code-review
综合代码审查 skill，覆盖安全、性能、代码质量和可维护性。Use when users ask to review code, analyze code quality, evaluate pull requests, or mention code review, security analysis, or performance optimization.
Best for PR reviewsWorks with GitHubLow risk
⌘source
- author
@lhfer- language
- Python
★1.1kstars
195forks
May 5, 2026
✦overview.md
Key Features
- ·Structured code review checklist
- ·Covers security, performance, quality
- ·Includes review templates and scripts
- ·Quantitative metrics analysis
- ·Severity-based issue tracking
Use Cases
- →Review a pull request for security vulnerabilities
- →Evaluate code quality and maintainability in a legacy codebase
- →Compare code complexity before and after refactoring
- →Generate structured review reports for team audits
Best for
- ✓PR reviews
- ✓team code audits
- ✓refactoring verification
Not ideal for
- !one-time code snippets
- !non-code artifacts
FAQs
name
code-review-specialist
description
综合代码审查 skill，覆盖安全、性能、代码质量和可维护性。Use when users ask to review code, analyze code quality, evaluate pull requests, or mention code review, security analysis, or performance optimization.
代码审查技能（Code Review Skill）
这个 skill 用于做结构化代码审查，重点关注：
- Security Analysis
- Performance Review
- Code Quality
- Maintainability
审查模板
参考文件
这个 skill 自带模板和脚本，做正式审查时应按需读取：
templates/review-checklist.md：结构化检查清单，覆盖安全、性能、质量和测试，避免漏掉大类。templates/finding-template.md：单个问题的记录模板，包含严重程度、位置、代码示例和影响分析。scripts/analyze-metrics.py：统计函数数、类数、平均行长和复杂度分数，可用于给审查补充量化依据。scripts/compare-complexity.py：对比两个版本的复杂度，适合审查重构前后的变化。
总结
- Overall quality assessment
- Key findings count
- Recommended priority areas
严重问题
- Issue
- Location
- Impact
- Severity
- Fix
按类别列出问题
安全
列出安全漏洞或风险点
性能
列出性能问题与复杂度风险
质量
列出命名、结构、文档和测试问题
可维护性
列出可维护性问题和重构建议
$install
1-click copynpx skills add lhfer/claude-howto-zh-cn --skill code-reviewSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.