review-code
Multi-dimensional code review with structured reports. Analyzes correctness, readability, performance, security, testing, and architecture. Triggers on "review code", "code review", "审查代码", "代码审查".
Install
mkdir -p .claude/skills/review-code && curl -L -o skill.zip "https://mcp.directory/api/skills/download/6582" && unzip -o skill.zip -d .claude/skills/review-code && rm skill.zipInstalls to .claude/skills/review-code
About this skill
Review Code
Multi-dimensional code review skill that analyzes code across 6 key dimensions and generates structured review reports with actionable recommendations.
Architecture Overview
┌─────────────────────────────────────────────────────────────────┐
│ ⚠️ Phase 0: Specification Study (强制前置) │
│ → 阅读 specs/review-dimensions.md │
│ → 理解审查维度和问题分类标准 │
└───────────────┬─────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────────────┐
│ Orchestrator (状态驱动决策) │
│ → 读取状态 → 选择审查动作 → 执行 → 更新状态 │
└───────────────┬─────────────────────────────────────────────────┘
│
┌───────────┼───────────┬───────────┬───────────┐
↓ ↓ ↓ ↓ ↓
┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐
│ Collect │ │ Quick │ │ Deep │ │ Report │ │Complete │
│ Context │ │ Scan │ │ Review │ │ Generate│ │ │
└─────────┘ └─────────┘ └─────────┘ └─────────┘ └─────────┘
↓ ↓ ↓ ↓
┌─────────────────────────────────────────────────────────────────┐
│ Review Dimensions │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │Correctness│ │Readability│ │Performance│ │ Security │ │
│ └──────────┘ └──────────┘ └──────────┘ └──────────┘ │
│ ┌──────────┐ ┌──────────┐ │
│ │ Testing │ │Architecture│ │
│ └──────────┘ └──────────┘ │
└─────────────────────────────────────────────────────────────────┘
Project Context: Run ccw spec load --category review for review standards, checklists, and approval gates.
Key Design Principles
- 多维度审查: 覆盖正确性、可读性、性能、安全性、测试覆盖、架构一致性六大维度
- 分层执行: 快速扫描识别高风险区域,深入审查聚焦关键问题
- 结构化报告: 按严重程度分类,提供文件位置和修复建议
- 状态驱动: 自主模式,根据审查进度动态选择下一步动作
⚠️ Mandatory Prerequisites (强制前置条件)
⛔ 禁止跳过: 在执行任何审查操作之前,必须完整阅读以下文档。
规范文档 (必读)
| Document | Purpose | Priority |
|---|---|---|
| specs/review-dimensions.md | 审查维度定义和检查点 | P0 - 最高 |
| specs/issue-classification.md | 问题分类和严重程度标准 | P0 - 最高 |
| specs/quality-standards.md | 审查质量标准 | P1 |
模板文件 (生成前必读)
| Document | Purpose |
|---|---|
| templates/review-report.md | 审查报告模板 |
| templates/issue-template.md | 问题记录模板 |
Execution Flow
┌─────────────────────────────────────────────────────────────────┐
│ Phase 0: Specification Study (强制前置 - 禁止跳过) │
│ → Read: specs/review-dimensions.md │
│ → Read: specs/issue-classification.md │
│ → 理解审查标准和问题分类 │
├─────────────────────────────────────────────────────────────────┤
│ Action: collect-context │
│ → 收集目标文件/目录 │
│ → 识别技术栈和语言 │
│ → Output: state.context (files, language, framework) │
├─────────────────────────────────────────────────────────────────┤
│ Action: quick-scan │
│ → 快速扫描整体结构 │
│ → 识别高风险区域 │
│ → Output: state.risk_areas, state.scan_summary │
├─────────────────────────────────────────────────────────────────┤
│ Action: deep-review (per dimension) │
│ → 逐维度深入审查 │
│ → 记录发现的问题 │
│ → Output: state.findings[] │
├─────────────────────────────────────────────────────────────────┤
│ Action: generate-report │
│ → 汇总所有发现 │
│ → 生成结构化报告 │
│ → Output: review-report.md │
├─────────────────────────────────────────────────────────────────┤
│ Action: complete │
│ → 保存最终状态 │
│ → 输出审查摘要 │
└─────────────────────────────────────────────────────────────────┘
Directory Setup
const timestamp = new Date().toISOString().slice(0,19).replace(/[-:T]/g, '');
const workDir = `.workflow/.scratchpad/review-code-${timestamp}`;
Bash(`mkdir -p "${workDir}"`);
Bash(`mkdir -p "${workDir}/findings"`);
Output Structure
.workflow/.scratchpad/review-code-{timestamp}/
├── state.json # 审查状态
├── context.json # 目标上下文
├── findings/ # 问题发现
│ ├── correctness.json
│ ├── readability.json
│ ├── performance.json
│ ├── security.json
│ ├── testing.json
│ └── architecture.json
└── review-report.md # 最终审查报告
Review Dimensions
| Dimension | Focus Areas | Key Checks |
|---|---|---|
| Correctness | 逻辑正确性 | 边界条件、错误处理、null 检查 |
| Readability | 代码可读性 | 命名规范、函数长度、注释质量 |
| Performance | 性能效率 | 算法复杂度、I/O 优化、资源使用 |
| Security | 安全性 | 注入风险、敏感信息、权限控制 |
| Testing | 测试覆盖 | 测试充分性、边界覆盖、可维护性 |
| Architecture | 架构一致性 | 设计模式、分层结构、依赖管理 |
Issue Severity Levels
| Level | Prefix | Description | Action Required |
|---|---|---|---|
| Critical | [C] | 阻塞性问题,必须立即修复 | Must fix before merge |
| High | [H] | 重要问题,需要修复 | Should fix |
| Medium | [M] | 建议改进 | Consider fixing |
| Low | [L] | 可选优化 | Nice to have |
| Info | [I] | 信息性建议 | For reference |
Reference Documents
More by catlog22
View all skills by catlog22 →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
fastapi-templates
wshobson
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
Related MCP Servers
Browse all serversGet structured & freeform code reviews with code quality analysis tools powered by OpenAI, Google & Anthropic. Supports
Unlock AI-ready web data with Firecrawl: scrape any website, handle dynamic content, and automate web scraping for resea
Break down complex problems with Sequential Thinking, a structured tool and step by step math solver for dynamic, reflec
Enhance software testing with Playwright MCP: Fast, reliable browser automation, an innovative alternative to Selenium s
Optimize your codebase for AI with Repomix—transform, compress, and secure repos for easier analysis with modern AI tool
Integrate FireCrawl for advanced web scraping to extract clean, structured data from complex websites—fast, scalable, an
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.