studio-review
Skill1 starsChanged 3 months agoMITView on GitHub
【Studio】技术评审 — 性能/可维护性/安全代码审计 → 评审报告。当用户说「评审代码/审查这段实现」时使用。
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- studio-arch-designSkill
- studio-discoverySkill
- studio-gate-checkSkill
- studio-project-scanSkill
- studio-setup-stackSkill
- studio-sprint-kickoffSkill
- studio-summarize-archSkill
- usds-cost-reportSkill
- usds-debt-logSkill
- usds-micro-adrSkill
- usds-mode-switchSkill
- usds-onboardSkill
- usds-startSkill
- usds-updateSkill
- vibe-branchSkill
- vibe-checkSkill
- vibe-explain-backSkill
- vibe-graduateSkill
- vibe-prototypeSkill
- vibe-startSkill
- vibe-taste-reviewSkill
The file
Files
/studio-review — 技术评审
代理: technical-architect | 产出: docs/reviews/REVIEW-xxx.md
工作流
- 提问: 询问开发者核心问题是什么，是否有未处理的"脏路"。
- 发现: 列出 2-3 个关键发现（性能瓶颈 / 代码异味 / ADR 违反）+ 改进建议。
- 安全评审: 涉及认证、数据库、外部 API、文件操作时，必须调用
security-engineer：- 检查工具参数是否可被模型/用户输入控制（AI 代理执行风险）
- OWASP Top 10 快速扫描（注入 / 越权 / 硬编码密钥）
- 输出：通过 或 需修复（附文件+行号）
security-engineer标记"需修复"则自动列为必须修复项
- 决策: 用
ask_user列出改进点，让用户选择哪些必须本次修复。 - 草案: 展示重构代码片段，用
ask_user提供 [执行重构] [放弃修改]。 - 批准: 用户点击后执行修改，写入评审摘要到
docs/reviews/。
成功门控
- 代码符合
TECHNICAL-PREFERENCES.md - 无明显 N+1 或内存泄漏，逻辑符合 ADR 契约
- 生成评审摘要至
docs/reviews/
输出约束 [强制]
用户批准后，向主上下文只输出：
评审完成 — [✅ 通过 / ⚠️ 通过（含建议）/ ❌ 需返工]
- 报告：docs/reviews/REVIEW-[xxx].md
- 发现：[X] 条（已修复 [Y] / 遗留 [Z]）| 安全：[通过/需修复/未触发]
- 下一步：[/studio-gate-check 或 返工说明]协作路径
- 不通过 → 任务回退
In Progress - 通过 → 交
qa-lead执行/studio-gate-check
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.