Token导航 LogoToken导航

Agent Skill · 前端设计

code-review(代码审查)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

code-review 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 7,287。

总安装 392周安装 16GitHub Stars 11下载 125核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:code-review(代码审查)
来源仓库:https://github.com/lobbi-docs/claude
仓库路径:skills/code-review
安装命令:
npx skills add https://github.com/lobbi-docs/claude --skill code-review
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/lobbi-docs/claude --skill code-review

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。适合提炼结构、补齐章节、统一术语或检查链接,提升内容可读性。使用时保留项目已有事实和命令,避免将未确认信息写成确定结论。涉及对外文案时需控制语气,防止过度营销或夸大能力。安装方式:通过 npx 从 GitHub 仓库添加技能。

来源仓库内路径:skills/code-review

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/lobbi-docs/claude --skill code-review;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

code-review 怎么安装?

在终端执行 npx skills add https://github.com/lobbi-docs/claude --skill code-review。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

code-review 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

code-review 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

code-review 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

code-review 用的人多吗?

公开数据是累计安装 392 次,近一周安装 16 次,下载 125 次,GitHub 11 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

code-review 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
code-review

代码审查 · 本页

39211需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Code Review Skill

Systematic code review patterns covering security, performance, accessibility, quality, and testing across languages and frameworks.

Security Review

Critical Checks:

  • Authentication tokens validated; authorization on sensitive ops
  • Session management secure (httpOnly, secure, sameSite)
  • No hardcoded credentials/API keys
  • Proper RBAC implementation
  • JWT tokens with proper algorithms (not 'none')
  • Password hashing: bcrypt/argon2 (not MD5/SHA1)

Input Validation:

  • User inputs sanitized
  • SQL injection prevention (parameterized queries)
  • XSS prevention (escaping/sanitization)
  • CSRF tokens on state-changing ops
  • File upload validation (type, size, content)
  • JSON/XML size limits
  • URL validation for redirects

Data Protection:

  • Sensitive data encrypted at rest
  • TLS/HTTPS for transit
  • No sensitive data in logs
  • PII handling regulation-compliant
  • Secure random (crypto.randomBytes)
  • Secrets in env vars or secret managers
  • Encrypted database connections

OWASP Top 10: No injection, broken auth, data exposure, XXE, broken access control, misconfiguration, XSS, insecure deserialization, vulnerable components, insufficient logging

Performance Review

Database & Queries:

  • N+1 queries identified and fixed
  • Proper indexing on WHERE/JOIN columns
  • Query result sets limited (pagination)
  • Connection pooling implemented
  • Expensive queries cached
  • Batch operations instead of loops

Frontend Performance:

  • Code splitting for large bundles
  • Lazy loading routes/components
  • Images optimized and lazy loaded
  • CSS/JS minified and compressed
  • Memoization for expensive computations
  • Virtual scrolling for long lists

API & Network:

  • API responses paginated
  • GraphQL queries optimized (no over-fetching)
  • Response compression (gzip/brotli)
  • CDN for static assets
  • HTTP/2 or HTTP/3
  • Proper caching headers
  • Rate limiting implemented

Memory Management:

  • Event listeners removed
  • No memory leaks (closures, timers)
  • Large objects disposed
  • File streams closed
  • WeakMap/WeakSet for caching

Accessibility Review (WCAG 2.1 AA)

Semantic HTML:

  • Proper heading hierarchy (h1, h2, h3)
  • Semantic elements (nav, main, article, aside)
  • Form labels properly associated
  • Button vs link used correctly
  • Tables with proper headers

Keyboard Navigation:

  • All interactive elements accessible
  • Logical tab order
  • Focus indicators visible
  • No keyboard traps
  • Skip links for navigation

Screen Reader Support:

  • All images have alt text
  • ARIA labels where needed
  • Live regions for dynamic content
  • Hidden content marked properly

Color & Contrast:

  • Text contrast >= 4.5:1 (normal)
  • Text contrast >= 3:1 (large)
  • Info not conveyed by color alone

Forms:

  • Error messages associated with fields
  • Required fields clearly marked
  • Validation accessible
  • Autocomplete attributes set

Code Quality Standards

Readability:

  • Descriptive variable/function names
  • Functions < 50 lines
  • Consistent naming (camelCase, PascalCase)
  • No magic numbers
  • Proper indentation

Maintainability:

  • DRY principle followed
  • SOLID principles applied
  • Low coupling, high cohesion
  • Proper separation of concerns
  • Configuration externalized
  • Feature flags for gradual rollout

Error Handling:

  • All errors caught and handled
  • User-friendly messages
  • Errors logged with context
  • Graceful degradation
  • Retry logic for transient failures
  • Circuit breakers for external services

Comments:

  • Complex logic explained
  • Why, not what (code self-explanatory)
  • TODO/FIXME with issue tracking
  • JSDoc/TSDoc for public APIs
  • No commented-out code

Testing Requirements

Unit Tests:

  • All business logic tested
  • Edge cases covered
  • Error conditions tested
  • Mocks for external dependencies
  • Test coverage >= 80%
  • Deterministic tests (no flaky)

Integration Tests:

  • API endpoints tested
  • Database operations tested
  • External integrations tested
  • Auth flows tested

E2E Tests:

  • Critical user flows covered
  • Happy paths tested
  • Error scenarios tested

Test Quality:

  • Readable and maintainable
  • AAA pattern (Arrange, Act, Assert)
  • Meaningful descriptions
  • No interdependencies
  • Fast execution (< 10s unit tests)

Language-Specific Patterns

TypeScript/JavaScript

Type Safety:

  • No any types (use unknown if needed)
  • Strict mode enabled
  • Union types over enums
  • Proper generic constraints
  • Type guards for narrowing

Modern Patterns:

  • Destructuring and defaults
  • Optional chaining (?.) and nullish coalescing (??)
  • Async/await over promise chains
  • Arrow functions for callbacks

React Components

Best Practices:

  • Functional components with hooks
  • Props properly typed
  • Minimal, localized state
  • Effect dependencies correct
  • No inline function definitions
  • Keys correct in lists
  • useCallback/useMemo for optimization

Node.js

Server Setup:

  • Error handling middleware
  • Request validation
  • Rate limiting
  • Helmet for security headers
  • CORS configured
  • Graceful shutdown handling

Python

Best Practices:

  • Type hints on functions
  • PEP 8 compliance
  • Context managers for resources
  • List comprehensions over loops
  • Dataclasses for data structures

SQL

Best Practices:

  • Parameterized queries only
  • Indexes on WHERE/JOIN columns
  • LIMIT on large queries
  • Transactions for consistency
  • Specify columns (no SELECT *)

Review Process

File Change Analysis:

  • High risk: auth, migrations, security config, payments, encryption
  • Medium risk: business logic, API, queries, integrations
  • Low risk: UI, tests, docs

Impact Assessment:

  • Blast radius of change
  • Backward compatibility
  • Database migrations needed
  • User impact
  • Performance implications
  • Security implications

Approval Criteria:

  • No critical security issues
  • Tests passing
  • Code coverage maintained/improved
  • Documentation updated
  • No performance regressions
  • Accessibility requirements met
  • Code follows style guide
  • Changes backward compatible (or migration plan exists)

Request Changes for:

  • Critical security vulnerabilities
  • Failing tests
  • Missing test coverage
  • Breaking changes without migration
  • Performance regressions
  • Accessibility violations

Common Issues Reference

Security: Hardcoded secrets, SQL injection, missing auth, weak random generation, PII in logs, missing CSRF

Performance: N+1 queries, missing indexes, unnecessary re-renders, large bundles, sync blocking ops, memory leaks

Code Smells: Functions > 50 lines, nesting > 3 levels, duplication, magic numbers, poor naming, god objects

Missing Error Handling: Unhandled rejections, missing try/catch, no input validation, silent failures, generic messages

Incomplete Tests: Missing edge cases, no error tests, flaky tests, no integration tests, no accessibility tests

Review Workflow

  1. Initial Scan (2 min): PR description, file changes, high-risk files
  2. Deep Dive (15-30 min): Review each file, apply checklists, note issues
  3. Testing Verification (5 min): Check coverage, test quality
  4. Documentation Check (3 min): Updated docs, breaking changes
  5. Feedback Generation (5 min): Organize by severity, code suggestions
  6. Decision (1 min): Approve, request changes, or comment

Tools Integration

Automated Checks:

  • ESLint/Prettier: Code style
  • SonarQube: Quality metrics
  • Snyk/Dependabot: Security vulnerabilities
  • Jest/Vitest: Test coverage
  • Lighthouse: Performance/accessibility
  • TypeScript: Type safety

Manual Review Focus:

  • Business logic correctness
  • Architecture decisions
  • Security implications
  • UX impact
  • Maintainability

Best Practices Summary

  1. Security first
  2. Performance matters
  3. Accessibility is non-negotiable
  4. Quality over speed
  5. Constructive feedback
  6. Continuous improvement

平台分布

Codex

37.49%
按下载量换算47

Claude

29.7%
按下载量换算37

Cursor

19.52%
按下载量换算24

Gemini CLI

9.87%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills