assess-docs-ssot
技能:SSOT 完整性评估(Assess Docs SSOT)
目的 (Purpose)
发现文档之间的语义重叠与冲突,建立 canonical source 与修复动作,降低重复与不一致风险。
核心目标(Core Objective)
首要目标:输出可执行 SSOT 审计报告(Intent Registry + Conflict Matrix + Repair Plan)。
成功标准:
- ✅ 已完成意图建模(path_layer/artifact_type/ownership/granularity/section_intents)
- ✅ 已完成候选对筛选与冲突判定
- ✅ 已产出带优先级的冲突矩阵
- ✅ 每个 P0/P1/P2 冲突都有 canonical source 与 repair action
- ✅ 已写入
docs/calibration/ssot-integrity-audit.md
范围边界(Scope Boundaries)
本技能负责:SSOT 语义冲突审计。 本技能不负责:核心合规评分、链接图检查、代码文档对齐。
使用场景(Use Cases)
- full 治理审计
- 多目录文档重构前冲突排查
行为(Behavior)
阶段 0:Norms Resolution(v1.1 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 ssot-integrity-audit artifact_type 的 path_pattern,则使用项目值;否则 fall through 到技能默认(docs/calibration/ssot-integrity-audit.md)。本技能为固定路径治理产出,只用 path_pattern 覆盖机制。
阶段 1:SSOT 评估
- 意图建模(Intent Registry)
- 候选对筛选(意图重叠 + 粒度相近)
- 分层相似度分析(section/doc/entity)
- 冲突分级(P0/P1/P2/Info)
- 输出 canonical mapping 与修复清单
输入与输出 (Input & Output)
输入
- docs 范围
- 可选冲突阈值
- 可选重点层
输出
docs/calibration/ssot-integrity-audit.md
限制(Restrictions)
- 仅输出审计报告,不自动合并文档
- 不自动删除或移动文件
自检(Self-Check)
- Intent Registry 完整
- Conflict Matrix 完整
- 每个冲突含 canonical source + repair action
- 报告已落盘
示例(Examples)
- 两份 roadmap 文档里里程碑日期冲突 -> P0
附录:输出合约 (Appendix: Output Contract)
本技能产出 SSOT Integrity Audit:
| 元素 | 格式 | 必填字段 | 路径模式 |
|---|---|---|---|
| 报告主体 | Markdown | front-matter;章节:意图分类 / 冲突矩阵 / 权威源映射 / 修复建议 | docs/calibration/ssot-integrity-audit.md |
| 冲突矩阵 | 表格 | concept / canonical_source / divergent_sources / conflict_kind(duplicate / contradiction / drift) | 「冲突矩阵」节 |
| 权威源映射 | 表格 | concept / canonical_path / superseded_paths / handoff_skill | 「权威源映射」节 |
| 机器可读块 | YAML fenced yaml ssot_conflicts: |
concepts[] 每项含 name/canonical/divergents/severity | 报告末尾 |
More from nesnilnehc/ai-cortex
review-codebase
Architecture and design review for specified files/dirs/repo. Covers tech debt, patterns, quality. Diff-only review use review-diff. Complements review-code (orchestrated).
101review-vue
Review Vue 3 code for Composition API, reactivity, components, state (Pinia), routing, and performance. Framework-only atomic skill; output is a findings list.
88review-diff
Review only git diff for impact, regression, correctness, compatibility, and side effects. Scope-only atomic skill; output is a findings list for aggregation.
88review-java
Review Java code for language and runtime conventions: concurrency, exceptions, try-with-resources, API versioning, collections and Streams, NIO, and testability. Language-only atomic skill; output is a findings list.
80review-architecture
Review code for architecture: module and layer boundaries, dependency direction, single responsibility, cyclic dependencies, interface stability, and coupling. Cognitive-only atomic skill; output is a findings list.
78review-code
Orchestrate comprehensive code reviews by running scope, language, framework, library, and cognitive review skills in sequence, then aggregate findings into a unified report.
71