdown request file (required) |
--provider | -P | Provider: github, anthropic, openai, google |
--model | -m | Model (provider-specific, uses default if not set) |
--add-dir | -d | Add directory for file access |
--workspace | -w | Copy local paths to temp workspace (for uncommitted files) |
--reasoning | -R | Reasoning effort: low, medium, high (openai only) |
--raw | Output raw response without JSON | |
--extract-diff | Extract only the diff block |
Run iterative code review pipeline.
Pipeline (per round):
| Option | Short | Description |
|---|---|---|
--file | -f | Markdown request file (required) |
--provider | -P | Provider: github, anthropic, openai, google |
--model | -m | Model for all steps |
--add-dir | -d | Add directory for file access |
--workspace | -w | Copy local paths to temp workspace |
--reasoning | -R | Reasoning effort: low, medium, high (openai only) |
--rounds | -r | Iteration rounds (default: 2) |
--save-intermediate | -s | Save step outputs |
--output-dir | -o | Directory for output files |
# Full pipeline with intermediate files saved
python .agents/skills/code-review/code_review.py review-full \
--file request.md \
--save-intermediate \
--output-dir ./reviews
# Creates: round1_step1.md, round1_step2.md, round1_final.md, round1.patch
Build a request markdown file from options.
| Option | Short | Description |
|---|---|---|
--title | -t | Title describing the fix (required) |
--repo | -r | Repository owner/repo (required) |
--branch | -b | Branch name (required) |
--path | -p | Paths of interest (repeatable) |
--summary | -s | Problem summary |
--objective | -o | Objectives (repeatable) |
--acceptance | -a | Acceptance criteria (repeatable) |
--touch | Known touch points (repeatable) | |
--output | Write to file instead of stdout |
Bundle request for copy/paste into GitHub Copilot web.
IMPORTANT: Copilot web can only see committed & pushed changes!
| Option | Short | Description |
|---|---|---|
--file | -f | Markdown request file (required) |
--repo-dir | -d | Repository directory (for git status check) |
--output | -o | Output file (default: stdout) |
--clipboard | -c | Copy to clipboard (xclip/pbcopy) |
--skip-git-check | Skip git status verification |
List available models for a provider.
| Option | Short | Description |
|---|---|---|
--provider | -P | Provider to list models for |
Print the example review request template.
Search for review request markdown files.
The --workspace flag copies local files to a temporary directory that providers can access.
This is useful when you have uncommitted changes that aren't visible to remote-based providers.
# Copy src/ and tests/ to temp workspace
python .agents/skills/code-review/code_review.py review \
--file request.md \
--workspace ./src \
--workspace ./tests
The workspace is automatically cleaned up after the review completes.
github)gh CLI authenticated--continue for session continuityanthropic)claude CLI--continue for session continuityopenai)codex CLI--continue (session context lost between rounds)google)gemini CLI--continue (use /chat save/resume in interactive mode)The intended workflow is for the project agent (Claude) to interpret and apply suggestions:
User asks for code review
|
Project agent creates review request (follows template)
|
review/review-full sends to provider CLI
|
Project agent parses output, decides what to apply
|
Project agent uses Edit tool to apply changes it concurs with
|
If unclear, agent asks provider (another round) or the user
Why this approach:
git apply)pip install typer rich