nesnilnehc/audit-docs
skills/audit-docs/SKILL.md
Audit documentation governance in read-only mode and produce a unified report with prioritized actions and explicit skill routing.
$ install --global
skillsauthnpx skillsauth add nesnilnehc/ai-cortex audit-docsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 29, 2026, 9:50 AM12.7s3 files scanned
SKILL.md
- name:
- audit-docs
- description:
- Unified governance report with compliance summary, risk map, and prioritized action plan
- description_zh:
- 以只读方式审计文档治理并输出统一报告，给出优先级行动与明确技能路由。
- tags:
- [documentation, governance, orchestration, workflow, ssot]
- version:
- 2.1.0
- license:
- MIT
- recommended_scope:
- project
- author:
- ai-cortex
- triggers:
- [docs governance, documentation governance, governance check, doc audit]
- type:
- document-artifact
- mode:
- full
- code_diff:
- null
- artifact_type:
- audit-docs
- path_pattern:
- docs/calibration/audit-docs.md
- lifecycle:
- living
技能：文档治理审计（Audit Docs）
目的 (Purpose)
用只读方式整合文档治理现状，输出统一审计报告与行动路线图，不执行结构改造或规范落盘。
核心目标（Core Objective）
首要目标：产出可直接执行的治理审计报告（问题、优先级、路由），而不是直接改仓库。
成功标准（必须全部满足）：
- ✅ 已完成模式对应的只读评估编排
- ✅ 已汇总核心 findings 与风险优先级
- ✅ 已输出明确的下一步技能路由
- ✅ 已生成单一统一报告
docs/calibration/audit-docs.md - ✅ 未执行整理、迁移、规范落盘等写入操作
验收测试：团队是否能仅凭报告决定“下一步调用哪些技能”，且无需担心被隐式改仓库？
范围边界（Scope Boundaries）
本技能负责：
- 按模式编排只读评估技能
- 聚合评分、风险和行动优先级
- 生成统一治理报告
本技能不负责：
- 建立或更新规范文件（
define-docs-norms） - 仓库整理或文件迁移（
tidy-repo） - 自动接受并应用任何修改
交接点：报告完成后，交由用户选择是否执行创建/整理类技能。
使用场景（Use Cases）
- 新项目治理基线检查
- 发布前治理审计
- PR 合并前文档门禁
- 周期性治理体检
行为（Behavior）
阶段 0：Norms Resolution（v2.1 新增）
按 specs/artifact-contract.md §8 Runtime Norms Resolution Protocol 的 §8.2 / §8.3 / §8.5 实现：读项目规范若声明了 audit-docs artifact_type 的 path_pattern，则使用项目值；否则 fall through 到技能默认（docs/calibration/audit-docs.md）。本技能为固定路径治理产出（orchestrator 角色），只用 path_pattern 覆盖机制；所依赖的子技能各自执行其 Stage 0。
模式定义
quick：仅assess-docs（核心评估）full：assess-docs+assess-docs-links+assess-docs-ssotcode-review：assess-docs+assess-docs-code-alignment
执行步骤
- 预检查：git 仓库可访问、docs 路径可读
- 规范检查：若缺失
docs/ARTIFACT_NORMS.md，仅记录风险并路由discover-docs-norms/define-docs-norms - 按模式执行只读评估技能并收集输出
- 汇总评分（结构、就绪、链接、SSOT、代码对齐）
- 生成
docs/calibration/audit-docs.md
输入与输出 (Input & Output)
输入
- 项目路径（默认 CWD）
- 模式：
quick|full|code-review - 可选
code-diff（用于code-review）
输出
docs/calibration/audit-docs.md- 引用的下游报告（按模式）：
docs/calibration/doc-assessment.mddocs/calibration/doc-link-health.mddocs/calibration/ssot-integrity-audit.mddocs/calibration/code-doc-alignment.md
限制（Restrictions）
硬边界（Hard Boundaries）
- 不执行
tidy-repo --apply或等价改写操作 - 不执行
define-docs-norms落盘 - 不自动接受规范推导结果
技能边界 (Skill Boundaries)
不要做这些（其他技能负责）：
- 规范发现：
discover-docs-norms - 规范落盘：
define-docs-norms - 仓库整理：
tidy-repo
自检（Self-Check）
- [ ] 模式对应编排正确
- [ ] 已汇总下游报告结论
- [ ] 已输出优先级路线图
- [ ] 未触发任何结构/规范写入
- [ ] 审计报告已落盘
示例（Examples）
示例 1：full 审计
- 执行：
assess-docs+assess-docs-links+assess-docs-ssot - 输出：
audit-docs.md+ 路由建议
示例 2：code-review 审计
- 执行：
assess-docs+assess-docs-code-alignment - 输出：聚焦 PR 的文档门禁建议
附录：输出合约 (Appendix: Output Contract)
本技能为 read-only 审计聚合器，产出统一报告：
| 元素 | 格式 | 必填字段 | 路径模式 |
| :--- | :--- | :--- | :--- |
| 报告主体 | Markdown | front-matter；章节：执行摘要 / 子审计聚合（assess-docs / assess-docs-links / assess-docs-ssot / assess-docs-code-alignment）/ 优先动作 / 技能路由 | docs/calibration/audit-docs.md |
| 优先动作 | 表格 | rank / issue / target_artifact / recommended_skill / rationale | 「优先动作」节 |
| 技能路由 | 列表项 | skill_id / invocation_hint / scope / expected_output_artifact | 「技能路由」节 |
| 机器可读块 | YAML fenced yaml audit_summary: | counts、top_actions[] 每项含 rank/skill/artifact | 报告末尾 |
Related Skills
nesnilnehc/scaffold-agent-tests
development
VerifiedTrustedCommunity
Generate an LLM agent test suite (golden cases, mock-LLM unit tests, evaluator harness) from an agent implementation and its agent-test contract. Use when an agent has no tests, or a contract exists but the test code is missing.
7SKILL.mdUpdated May 30, 2026
nesnilnehc/redeploy-local
development
VerifiedTrustedCommunity
After code changes, auto-detect the project's build system and local deployment method for a given directory, then build the project and restart its locally-deployed environment (Docker Compose / systemd / process manager). Never assumes — asks only when detection is ambiguous. Caches detected commands per project in .cortex/redeploy-local.yaml; re-invocations on the same project skip re-scanning until signal files change, the cache expires (30 days), or the skill version bumps.
7SKILL.mdUpdated May 22, 2026
nesnilnehc/publish-nats-message
tools
VerifiedTrustedCommunity
Publish a NATS message conforming to a cross-team contract, using NATS MCP tools. Authors the contract on first use if missing. Reads project-level cache (.cortex/nats.yaml) to avoid re-prompting basics across sessions.
7SKILL.mdUpdated May 22, 2026
nesnilnehc/consume-nats-message
tools
VerifiedTrustedCommunity
Drain pending NATS messages from a producer contract via NATS MCP tools (default batch / drain-style). Applies Tolerant Reader semantics and per-message ack/nak/term, returning aggregated stats. Reads project-level cache (.cortex/nats.yaml) to avoid re-prompting.
7SKILL.mdUpdated May 22, 2026