code-review-playbook by yonatangross/orchestkit
npx skills add https://github.com/yonatangross/orchestkit --skill code-review-playbook包含钩子
此技能使用 Claude 钩子,可自动响应事件执行代码。安装前请仔细审查。
此技能提供了一个全面的框架,用于进行有效的代码审查,以提高代码质量、分享知识并促进协作。无论您是提供反馈的审查者,还是准备代码以供审查的作者,本手册都能确保审查过程全面、一致且富有建设性。
代码审查服务于多个目的:
保持友善和尊重:
保持具体和可操作:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
平衡速度与彻底性:
区分必须修复与锦上添花:
issue [blocking]: Missing error handling for API call
If the API returns a 500 error, this will crash. Add try/catch.
security [blocking]: API endpoint is not authenticated
The /api/admin/users endpoint is missing auth middleware.
加载 Read("${CLAUDE_SKILL_DIR}/references/conventional-comments.md") 以获取完整格式、标签(praise、nitpick、suggestion、issue、question、security、bug、breaking)、修饰符([blocking]、[non-blocking]、[if-minor])和示例。
检查上下文:
验证自动化检查:
预留时间:
遵循模式:
高层次审查 (5-10 分钟)
详细审查 (20-45 分钟)
测试考虑 (5-10 分钟)
文档检查 (5 分钟)
提供明确决定:
回复作者:
对于审查者:
对于作者:
技能版本 : 2.0.0 最后更新 : 2026-01-08 维护者 : AI Agent Hub Team
ork:architecture-patterns - 在代码审查期间强制执行测试和架构最佳实践security-scanning - 自动化安全检查,以补充手动审查ork:testing-unit - 在审查期间验证的单元测试模式每个类别在 rules/ 目录下都有按需加载的独立规则文件:
| 类别 | 规则 | 影响 | 关键模式 |
|---|---|---|---|
| TypeScript 质量 | rules/typescript-quality.md | HIGH | No any、Zod 验证、穷举 switch、React 19 |
| Python 质量 | rules/python-quality.md | HIGH | Pydantic v2、ruff、mypy strict、async 超时 |
| 安全基线 | rules/security-baseline.md | CRITICAL | 无密钥、端点身份验证、输入验证 |
| 代码检查 | rules/linting-biome-setup.md | HIGH | Biome 设置、ESLint 迁移、渐进式采用 |
| 代码检查 | rules/linting-biome-rules.md | HIGH | Biome 配置、类型感知规则、CI 集成 |
总计:4 个类别中的 5 条规则
scripts/review-pr.md - 使用自动获取的 GitHub 数据进行动态 PR 审查
/ork:review-pr [PR-number]gh)$ARGUMENTS 和 !command 获取实时 PR 数据assets/review-feedback-template.md - 静态审查反馈模板
assets/pr-template.md - PR 描述模板
每周安装次数
106
代码仓库
GitHub 星标数
132
首次出现
Jan 22, 2026
安全审计
安装于
opencode97
gemini-cli96
codex94
github-copilot93
claude-code90
cursor89
Contains Hooks
This skill uses Claude hooks which can execute code automatically in response to events. Review carefully before installing.
This skill provides a comprehensive framework for effective code reviews that improve code quality, share knowledge, and foster collaboration. Whether you're a reviewer giving feedback or an author preparing code for review, this playbook ensures reviews are thorough, consistent, and constructive.
Code reviews serve multiple purposes:
Be Kind and Respectful:
Be Specific and Actionable:
Balance Speed with Thoroughness:
Distinguish Must-Fix from Nice-to-Have:
issue [blocking]: Missing error handling for API call
If the API returns a 500 error, this will crash. Add try/catch.
security [blocking]: API endpoint is not authenticated
The /api/admin/users endpoint is missing auth middleware.
Load Read("${CLAUDE_SKILL_DIR}/references/conventional-comments.md") for the full format, labels (praise, nitpick, suggestion, issue, question, security, bug, breaking), decorations ([blocking], [non-blocking], [if-minor]), and examples.
Check Context:
Verify Automated Checks:
Set Aside Time:
Follow a Pattern:
High-Level Review (5-10 minutes)
Detailed Review (20-45 minutes)
Testing Considerations (5-10 minutes)
Documentation Check (5 minutes)
Provide Clear Decision:
Respond to Author:
For Reviewers:
For Authors:
Skill Version : 2.0.0 Last Updated : 2026-01-08 Maintained by : AI Agent Hub Team
ork:architecture-patterns - Enforce testing and architectural best practices during code reviewsecurity-scanning - Automated security checks to complement manual reviework:testing-unit - Unit testing patterns to verify during reviewEach category has individual rule files in rules/ loaded on-demand:
| Category | Rule | Impact | Key Pattern |
|---|---|---|---|
| TypeScript Quality | rules/typescript-quality.md | HIGH | No any, Zod validation, exhaustive switches, React 19 |
| Python Quality | rules/python-quality.md | HIGH | Pydantic v2, ruff, mypy strict, async timeouts |
| Security Baseline | rules/security-baseline.md | CRITICAL | No secrets, auth on endpoints, input validation |
| Linting | rules/linting-biome-setup.md |
Total: 5 rules across 4 categories
scripts/review-pr.md - Dynamic PR review with auto-fetched GitHub data
/ork:review-pr [PR-number]gh)$ARGUMENTS and !command for live PR dataassets/review-feedback-template.md - Static review feedback template
assets/pr-template.md - PR description template
Weekly Installs
106
Repository
GitHub Stars
132
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode97
gemini-cli96
codex94
github-copilot93
claude-code90
cursor89
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
120,000 周安装
Claude Cowork插件开发指南:从零创建自定义插件完整流程
635 周安装
交互式作品集设计指南:30秒吸引招聘者,提升作品集转化率与个人品牌
621 周安装
OpenClaw voice-call 插件:集成 Twilio/Telnyx/Plivo 实现智能语音通话
643 周安装
iOS PermissionKit 教程:Swift 26+ 通信安全与家长权限请求框架
644 周安装
AlarmKit iOS闹钟框架:在锁屏、灵动岛和Apple Watch上创建醒目闹钟与计时器
655 周安装
iOS 身份验证开发指南:Sign in with Apple、OAuth、生物识别与密码自动填充
652 周安装
| HIGH |
| Biome setup, ESLint migration, gradual adoption |
| Linting | rules/linting-biome-rules.md | HIGH | Biome config, type-aware rules, CI integration |