code-review

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Code Review Skill

代码审查Skill

Conduct a thorough code review for quality, security, and maintainability with severity-rated feedback.

执行全面的代码审查，针对代码质量、安全性和可维护性提供带有严重程度评级的反馈。

When to Use

适用场景

This skill activates when:

User requests "review this code", "code review"
Before merging a pull request
After implementing a major feature
User wants quality assessment

当出现以下情况时，该技能会激活：

用户请求"审查这段代码"、"代码审查"
在合并pull request之前
完成主要功能实现之后
用户需要进行质量评估

What It Does

功能说明

Delegates to the

code-reviewer

agent (Opus model) for deep analysis:

Identify Changes
- Run
```
git diff
```
  to find changed files
- Determine scope of review (specific files or entire PR)
Review Categories
- Security - Hardcoded secrets, injection risks, XSS, CSRF
- Code Quality - Function size, complexity, nesting depth
- Performance - Algorithm efficiency, N+1 queries, caching
- Best Practices - Naming, documentation, error handling
- Maintainability - Duplication, coupling, testability
Severity Rating
- CRITICAL - Security vulnerability (must fix before merge)
- HIGH - Bug or major code smell (should fix before merge)
- MEDIUM - Minor issue (fix when possible)
- LOW - Style/suggestion (consider fixing)
Specific Recommendations
- File:line locations for each issue
- Concrete fix suggestions
- Code examples where applicable

委托给

code-reviewer

Agent（Opus模型）进行深度分析：

识别变更
- 运行
```
git diff
```
  查找已变更的文件
- 确定审查范围（特定文件或整个PR）
审查类别
- 安全性 - 硬编码密钥、注入风险、XSS、CSRF
- 代码质量 - 函数大小、复杂度、嵌套深度
- 性能 - 算法效率、N+1查询、缓存
- 最佳实践 - 命名规范、文档、错误处理
- 可维护性 - 代码重复、耦合度、可测试性
严重程度评级
- CRITICAL（严重） - 安全漏洞（合并前必须修复）
- HIGH（高） - 缺陷或主要代码异味（合并前应修复）
- MEDIUM（中） - 次要问题（尽可能修复）
- LOW（低） - 代码风格/建议（考虑修复）
具体建议
- 每个问题对应的文件:行号位置
- 具体的修复建议
- 适用时提供代码示例

Agent Delegation

Agent委托

Task(
  subagent_type="oh-my-claudecode:code-reviewer",
  model="opus",
  prompt="CODE REVIEW TASK

Review code changes for quality, security, and maintainability.

Scope: [git diff or specific files]

Review Checklist:
- Security vulnerabilities (OWASP Top 10)
- Code quality (complexity, duplication)
- Performance issues (N+1, inefficient algorithms)
- Best practices (naming, documentation, error handling)
- Maintainability (coupling, testability)

Output: Code review report with:
- Files reviewed count
- Issues by severity (CRITICAL, HIGH, MEDIUM, LOW)
- Specific file:line locations
- Fix recommendations
- Approval recommendation (APPROVE / REQUEST CHANGES / COMMENT)"
)

Task(
  subagent_type="oh-my-claudecode:code-reviewer",
  model="opus",
  prompt="CODE REVIEW TASK

Review code changes for quality, security, and maintainability.

Scope: [git diff or specific files]

Review Checklist:
- Security vulnerabilities (OWASP Top 10)
- Code quality (complexity, duplication)
- Performance issues (N+1, inefficient algorithms)
- Best practices (naming, documentation, error handling)
- Maintainability (coupling, testability)

Output: Code review report with:
- Files reviewed count
- Issues by severity (CRITICAL, HIGH, MEDIUM, LOW)
- Specific file:line locations
- Fix recommendations
- Approval recommendation (APPROVE / REQUEST CHANGES / COMMENT)"
)

External Model Consultation (Preferred)

外部模型咨询（推荐）

The code-reviewer agent SHOULD consult Codex for cross-validation.

code-reviewer Agent应咨询Codex进行交叉验证。

Protocol

流程规范

Form your OWN review FIRST - Complete the review independently
Consult for validation - Cross-check findings with Codex
Critically evaluate - Never blindly adopt external findings
Graceful fallback - Never block if tools unavailable

先独立完成审查 - 自主完成审查工作
咨询以验证结果 - 与Codex交叉核对审查发现
严谨评估 - 切勿盲目采纳外部结果
优雅降级 - 若工具不可用，切勿阻塞流程

When to Consult

咨询时机

Security-sensitive code changes
Complex architectural patterns
Unfamiliar codebases or languages
High-stakes production code

安全敏感的代码变更
复杂的架构模式
不熟悉的代码库或编程语言
高风险的生产环境代码

When to Skip

跳过时机

Simple refactoring
Well-understood patterns
Time-critical reviews
Small, isolated changes

简单的重构
熟知的代码模式
时间紧迫的审查
小型、独立的变更

Tool Usage

工具使用

Use

mcp__x__ask_codex

with

agent_role: "code-reviewer"

Note: Codex calls can take up to 1 hour. Consider the review timeline before consulting.

使用

mcp__x__ask_codex

，并设置

agent_role: "code-reviewer"

。

注意： 调用Codex可能需要长达1小时。请在咨询前考虑审查时间线。

Output Format

输出格式

CODE REVIEW REPORT
==================

Files Reviewed: 8
Total Issues: 15

CRITICAL (0)
-----------
(none)

HIGH (3)
--------
1. src/api/auth.ts:42
   Issue: User input not sanitized before SQL query
   Risk: SQL injection vulnerability
   Fix: Use parameterized queries or ORM

2. src/components/UserProfile.tsx:89
   Issue: Password displayed in plain text in logs
   Risk: Credential exposure
   Fix: Remove password from log statements

3. src/utils/validation.ts:15
   Issue: Email regex allows invalid formats
   Risk: Accepts malformed emails
   Fix: Use proven email validation library

MEDIUM (7)
----------
...

LOW (5)
-------
...

RECOMMENDATION: REQUEST CHANGES

Critical security issues must be addressed before merge.

CODE REVIEW REPORT
==================

Files Reviewed: 8
Total Issues: 15

CRITICAL (0)
-----------
(none)

HIGH (3)
--------
1. src/api/auth.ts:42
   Issue: User input not sanitized before SQL query
   Risk: SQL injection vulnerability
   Fix: Use parameterized queries or ORM

2. src/components/UserProfile.tsx:89
   Issue: Password displayed in plain text in logs
   Risk: Credential exposure
   Fix: Remove password from log statements

3. src/utils/validation.ts:15
   Issue: Email regex allows invalid formats
   Risk: Accepts malformed emails
   Fix: Use proven email validation library

MEDIUM (7)
----------
...

LOW (5)
-------
...

RECOMMENDATION: REQUEST CHANGES

Critical security issues must be addressed before merge.

Review Checklist

审查检查清单

The code-reviewer agent checks:

code-reviewer Agent会检查以下内容：

Security

安全性

Code Quality

代码质量

Performance

性能

No N+1 query patterns
Appropriate caching where applicable
Efficient algorithms (avoid O(n²) when O(n) possible)
No unnecessary re-renders (React/Vue)

无N+1查询模式
在适用场景下使用了合适的缓存
算法高效（在可行时避免O(n²)复杂度）
无不必要的重渲染（React/Vue）

Best Practices

最佳实践

Approval Criteria

批准标准

APPROVE - No CRITICAL or HIGH issues, minor improvements only REQUEST CHANGES - CRITICAL or HIGH issues present COMMENT - Only LOW/MEDIUM issues, no blocking concerns

APPROVE（批准） - 无CRITICAL或HIGH级问题，仅存在次要改进点 REQUEST CHANGES（要求变更） - 存在CRITICAL或HIGH级问题 COMMENT（评论） - 仅存在LOW/MEDIUM级问题，无阻塞性问题

Use with Other Skills

与其他Skill搭配使用

With Pipeline:

/pipeline review "implement user authentication"

Includes code review as part of implementation workflow.

With Ralph:

/ralph code-review then fix all issues

Review code, get feedback, fix until approved.

With Ultrawork:

/ultrawork review all files in src/

Parallel code review across multiple files.

与Pipeline搭配：

/pipeline review "implement user authentication"

将代码审查作为实现工作流的一部分。

与Ralph搭配：

/ralph code-review then fix all issues

审查代码、获取反馈、修复问题直至获得批准。

与Ultrawork搭配：

/ultrawork review all files in src/

对多个文件进行并行代码审查。

Best Practices

最佳实践

Review early - Catch issues before they compound
Review often - Small, frequent reviews better than huge ones
Address CRITICAL/HIGH first - Fix security and bugs immediately
Consider context - Some "issues" may be intentional trade-offs
Learn from reviews - Use feedback to improve coding practices

尽早审查 - 在问题复杂化之前发现并解决
经常审查 - 小型、频繁的审查优于大规模审查
优先处理CRITICAL/HIGH级问题 - 立即修复安全漏洞和缺陷
考虑上下文 - 某些“问题”可能是有意的权衡选择
从审查中学习 - 利用反馈改进编码实践