spec-code-review ​

用多 persona、confidence gate、合成去重和 safe_auto 修复做结构化代码评审。

ASCII 链路图 ​

text
Codebase -> Spec -> Plan -> Tasks -> Code -> Review -> Knowledge
                                                |
                                                v
                                                spec-code-review
                                                entry: spec-code-review
                                                type: workflow command

基本信息 ​

字段内容
Skillspec-code-review
类型workflow command
研发链路位置Review
当前入口spec-code-review
兼容别名/spec:code-review、$spec-code-review
Sourceskills/spec-code-review/SKILL.md
Governancesrc/cli/contracts/dual-host-governance/skills-governance.json（supported-host skills governance）

描述 ​

Structured code review for bugs, regressions, tests, and standards. Report-only by default; apply fixes only when the current user or upstream caller explicitly requests review-and-fix. mode:agent is always report-only.

Source 契约摘要 ​

该 source skill 未声明标准 Workflow Contract Summary 小节；本页以 frontmatter、supported-host governance 和维护者补充元数据为准。

何时使用 ​

  • 提交 PR 前。
  • 完成实现后需要质量门。
  • 需要围绕 diff 查逻辑、测试、安全、性能、契约和栈专项问题。

工作步骤 ​

  • 读取 diff、PR、文档、计划、task pack 或专项审查输入。
  • 按风险域选择 always-on 与 conditional reviewer personas。
  • 合并、去重和校准 findings，区分 safe_auto、gated_auto、manual 和 advisory。
  • 输出修复、残留风险或下一步处理建议。

输出 ​

  • review findings、safe_auto fixes、residual risks、audit report 或 release checklist。
  • 当 reviewer dispatch 不可用时，输出明确的 report-only fallback 覆盖说明。

Agent / Persona 列表 ​

  • 这是 persona agents 的主要使用层：correctness、testing、security、performance、scope、design 等按证据触发。
  • review workflow 自身负责任务边界、合成和最终判断。

本 skill 在 source 中挂载了 17 个 skill-local 专家资产（agent 0 · persona 17），路径为 skills/spec-code-review/references/{agents,personas}/。跨 skill 复用时，详情页按文件名去重。

名称类型摘要
spec-adversarial-reviewerpersonaYou are a chaos engineer who reads code by trying to break it.
spec-agent-native-reviewerpersonaYou review code to ensure agents are first-class citizens with the same capabilities as users -- not bolt-on features.
spec-api-contract-reviewerpersonaYou are an API design and contract stability expert who evaluates changes through the lens of every consumer that depends on the current interface.
spec-correctness-reviewerpersonaYou are a logic and behavioral correctness expert who reads code by mentally executing it -- tracing inputs through branches, tracking state across calls, an...
spec-data-migration-reviewerpersonaYou are a data migration and schema-change reviewer.
spec-deployment-verification-agentpersonaYou are a Deployment Verification Agent.
spec-frontend-quality-reviewerpersona你审查当前 diff 中用户可见的 Web 交互质量。关注用户能否理解状态、用键盘完成任务、在窄屏和不同视觉条件下继续操作，以及 presentation/data 边界是否让这些行为可维护。只报告当前 source/diff 可以支持的缺陷；不把 visual polish、browser field outc...
spec-julik-frontend-races-reviewerpersonaYou are Julik, a seasoned full-stack developer reviewing frontend code through the lens of timing, cleanup, and UI feel.
spec-learnings-researcherpersonaYou are a domain-agnostic institutional knowledge researcher.
spec-maintainability-reviewerpersonaYou are a structural code-quality reviewer.
spec-performance-reviewerpersonaYou are a runtime performance and scalability expert who reads code through the lens of "what happens when this runs 10,000 times" or "what happens when this...
spec-previous-comments-reviewerpersonaYou verify that prior review feedback on this PR has been addressed.
spec-project-standards-reviewerpersonaYou audit code changes against the project's own standards files -- CLAUDE.md, AGENTS.md, and any directory-scoped equivalents.
spec-reliability-reviewerpersonaYou are a production reliability and failure mode expert who reads code by asking "what happens when this dependency is down?" You think about partial failur...
spec-security-reviewerpersonaYou are an application security expert who thinks like an attacker looking for the one exploitable path through the code.
spec-swift-ios-reviewerpersonaYou are a senior iOS engineer who has shipped production SwiftUI and UIKit apps at scale.
spec-testing-reviewerpersonaYou are a test architecture and coverage expert who evaluates whether the tests in a diff actually prove the code works -- not just that they exist.

agent 详情页入口仍在 /reference/agents/*；完整按 skill 归属索引见 Agents 参考。persona 目前以 skill-local prompt 形式挂在所属 skill 下，不单独生成全局详情页。

边界 ​

  • report-only 模式不编辑。
  • safe_auto 之外的问题需要用户或下游 resolver 决策。

源码校准 ​

  • 本页由 website/scripts/generate-skill-detail-pages.js 从上游 source skill 生成。
  • 当前入口、兼容别名与宿主投递 metadata 来自 src/cli/contracts/dual-host-governance/skills-governance.json。
  • 当 source skill 或 governance contract 变化后，应重新运行 npm run reference:pages 并执行 npm run content:audit。