메뉴
在需求进入审查阶段后，对照已确认的 `spec.md`、`tasks.md`、`log.md` 与实际代码执行两阶段代码审查。用于用户要求做 review、核对实现是否符合 spec、进入 review 阶段、先查功能一致性再查代码质量、输出 Critical/Important/Minor 问题，或决定是否回退到 `spec-apply`/`spec-fix` 修正时使用。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
| name | spec-review |
| description | 在需求进入审查阶段后，对照已确认的 `spec.md`、`tasks.md`、`log.md` 与实际代码执行两阶段代码审查。用于用户要求做 review、核对实现是否符合 spec、进入 review 阶段、先查功能一致性再查代码质量、输出 Critical/Important/Minor 问题，或决定是否回退到 `spec-apply`/`spec-fix` 修正时使用。 |
在执行本 skill 时，同时遵守 ../../references/full-sdd-lifecycle.md 中 spec-review 阶段的协同规则。
skills/code-review-and-quality/SKILL.mdskills/security-and-hardening/SKILL.mdskills/performance-optimization/SKILL.md执行 AI 主导的两阶段审查，并把“是否通过”建立在代码证据上，而不是建立在报告、口头说明或实现者自述上。
执行前先确认以下条件成立：
spec.mdtasks.md、log.md，一并读取并用于理解上下文，但不要把它们当作事实来源若以下任一情况成立，停止审查并说明原因：
spec.md 缺失或仍存在关键待确认项按以下顺序执行，不要跳步，不要把两个阶段混在一起。
先收集最小必要上下文：
spec.md，必要时补读 tasks.md、log.mddocs/rules/README.md、docs/rules/project-context.mddocs/rules/code-style.md、docs/rules/ts.md、docs/rules/security.md执行时坚持下面约束：
log.md、提交说明或人工总结当成完成证据此阶段由 spec-reviewer 视角执行，只检查“做没做到”，不讨论风格优雅与否。
执行要求：
spec.md 中的功能点、流程、边界、非目标、验收条件拆成核对清单阶段一输出至少包含：
PASS 或 FAILspec-apply 或 spec-fix，并停止阶段二只有阶段一 PASS 后，才允许进入此阶段。此阶段由 code-quality-reviewer 视角执行。
检查重点：
docs/rules/ 中的长期规则与分层约束skills/code-review-and-quality/SKILL.md 的严重度和证据要求保持一致输出要求：
Critical、Important、Minor最终结论只能是以下三种之一：
spec-apply 或 spec-fixspec-fix 或定向修复不要在以下情况下宣称“审查通过”：
向用户汇报时至少包含：
PASS / FAILspec-apply、或进入 spec-fix