做什么
为React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java, 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C#/.NET, Kotlin, Swift, Dart, Flutter, NestJS, C/C++, Zig, CSS/Less, Qt等提供综合代码审查指导. 涵盖所有生态系统的架构审查、业绩审查、安全审计、代码质量防标和常见错误
技能库 智客分类:安全测试 code-review-skill
为React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java, 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C#/.NET, Kotlin, Swift, Dart, Flutter, NestJS, C/C++, Zig, CSS/Less, Qt等提供综合代码审查指导. 涵盖架构审查,性能审查,安全审计,代码质量防标,以及所有生态系统常见的bug. 使用时:审查拉动请求,进行PR审查,代码审查,审查代码修改,建立审查标准,指导开发者,架构审查,安全审计,业绩审查,检查代码质量,查找错误,提供代码反馈.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
为React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java, 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C#/.NET, Kotlin, Swift, Dart, Flutter, NestJS, C/C++, Zig, CSS/Less, Qt等提供综合代码审查指导. 涵盖所有生态系统的架构审查、业绩审查、安全审计、代码质量防标和常见错误
这个技能
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Code Review Skill、When to Use This Skill、Core Principles、1. The Review Mindset、2. Effective Feedback、3. Review Scope。
文件分析:除 SKILL.md 外,正文引用了 scripts/pr-analyzer.py、assets/pr-review-template.md、assets/review-checklist.md,属于带资源的技能包,这些文件按需再读。
Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C#/.NET, Kotlin, Swift, Dart, Flutter, NestJS, C/C++, Zig, CSS/Less/Sass, Qt, and more. Covers architecture review, performance review, security audit, code quality anti-patterns, and common bugs across all ecosystems. Use when: reviewing pull requests, conducting PR reviews, code review, reviewing code changes, establishing review standards, mentoring developers, architecture reviews, security audits, performance reviews, checking code quality, finding bugs, giving feedback on code.
Code Review SkillWhen to Use This SkillCore Principles1. The Review Mindset2. Effective Feedback3. Review ScopeReview ProcessPhase 1: Context Gathering (2-3 minutes)Phase 2: High-Level Review (5-10 minutes)Phase 3: Line-by-Line Review (10-20 minutes)Phase 4: Summary & Decision (2-3 minutes)Review Techniques
来源分类:skills.sh agent-skill
namecode-review-skilldescriptionscripts/pr-analyzer.pyassets/pr-review-template.mdassets/review-checklist.md以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。
具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「code-review-skill」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-8f09237d189d398c-%E4%BB%A3%E7%A0%81%E5%AE%A1%E6%9F%A5%E6%8A%80%E8%83%BD.html 请存为 .cursor/skills/code-review-skill/SKILL.md 或 .claude/skills/code-review-skill/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。 该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/awesome-skills/code-review-skill 取完整目录,不要只建一个 SKILL.md。
需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。
npx skills add 'https://github.com/awesome-skills/code-review-skill' --list
npx skills add 'https://github.com/awesome-skills/code-review-skill' --skill 'code-review-skill'
CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。
name: code-review-skill description: | Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C#/.NET, Kotlin, Swift, Dart, Flutter, NestJS, C/C++, Zig, CSS/Less/Sass, Qt, and more. Covers architecture review, performance review, security audit, code quality anti-patterns, and common bugs across all ecosystems. Use when: reviewing pull requests, conducting PR reviews, code review, reviewing code changes, establishing review standards, mentoring developers, architecture reviews, security audits, performance reviews, checking code quality, finding bugs, giving feedback on code. allowed-tools:
Transform code reviews from gatekeeping to knowledge sharing through constructive feedback, systematic analysis, and collaborative improvement.
Goals of Code Review:
Not the Goals:
Good Feedback is:
❌ Bad: "This is wrong."
✅ Good: "This could cause a race condition when multiple users
access simultaneously. Consider using a mutex here."
❌ Bad: "Why didn't you use X pattern?"
✅ Good: "Have you considered the Repository pattern? It would
make this easier to test. Here's an example: [link]"
❌ Bad: "Rename this variable."
✅ Good: "[nit] Consider `userCount` instead of `uc` for
clarity. Not blocking if you prefer to keep it."
What to Review:
What Not to Review Manually:
Before diving into code, understand:
For large diffs, pipe the diff through
scripts/pr-analyzer.py(git diff main...HEAD | python scripts/pr-analyzer.py) to triage complexity and get a suggested review approach before reading.
For each file, check:
Use checklists for consistent reviews. See Security Review Guide for comprehensive security checklist.
Instead of stating problems, ask questions:
❌ "This will fail if the list is empty."
✅ "What happens if `items` is an empty array?"
❌ "You need error handling here."
✅ "How should this behave if the API call fails?"
Use collaborative language:
❌ "You must change this to use async/await"
✅ "Suggestion: async/await might make this more readable. What do you think?"
❌ "Extract this into a function"
✅ "This logic appears in 3 places. Would it make sense to extract it?"
Use labels to indicate priority:
[blocking] - Must fix before merge[important] - Should fix, discuss if disagree[nit] - Nice to have, not blocking[suggestion] - Alternative approach to consider[learning] - Educational comment, no action needed[praise] - Good work, keep it up!Severity levels: 🔴 / 🟡 / 🟢 are the three severity tiers used as the standard across all guides in this skill — 🔴 blocks the merge, 🟡 should be addressed, 🟢 is optional. The remaining markers (💡 / 📚 / 🎉) are non-blocking annotations.
根据审查的代码语言,查阅对应的详细指南:
| Language/Framework | Reference File | Key Topics | |-------------------|----------------|------------| | React | React Guide | Hooks, useEffect, React 19 Actions, RSC, Suspense, TanStack Query v5 | | Vue 3 | Vue Guide | Composition API, 响应性系统, Props/Emits, Watchers, Composables | | Angular 17+ | Angular Guide | Signals, Standalone, RxJS, Zoneless, 模板优化, 测试, 路由守卫, HttpInterceptor | | Rust | Rust Guide | 所有权/借用, Unsafe 审查, 异步代码, 取消安全性, 错误处理 | | TypeScript | TypeScript Guide | 类型安全, async/await, 不可变性, 测试, 模块解析, TS 5.x | | Python | Python Guide | 可变默认参数, 异常处理, 类属性 | | Django / DRF | Django Guide | 安全审查, N+1 查询, Serializer 反模式, ViewSet, 异步视图 | | FastAPI | FastAPI Guide | Depends, Pydantic v2 validation, async correctness, sessions/N+1, auth vs authorization, test-driven verification | | Java | Java Guide | Java 17/21 新特性, Spring Boot 3, 虚拟线程, Stream/Optional | | Java 8 / Legacy | Java 8 Guide | Java 8, Spring Boot 2, javax.*, Stream/Optional, java.time, CompletableFuture | | PHP | PHP Guide | PHP 8.x type system, PDO, security review, Composer, PHPUnit/PHPStan | | Ruby / Rails | Ruby Guide | Ruby semantics, Rails 8, Active Record, Active Job, security, testing | | C# / .NET | C# Guide | C# 12 特性, 异步编程, EF Core 性能, ASP.NET Core, LINQ | | Go | Go Guide | 错误处理, goroutine/channel, context, 接口设计 | | Kotlin / Android | Kotlin Guide | 协程, Flow, Jetpack Compose, 空安全, 内存泄漏, 架构模式 | | Swift / SwiftUI | Swift Guide | Optionals, Swift Concurrency, Sendable/actors, SwiftUI property wrappers, value vs reference types, API design | | Dart / Flutter | Dart Guide | Widget rebuilds, const constructors, null safety, isolates, async in build, Riverpod/Bloc, platform channels, keys, disposal | | NestJS | NestJS Guide | 依赖注入, 分层架构, DTO 验证, Guard/Interceptor, 循环依赖 | | Svelte / SvelteKit | Svelte Guide | Runes, Load 函数, Form Actions, Store 迁移, SSR/CSR 边界 | | C | C Guide | 指针/缓冲区, 内存安全, UB, 安全编码, 可移植性, 测试 | | C++ | C++ Guide | RAII, 智能指针, C++20/23, constexpr, 测试 | | Zig | Zig Guide | Allocators, error unions, defer/errdefer, comptime, C interop | | CSS/Less/Sass | CSS Guide | 变量规范, !important, 性能优化, 响应式, 兼容性 | | Qt | Qt Guide | 对象模型, 信号/槽, Model/View, QML, Qt6 迁移, 测试 |
Language-agnostic patterns applicable to all code reviews:
| Topic | Reference File | Key Topics | |-------|----------------|------------| | Architecture Review | Architecture Review Guide | SOLID, anti-patterns, coupling/cohesion, dependency direction | | Performance Review | Performance Review Guide | Web Vitals, N+1, algorithm complexity, memory leaks, caching | | Security Review | Security Review Guide | SQLi, XSS, CSRF, SSRF, IDOR, 命令注入, 跨语言示例 | | Universal Quality | Universal Quality Guide | Reuse audit, parameter sprawl, leaky abstractions, nested conditionals, stringly-typed code, TOCTOU, no-op updates, redundant state | | Common Bugs | Common Bugs Checklist | Language-specific bug patterns, common pitfalls | | SQL Injection Prevention | SQL Injection Guide | Parameterized queries, ORM safety, 6 languages, dynamic identifiers, detection | | XSS Prevention | XSS Prevention Guide | Output encoding, CSP, 5 frameworks, input validation vs encoding, detection | | N+1 Queries | N+1 Queries Guide | Eager loading, batch fetching, DataLoader, 5 languages, detection | | Error Handling | Error Handling Guide | Fail fast, error hierarchy, 7 languages, anti-patterns, logging | | Async & Concurrency | Concurrency Guide | Goroutines, async/await, actors, structured concurrency, 7 languages | | Review Best Practices | Code Review Best Practices | Communication, reviewer mindset, giving feedback, severity labels |
安全测试
人工智能特工的安全第一技能审查。 在安装来自 ClawdHub, GitHub 或其他来源的任何技能之前使用 。 检查红旗,许可范围,可疑图案.
安全测试
MoltGuard——由OpenGuardrails担任OpenClaw保安. 安装 MoltGuard 以保护你和你的人类免受迅速注射、数据过滤和恶意命令的影响。 资料来源:https://github.com/openguardrails/openguardrails/tre…
安全测试
用于审查安全漏洞代码,实施认证流,审计OWASP Top 10,配置CORS/CSP头,处理秘密,输入验证,SQL注射预防,XSS保护,或任何与安全相关的代码审查.
安全测试
安装任何AI代理技能前的安全审查协议. 红旗侦取入证盗取,疏通密码,放出. 风险分类:低/中/高/高。 编制结构化审查报告。 不先运行此功能, 绝不安装不信任的技能 .