Updated 1w ago
by qshanx
docs-governance
Claude Code、Codex 与 ChatGPT 的文档驱动开发治理插件:防文档腐烂、维护上下文与决策、契约协作、测试与回归证据。
325 GitHub stars (325)
+195 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | +1 |
| Oct 6 | +3 |
| Oct 7 | 0 |
| Oct 8 | +2 |
| Oct 9 | +2 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | +10 |
| Oct 13 | +5 |
| Oct 14 | +8 |
| Oct 15 | +4 |
| Oct 16 | +11 |
| Oct 17 | +17 |
| Oct 18 | +2 |
| Oct 19 | +7 |
| Oct 20 | +12 |
| Oct 21 | +13 |
| Oct 22 | +5 |
| Oct 23 | −1 |
| Oct 24 | +9 |
| Oct 25 | +13 |
| Oct 26 | +9 |
| Oct 27 | +6 |
| Oct 28 | +12 |
| Oct 29 | +12 |
| Oct 30 | +18 |
| Oct 31 | +3 |
| Nov 1 | +11 |
| Nov 2 | +6 |
| Nov 3 | +2 |
| Nov 4 | −3 |
| Nov 5 | 0 |
- 19 skills (19 skills found in its SKILL.md files)
- 5 forks (5 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add qshanx/docs-governance
Asks which skills and agents to install. Just one: npx skills add qshanx/docs-governance --skill agent-entrypoints — add -g for every project.
Claude Code
git clone https://github.com/qshanx/docs-governancecp -r "docs-governance/skills/documentation/agent-entrypoints" ~/.claude/skills/
Copies the agent-entrypoints skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add qshanx/docs-governance
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
agent-entrypoints
创建、优化或审查项目及模块级 AGENTS.md / CLAUDE.md 等 Agent 入口文档时使用。根据项目事实精简规则、设置按需读取指针,支持模块两入口布局,并检查规则是否可执行、入口是否冲突。
skills/documentation/ on GitHub (opens in a new tab)agent-entrypoints/ SKILL.md -
agent-workflow-governance
用户要求整体检查项目治理规则的承载位置、精简常驻约束,或判断散落资料能否沉淀为 Skill、脚本或 Hook 时使用。只读识别主源、重复工作流与自动化缺口,给出证据和最小建议;单项文档维护直接使用已有专项 Skill。
skills/documentation/ on GitHub (opens in a new tab)agent-workflow-governance/ SKILL.md -
architecture-docs
判断项目是否需要架构文档,或生成、完善、审查 ARCHITECTURE.md 及已有架构说明。用于模块分工、状态归属、依赖关系或核心流程需要梳理时;依据项目证据记录结构,区分当前实现与已确认设计。
skills/documentation/ on GitHub (opens in a new tab)architecture-docs/ SKILL.md -
context-and-decisions
兼容旧 context-and-decisions 调用;领域术语与 ADR 的形成和修改统一转交随插件提供的 domain-modeling。
skills/documentation/ on GitHub (opens in a new tab)context-and-decisions/ SKILL.md -
docs-audit
只读审计现有项目文档,检查资料散乱、入口难找、断链、内容过时、重复主源及当前与历史混用。用于用户要求“审计文档”“检查文档是否过时”“看看文档哪里乱”,或阶段交接前检查文档体系时。
skills/documentation/ on GitHub (opens in a new tab)docs-audit/ SKILL.md -
docs-governance
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.
skills/documentation/ on GitHub (opens in a new tab)docs-governance/ SKILL.md -
docs-maintenance
在任务改变了文档承载的事实、发现正文冲突,或用户要求“同步文档”“收尾”“准备交接”时,按影响同步现有文档。
skills/documentation/ on GitHub (opens in a new tab)docs-maintenance/ SKILL.md -
docs-retro
从对话、文档变更及审计记录中复盘文档管理的问题和经验,减少资料难找、同步遗漏、重复维护和旧说明误用。用户要求“复盘文档管理”“为什么文档总漏更新”“总结文档治理经验”,或项目约定文档管理阶段复盘时使用;默认只读,输出有证据、适用条件和落点的改进建议。
skills/documentation/ on GitHub (opens in a new tab)docs-retro/ SKILL.md -
docs-structure
规划、整理或只读审查项目文档结构时使用。按职责聚合同类资料,明确当前主源、历史归档与按需读取入口。
skills/documentation/ on GitHub (opens in a new tab)docs-structure/ SKILL.md -
domain-modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
skills/documentation/ on GitHub (opens in a new tab)domain-modeling/ SKILL.md -
living-docs-governance
为新项目或尚未建立文档管理体系的已有项目,规划并建立文档入口、资料分工和维护方式。 用户要求“建立文档管理体系”“首次配置文档治理”时使用;暂保留只读文档审计、日志统计与归档。 单独优化 Agent 入口、日常同步或执行复盘,交给对应 Skill。
skills/documentation/ on GitHub (opens in a new tab)living-docs-governance/ SKILL.md -
module-governance
为新业务模块建档、补齐已有模块约定或维护模块边界变化。用户提出新建核心模块、补齐模块文档或调整模块职责时可按意图选择,无须点名 Skill;区分项目级与模块级 AGENTS,关联 CONTEXT、接口与决策,复用现有治理 Skills。普通 Bug、样式修改和纯审计不启动建档。
skills/documentation/ on GitHub (opens in a new tab)module-governance/ SKILL.md -
product-evolution
在 docs 下建立或维护产品管理入口,登记材料来源,统一需求编号、状态与修订,连接需求池、单需求、版本及验收复盘,并只读审查需求演变是否可追溯。用于产品文档管理员、PRD 版本混乱、产品进展难以理解、已确认决定未回写或需要产品文档审查时。English triggers: product documentation manager, product evolution, PRD governance, product baseline, product progress review.
skills/documentation/ on GitHub (opens in a new tab)product-evolution/ SKILL.md -
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
skills/documentation/ on GitHub (opens in a new tab)writing-for-agents/ SKILL.md -
change-impact
在改代码、数据、接口或治理文档前做有证据的影响分析,并在实施后把计划影响与实际 diff 对照;覆盖代码调用、数据/Schema、API 契约、测试、文档、ADR、部署、迁移和回滚。用于跨模块修改、高风险变更、数据库迁移、认证、公共接口、用户问“会影响哪里”“改之前检查一下”或实施后需要反思偏差时。English triggers: change impact analysis, blast radius, pre-change analysis, migration impact, rollback plan, post-implementation alignment.
skills/engineering/ on GitHub (opens in a new tab)change-impact/ SKILL.md -
contract-first
也适用于同一进程内存在明确消费者、提供者和公共接口且有漂移风险的业务模块;按实际边界验证公开签名与行为,无网络边界时不要求序列化证据。 分前端/后端(或多个服务)多端开发的项目,用 CONTRACT.md 指向的唯一机器契约,各端只照它各做各的,防止字段漂移导致集成时白屏。支持单会话多 agent 和多终端各自跑两种模式。只要项目有前后端/多服务、接口字段老对不上、各端联调卡住、某端改了字段忘了通知别人、或前端为渲染一个页面要调一堆接口拼数据,就用这个 skill,哪怕用户没明说"契约"。这套方法论的学名是消费者驱动契约(Consumer-Driven Contracts, CDC)/ 契约测试。中文触发:契约式开发、接口契约、前后端协作、多终端协作、防字段漂移、接口对不上、联调、API 契约、字段命名不一致、集成白屏、唯一真相源、契约测试、CDC。English triggers: c…
skills/engineering/ on GitHub (opens in a new tab)contract-first/ SKILL.md -
loop-design-check
把一个任务"写成"一个目标导向的 loop,并"检查"这个 loop 写得对不对、会不会跑飞——防止空转烧钱 / Goodhart 作弊 / 把错的干到底。两个动作:① 写 loop(先做减法判该不该建 → 定可判定目标 → 选回路类型 → 选骨架)② 体检 loop(过五个崩法 + 可判定性 + 边界 + 降级 + judge 独立 + 判断留人红线)。中文触发:写 loop、设计 loop、做一个 loop、把任务变 loop、agent 自动循环、检查 loop 对不对、loop 体检、loop 会不会跑飞、loop 空转烧钱、loop 作弊、目标导向循环、可判定目标、五个崩法、plan build judge、文档驱动派活、该不该建 loop。English triggers: design an agent loop, write a loop, check a loop, l…
skills/engineering/ on GitHub (opens in a new tab)loop-design-check/ SKILL.md -
module-regression
大项目模块间联动回归——一份 REGRESSION.md 回归台账登记"每个模块的下游消费者 + 可执行的回归验收命令",跨模块行为或依赖变化后按受影响范围回归,防"改一个模块悄悄弄坏其他模块"。判决靠退出码,不靠 AI 看着没问题。中文触发:模块回归、回归台账、回归审计、改A坏B、模块联动检查、影响面检查、模块牵连、下游验证、大项目改动检查。English triggers: module regression, regression ledger, impact regression audit, downstream verification.
skills/engineering/ on GitHub (opens in a new tab)module-regression/ SKILL.md -
test-collaboration
盘点并维护项目测试资产,按真实测试入口和重要覆盖变化维护 TESTS.md,必要时使用 TEST-ID 关联证据。用于测试资产盘点、测试缺口分析、单元/集成/契约/E2E/冒烟分类、Bug 回归保护、前后端或多服务基于同一契约的消费者/提供者测试、测试必要性判断、测试清单维护与交付前测试证据审查。中文触发:测试盘点、测试清单、测试资产、测试缺口、测试必要性、Bug 转测试、契约测试、前后端接口测试、测试治理。English triggers: test inventory, test catalog, test gap analysis, bug-to-test, contract testing, consumer contract, provider verification, test governance.
skills/engineering/ on GitHub (opens in a new tab)test-collaboration/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.