Code Review Excellence
Use when reviewing a change set, establishing review standards, mentoring contributors, or deciding whether findings block integration; produce constructive, evidence-linked feedback focused on behavior and risk.
Install
npx skills add sandbaseai/workbuddy-skill --skill code-review-excellencegit clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/code-review-excellence ~/.claude/skills/code-review-excellencePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# 卓越代码评审 把代码评审变成发现风险、共享知识和改善设计的协作过程。评审结论必须针对代码和可观察行为,而不是作者;格式化、导入排序和简单拼写优先交给自动化工具。 ## 评审边界 开始前记录:仓库、精确 `base`/`head`、需求或关联任务、文件范围、评审截止时间、可访问的测试/依赖环境、报告读者和合并决策人。 - 只读取被授权的代码、配置、测试和证据;不要把秘密、客户数据、私有 URL 或完整凭据复制到评论或报告。 - 先确认 CI、构建和已知限制,再开始逐行阅读;若 diff 过大或需求不清,先提出拆分或补充上下文。 - 评审意见不自动修改文件、批准、关闭线程、合并或发布;这些动作需要独立授权。 - 无法访问关键文件、测试或需求时标记 `BLOCKED`,不要用猜测代替结论。 ## 评审目标与优先级 评审应该回答:变更是否满足需求,是否保持已有不变量,失败时是否安全,是否有足够的回归证据,以及维护成本是否可接受。 按以下顺序处理: 1. **正确性与边界**:正常路径、空值、边界、并发、重试、时序、状态迁移和错误传播。 2. **安全与权限**:信任边界、认证授权、输入校验、注入、敏感数据、秘密、上传和外部依赖。 3. **可靠性与性能**:超时、取消、幂等、资源释放、N+1、阻塞 I/O、缓存、容量和降级。 4. **测试与可观测性**:行为测试、负面路径、回归覆盖、测试隔离、日志/指标/追踪和告警。 5. **设计与维护性**:接口契约、模块边界、命名、重复逻辑、迁移、兼容性和文档。 将 lint、格式化、导入顺序和可机械修复的拼写交给 CI,除非它们会造成实际行为或发布风险。 ## 分阶段流程 ### 1. 了解上下文 - 阅读需求、验收标准、设计决策和变更说明。 - 固定并记录 `base`/`head`,确认 diff 没有被重新生成或混入无关文件。 - 查看 CI、测试、构建产物、迁移说明和已知风险;记录未运行的检查及原因。 - 若变更超过团队可有效审查的规模,建议按接口/抽象、实现、集成和测试拆分。 ### 2. 高层检查 先不逐行纠结实现,确认: - 方案是否直接解决需求,是否引入不必要的复杂度或重复机制; - 新文件、依赖、配置、数据库迁移和公共 API 是否放在正确边界; - 失败路径、回滚/兼容路径和运行时开关是否明确; - 测试策略是否覆盖最重要的行为和风险,而不是只覆盖内部实现细节。 ### 3. 逐文件验证 对每个关键文件追踪调用者、数据流和错误路径。每个潜在问题都要验证触发条件、实际影响和现有控制: - 逻辑:空集合、极值、重复请求、重入、竞态、时区、编码和部分失败; - 安全:输入是否跨越信任边界,权限是否在每个敏感动作前检查,错误是否泄露信息; - 性能:查询数量、复杂度、内存、连接、并行度、超时和热路径; - 测试:测试的是用户可见行为,是否包含负面路径、独立性、确定性和回归断言; - 维护:职责是否清晰,抽象是否有使用者,契约/迁移/文档是否与实现一致。 能在授权隔离环境验证时,执行最小且可回收的检查,并引用实际输出;不能运行时明确标注未验证。 ### 4. 反馈与决定 每条评论都说明事实、触发条件、影响、证据和可行的下一步。优先提出最少但能解决根因的建议,必要时提供示例或测试方向。总结中分别列出优点、阻断项、非阻断建议、疑问和未覆盖范围,再给出: - `Approve`:没有未解决的高影响问题,关键证据充分;
Details
- Skill name
code-review-excellence- Repository
- sandbaseai/workbuddy-skill
- Path
skills/code-review-excellence/SKILL.md- License
- MIT
- Repo updated
- 8 September 2026
FAQ
What does the Code Review Excellence skill do?
Use when reviewing a change set, establishing review standards, mentoring contributors, or deciding whether findings block integration; produce constructive, evidence-linked feedback focused on behavior and risk.
How do I install the Code Review Excellence skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill code-review-excellence. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Code Review Excellence popular?
It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.
Related skills
Access Control Security Best Practices
9sandbaseai/workbuddy-skill
Design, review, implement, and verify least-privilege access controls across users, services, tenants, resources, and administrative workflows.
Accessibility Review
9sandbaseai/workbuddy-skill
Use when reviewing a web interface or interaction for semantic, keyboard, focus, screen-reader, ARIA, and contrast accessibility risks.
Acquire Codebase Knowledge
9sandbaseai/workbuddy-skill
Use when the user asks to map, document, or onboard into an existing codebase and needs evidence-backed architecture, structure, conventions, integrations, testing, and concerns documentation.
Copilot PR Autopilot
9sandbaseai/workbuddy-skill
Use when explicitly asked to run a bounded Copilot PR review loop, triage threads, verify fixes, and prepare a clean merge decision.
Code Review
5euxx/claude-skills-for-copilot
Multi-agent code review for local changes, files, or directories. Detects bugs, security issues, and conventions-file violations (AGENTS.md/CLAUDE.md/GEMINI.md).
Dev Rules
5Sagargupta16/claude-skills
Use when writing code, making git operations, handling secrets, reviewing PRs, or working with dependencies. Enforces git safety, security best practices, PR workflow discipline, and context-efficient development patterns. Auto-activates as guardrails.
Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.