跳到正文
cccskills
免费在 GitHub 公开

code-review-risk

Review changes for bugs, regressions, missing tests, safety gaps, public/private leaks, and architecture drift before stylistic comments.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md1.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

code-review-risk

Review for risk first.

Procedure

  1. Read the diff and the relevant tests/docs for the behavior being changed.
  2. Prioritize correctness, regressions, missing validation, public/private leaks, and architecture boundary violations.
  3. Check whether changes conflict with Constitution, ADRs, decision map, naming, storage, surface registry, or host ownership.
  4. Ground each finding in a concrete file/line and describe the user-visible or operational impact.
  5. For each confirmed finding, apply the Problem-to-Guardrail loop: name the punctual problem, general class, existing rule that should have caught it, and close with guard/test añadido, ADR/regla añadida, or deuda explícita con expiry.
  6. Enforce the anti-loop rule: if closure adds 2 ciclos seguidos of ADRs, ledgers, manifests, guards, or baselines sin reducir blockers reales, stop and classify the closure as blocker directo, deuda lateral, or pendiente externo; no más gobernanza para arreglar exceso de gobernanza.
  7. Separate findings from open questions and low-risk polish.
  8. If no issues are found, state the remaining test gaps or residual risk.

Constraints

  • Do not lead with style nits when behavioral risk exists.
  • Do not assume generated or staged files are safe without inspection.
  • Do not recommend reverting unrelated user work.
  • Do not mark a confirmed problem simply fixed when the defect class can recur.
  • Do not recommend more governance after 2 ciclos seguidos sin reducir blockers reales; classify the remaining state directly.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Govern Clawix accessibility changes across screen reader behavior, keyboard navigation, focus order, contrast, reduced motion, text scaling, timed interactions, and agent-generated UI.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Review or update stable, canonical, any-human, PMF, and adoption claims using adoption/canonicity governance packets.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Turn a new or changed ADR into implemented behavior, routing docs, tests, and guardrails rather than leaving it as standalone prose.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Repair confirmed architecture drift in small batches while preserving public canon and avoiding broad opportunistic refactors.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Given an existing Style, generate a human-readable brand guidelines document covering colors, typography, voice, do/don't, imagery rules, and usage examples. Use when the user asks for a brand book, brand guide, or design system document.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Add or improve canonical data catalog collections, fields, aliases, relations, evidence tags, docs, and tests.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

查看 clawic 的全部技能

报告此技能的问题