docs-governance skill
A plugin helps agents maintain project documentation, decisions and verification evidence across development sessions
- 325 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Setup can edit documentation and agent instructions within the confirmed file scope.
- Separately enabled enforcement can add project hooks.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/docs-governanceDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Setup can edit documentation and agent instructions within the confirmed file scope.
- Separately enabled enforcement can add project hooks.
This is third-party code. Review the repository files before installing.
What it does
docs-governance supplies workflows for maintaining a long-running project’s documentation. An initial audit reads existing material and recommends a small next step. Setup then connects rules, navigation and current status to confirmed sources. Separate skills cover architecture, module contracts and change impact. After a task, the agent can locate affected documents and reconcile them with code while distinguishing planned behavior from implemented behavior.
Who it is for. For teams handing projects across sessions and agents who need decision rationale to survive alongside code.
Good fit when
- Avoid rediscovering project rules in every session
- Reconcile documentation after interface changes
- Audit document sources and duplicates
- Update handoff material after a task
Not a fit when
- You need a replacement issue tracker
- You expect automatic proof that prose is current
- You need mandatory hooks without project configuration
Example request
Run a read-only documentation audit. Show stale links and suggest one small correction.Limitations
Ordinary use keeps Markdown authoritative, with a rebuildable optional SQLite index that does not replace the project documents. Setup confirms the file scope first, so expose existing agreements before approving edits. Hooks and Git checks require explicit project configuration and are not installed implicitly. Scripts check structure and links, while semantic drift against code still needs the agent to examine the actual changes.
How to disable. Disable the plugin and remove only its added references from project instructions. Disable separately configured hooks in project configuration.
FAQ
How do I run the first audit?
In Claude Code, use `/governance-audit`. The initial output is a report.
Does setup create a commit?
No. Setup does not implicitly initialize Git, commit or push.
Can I keep my existing spec?
Yes. Existing PRD and specification files remain authoritative.
How do I audit with Codex?
Ask `$docs-governance` to audit the current project in read-only mode.
Must I create every suggested document?
No. Setup reuses existing sources and stays within the agreed scope.
Discussion
No questions or reviews yet.
Related
SkillsMulti-agent documentation generator: analyzes a repository and builds a README and AI assistant config files
Repo Docs Skills
repo-docs-skills
Living project documentation for agents: guides, concepts and reference from real runs next to the source
A marketplace of five Claude Code plugins for researchers: literature search, research design, project memory and manuscript work
A skill that draws validated architecture, workflow, sequence and data-flow diagrams as one interactive HTML file
A CLI and skill for an agent to publish reports and specs as HTML documents that a team comments on, with every version kept
A skill plus the docx program: the agent fills forms, edits tables and reviews Word files with tracked changes
README in short
The project separates durable rules, navigation and current status. Existing history conventions remain in force, and tasks stay in the project’s tracker.
README badge
Original SKILL.md
--- name: docs-governance description: >- 作为面向长期 AI 协作项目的知识、决策与验证治理总入口，把优秀 Agent 的一次性工作沉淀为可继承、可验证、可持续演进的项目集体能力；根据用户意图把任务路由到活文档、领域上下文与 ADR、变更影响、接口契约、测试资产、模块回归或闭环设计能力，并在大型变更中组织正确顺序。用于用户只说“文档治理”“项目治理”“帮我整理项目知识”“改完怎么收尾”而未指定具体 Skill，或需要跨多项治理能力时。English triggers: docs governance router, project knowledge governance, documentation workflow, governance workflow. --- # 文档治理总路由 ## 定位 > **把优秀 Agent 的一次性工作，沉淀为项目可继承、可验证、可持续演进的集体能力。** 本插件不是让 Agent 多写文档，而是治理长期 AI 协作中的项目知识、关键决策与验证证据：让后续 Agent 能恢复上下文、沿用已确认约束、复核结果，并把新的有效做法继续沉淀回项目。 先判断意图，再读取并执行对应 Skill。不要在本路由复制各 Skill 的方法论。 ## 单项路由 | 用户意图 | 路由到 | |---|---| | 新建核心模块、补齐模块文档或维护模块约定，无须点名 Skill | `module-governance`；讨论只读，普通 Bug／样式不启动建档 | | 审计核心模块知识入口覆盖 | `docs-audit`，仅报告；边界核对使用 `architecture-docs` | | 检查治理规则应放在入口、Skill、附件、脚本还是 Hook，识别散落的可复用工作流 | `agent-workflow-governance`，默认只读交付证据与建议 | | 采集项目健康证据、核对验证入口与 CI 衔接 | `living-docs-governance` 的“项目健康证据采集” | | 编写或优化 Skill、Agent 入口及 AI 读取的文档 | `writing-for-agents`；事实核对仍走审计流程 | | 规划、整理或只读审查文档目录、归属与读取入口 | `docs-structure` | | 生成、精简或审查 AGENTS.md / CLAUDE.md，明确项目规范和产品读取入口 | `agent-entrypoints` | | 产品文档管理员、来源登记、需求池／编号／版本、十阶段管理与产品审查 | `product-evolution`；Claude Code 可由 `product-docs-manager` 执行 | | 新项目、讨论后项目或已有项目首次配置产品文档包与 Agent 入口 | `living-docs-governance` 的“统一 setup”模式；Claude Code 使用 `/governance-setup`，`/governance-init` 是兼容别名 | | 本次改动后的文档同步、整理、收尾或交接 | `docs-maintenance` | | 从对话、文档变更与审计记录复盘文档管理经验 | `docs-retro` | | LOG 管理或复盘 | `living-docs-governance` | | 是否需要架构文档，生成、完善或审查模块分工、状态归属、依赖与核心流程 | `architecture-docs` | | 领域术语、`CONTEXT.md`、架构或数据库决策、ADR | `domain-modeling`（Matt 原文与本地适配）；`context-and-decisions` 仅兼容旧调用 | | 修改前判断牵连面、迁移、回滚、实施后对照 | `change-impact` | | 前后端或服务间接口 | `contract-first` | | 测试资产盘点、重要覆盖缺口或契约证据 | `test-collaboration` | | 修改后验证本模块及下游 | `module-regression` | | 文档散乱、导航、时效、重复主源与当前／历史区分的只读审计 | `docs-audit` | | 指定 spine/context/adr/artifacts/full 的兼容审计 | `living-docs-governance` 的审计模式 |