跳到正文
cccskills
免费在 GitHub 公开

audit-ambiguity-execute

Execute ambiguity audit document-by-document with implementer simulation, rubric scoring, cross-layer checks, remediation, and verdicting

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.md2.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Overview

Prerequisites

  1. .memory/wiki/specs/audits/audit-scope.md exists and includes ## Rubric Files

Step-by-Step

Step 0 — Scope and rubric load

  1. Read .memory/wiki/specs/audits/audit-scope.md.
  2. Load only rubric files listed in ## Rubric Files.
  3. Enforce freshness/session-independence gate for remediated runs.

Step 1 — Coverage counter initialization

  1. Extract complete document list and declared counts.
  2. Announce total N and initialize processed count to 0/N.

Step 2 — Per-document execution loop (mandatory 3a→3b→3c)

For every scoped document:

  1. Implementer simulation (read full doc, attempt stub, enumerate forced decisions).
  2. Rubric scoring with evidence and two-implementer assertions.
  3. Devil's-advocate pass and score downgrades when warranted.
  4. Immediately append findings to layer report.
  5. Increment processed counter and report X/N.

Step 3 — Coverage completeness gate

  1. Compare processed documents to scoped list.
  2. If any skipped docs exist, stop and process them before continuing.

Step 4 — Cross-layer consistency checks (when applicable)

Run mandatory checks for BE/FE/all scope:

  • IA→BE flow/endpoint coverage
  • BE→FE field mapping
  • IA→FE access control consistency
  • BE error code FE-state mapping

Append all failures as blocking report items.

Step 5 — Compile summary and remediate gaps

  1. Compile ambiguity percentage + prioritized punch list.
  2. Execute remediation flow automatically:
    • classify judgment vs mechanical gaps
    • request decisions where needed
    • apply approved fixes
  3. Persist ## Gaps Fixed metadata in audit-scope file.

Step 6 — Graph refresh, final verdict, and next-step recommendation

  1. If remediation changed scoped specs, call memory_compile before presenting the verdict so the graph reflects current source truth.
  2. Present report + verdict.
  3. If gaps found, require fresh rerun.
  4. If 0% ambiguity and fresh-run criteria pass, recommend layer-appropriate next pipeline command.

Completion Checklist

  • scope/rubrics loaded from persisted file
  • all documents processed through full loop
  • coverage completeness gate passed
  • cross-layer checks executed when applicable
  • summary compiled
  • remediation flow executed for gaps
  • gaps-fixed metadata persisted
  • spec graph refreshed when remediation changed scoped specs
  • verdict + constrained next step presented

Next Steps

  • gaps remain: rerun /audit-ambiguity [layer] in fresh invocation
  • no gaps and pass criteria met: advance to layer-specific next command

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

Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Structured methodology for adversarial thinking — generating attack scenarios, abuse cases, race conditions, and security edge cases against specs and implementations. Produces spec-level gap items, not code-level fixes.

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Orchestrate multiple Antigravity skills through guided workflows for SaaS MVP delivery, security audits, AI agent builds, and browser QA.

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Manage API versioning and evolution with URL/header/query strategies, deprecation workflows, breaking change classification, sunset headers, and consumer-driven contract testing. Use when designing versioning strategy, deprecating endpoints, or evolving API contracts.

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Analyzes codebase structure, data flow, module relationships, and key patterns to generate and maintain a living architecture document (ARCHITECTURE.md).

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

查看 RepairYourTech 的全部技能

报告此技能的问题