菜单
Comprehensive code review with multi-agent analysis. Use when: "review", "code review", "check my code", "review PR", "audit code", "is this good", "review changes"
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
Full codebase audit: architecture health, dependencies, complexity, tech debt. Use when: "audit", "health check", "codebase analysis", "tech debt", "architecture review", "dependency check", "code quality"
Structured brainstorming with multiple approaches and tradeoffs. Use when: "brainstorm", "explore options", "what are my options", "compare approaches", "pros and cons", "which is better", "how should I", "alternatives"
Build error diagnosis and resolution. Use when: "build failed", "compile error", "bundler error", "fix build", "npm error", "type error", "won't compile"
Scaffold a new application with interactive dialogue. Use when: "create", "build me", "make an app", "new project", "scaffold", "generate app", "start new"
Generate a new custom skill from natural language description. Use when: "create skill", "new skill", "make a skill", "add command", "custom workflow", "skill template", "generate skill"
Systematic debugging with hypothesis-driven investigation. Use when: "debug", "not working", "bug", "broken", "error", "unexpected behavior", "fix issue", "investigate"
| name | review |
| description | Comprehensive code review with multi-agent analysis. Use when: "review", "code review", "check my code", "review PR", "audit code", "is this good", "review changes" |
| argument-hint | [file/dir|pr|security|performance] |
| user-invocable | true |
| disable-model-invocation | true |
$ARGUMENTS
This command performs a structured code review on specified files, directories, or recent changes.
/review - Review all staged/unstaged changes
/review [file/dir] - Review specific file or directory
/review pr - Review current PR changes
/review security - Security-focused review
/review performance - Performance-focused review
When /review is triggered:
Identify scope
git branch --show-currentgit diff --cached --statgit diff --statgit log --oneline -5Multi-agent analysis Invoke relevant agents based on file types:
| File Pattern | Agent | Focus |
|---|---|---|
*.tsx, *.jsx, *.css | frontend-specialist | Component quality, a11y, performance |
*.ts (server), *.py | backend-specialist | API design, security, error handling |
*.test.* | test-engineer | Test quality, coverage gaps |
prisma/*, migrations/* | database-architect | Schema quality, query performance |
Dockerfile, CI/* | devops-engineer | Config quality, security |
| All files | security-auditor | Vulnerabilities, secrets, OWASP |
Synthesize findings
## Code Review Report
### Scope
[Files reviewed, line count]
### Summary
| Severity | Count |
|----------|-------|
| Critical | X |
| Warning | X |
| Info | X |
### Findings
#### Critical
1. **[File:Line]** - [Issue description]
- Why: [Explanation]
- Fix: [Code suggestion]
#### Warnings
1. **[File:Line]** - [Issue description]
- Fix: [Suggestion]
#### Suggestions
1. **[File:Line]** - [Improvement idea]
### Verdict
[APPROVE / REQUEST CHANGES / NEEDS DISCUSSION]
| Dimension | What to Check |
|---|---|
| Correctness | Logic bugs, edge cases, off-by-one |
| Security | Injection, auth gaps, secrets exposure |
| Performance | N+1 queries, unnecessary re-renders, large bundles |
| Maintainability | Naming, complexity, single responsibility |
| Type Safety | Any types, missing generics, unsafe casts |
| Error Handling | Uncaught errors, missing fallbacks |
| Testing | Missing tests for new logic |
/review
/review src/services/auth.ts
/review src/components/
/review security
/review pr