setup-ai-document-system
Sets up repo-local adapters and `docs/agents/` configuration so engineering skills share one issue tracker, triage vocabulary, domain layout, AI-native…
Skill by pop1414
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/pop1414-setup-ai-document-system
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, testing, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/setup-ai-document-system
What's inside
- Skill name
setup-ai-document-system- Description
- Sets up repo-local adapters and `docs/agents/` configuration so engineering skills share one issue tracker, triage vocabulary, domain layout, AI-native document workflow, and optional BMad Level 3 extension. Run before first use of `to-prd`, `to-plan`, `to-spec`, `to-issues`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out`, or when those skills appear to be missing context about `docs/features`, labels, domain docs, BMad story cycle boundaries, or agent entry files such as `AGENTS.md` / `CLAUDE.md`.
- License
- MIT
- Instructions
- 182 lines in SKILL.md · view on GitHub
Files (9)
- SKILL.md
- bmad-integration.md
- document-system.md
- domain.md
- issue-tracker-github.md
- issue-tracker-gitlab.md
- issue-tracker-local.md
- level3-bmad-workflow.md
- triage-labels.md
SKILL.md (first lines)
# Setup AI Document System 搭建 engineering skills 依赖的每仓库配置。这个 skill 配置的是“项目内文档系统”,不是某个 agent 工具的固定入口。 - **Issue tracker** — issues 存放在哪里(默认 GitHub;也原生支持 `docs/features/<feature>/issues/` 本地 markdown) - **Triage labels** — 五个 canonical triage roles 使用的字符串 - **Domain docs** — `CONTEXT.md`、ADRs 和 feature docs 的位置,以及读取它们的消费规则 - **Document system** — `to-prd`、`to-plan`、`to-spec`、`to-issues`、`grill-with-docs` 如何组成同一条文档链 - **Agent adapter** — `AGENTS.md`、`CLAUDE.md` 或其他工具入口如何指向 `docs/agents/*.md` - **Optional BMad Level 3** — 复杂项目中如何把 BMad 作为展开、审计和执行层接入 AI-native 文档系统 这是 prompt-driven skill,不是确定性脚本。先探索,展示发现,和用户确认,然后再写入。 ## Process ### 1. Explore 查看当前 repo,理解起始状态。读取已有内容,不要假设: - `git remote -v` 和 `.git/config` — 这是 GitHub repo 吗?是哪一个? - repo 根目录常见 agent adapter 文件:`AGENTS.md`、`CLAUDE.md`、`.cursor/rules/`、`.github/copilot-instructions.md` 等。它们是否存在?是否已经指向 `docs/agents/*.md`? - repo 根目录的 `CONTEXT.md` 和 `CONTEXT-MAP.md` - `docs/adr/` 以及任何 `src/*/docs/adr/` 目录 - `docs/AI_DOCUMENT_SYSTEM.md` - `docs/BMAD_INTEGRATION.md` 和 `docs/LEVEL3_BMAD_WORKFLOW.md` - `docs/features/` 和 `docs/plans/` - `docs/agents/` — 这个 skill 之前是否已经输出过内容? - `_bmad-output/implementation-artifacts/sprint-status.yaml` 和 BMad story files — 是否已经启用 BMad story cycle? ### 2. Present findings and ask 总结现有什么、缺什么。然后带用户逐一完成五个决策:每次只展示一个 section,拿到用户回答后再进入下一个。不要一次性倾倒全部五个。 假设用户不知道这些术语是什么意思。每个 section 先用简短说明开头(它是什么、为什么这些 skills 需要它、选择不同选项会改变什么),然后展示选项和默认值。 **Section A — Issue tracker.** > Explainer: “issue tracker” 是这个 repo 存放执行任务的地方。`to-issues`、`triage`、`to-prd`、`to-plan`、`to-spec` 等 skills 会从中读取并写入;它们需要知道是调用外部 issue tracker CLI、在 `docs/features/<feature>/issues/` 下写 markdown 文件,还是遵循你描述的其他工作流。请选择你实际用来跟踪这个 repo 工作的位置。 默认姿态:这些 skills 是为 GitHub 设计的。如果 `git remote` 指向 GitHub,就推荐 GitHub。如果 `git remote` 指向 GitLab(`gitlab.com` 或 self-hosted host),就推荐 GitLab。否则(或用户偏好),提供: - **GitHub** — issues 存放在 repo 的 GitHub Issues 中(使用 `gh` CLI) - **GitLab** — issues 存放在 repo 的 GitLab Issues 中(使用 [`glab`](https://gitlab.com/gitlab-org/cli) CLI) - **Local markdown** — PRD、Spec 和 issues 作为文件存放在本 repo 的 `docs/features/<feature>/` 下(适合个人项目或没有 remote 的 repos) - **Other**(Jira、Linear 等)— 让用户用一段话描述工作流;skill 会把它记录为自由文本 **Section B — Triage label vocabulary.** > Explainer: `triage` skill 处理 incoming issue 时,会把它移过一个 state machine:需要评估、等待 reporter、已准备好给 AFK agent 接手、需要人工实现,或 won't fix。为此,它需要应用与你实际配置相匹配的 labels(或 issue tracker 中的等价物)。如果你的 repo 已经使用不同 label 名(例如 `bug:triage` 而不是 `needs-triage`),在这里映射它们,避免 skill 创建重复 labels。 五个 canonical roles: - `needs-triage` — maintainer needs to evaluate - `needs-info` — waiting on reporter - `ready-for-agent` — fully specified, AFK-ready (an agent can pick it up with no human context) - `ready-for-human` — needs human implementation - `wontfix` — will not be actioned 默认:每个 role 的字符串等于它的名称。询问用户是否想覆盖任何项。如果他们的 issue tracker 还没有现有 labels,默认值即可。 **Section C — Domain docs.** > Explainer: 一些 skills(`grill-with-docs`、`to-prd`、`to-plan`、`to-spec`、`to-issues`、`improve-codebase-architecture`、`diagnose`、`tdd`)会读取 `CONTEXT.md` 来学习项目的 domain language,读取 `docs/adr/` 来了解过去的架构决策,并读取 `docs/features/<feature>/` 来理解当前功能链路。它们需要知道 repo 是一个 global context,还是多个 contexts(例如 frontend/backend 分离的 monorepo),这样才能看对位置。 确认布局: - **Single-context** — repo 根目录一个 `CONTEXT.md` + `docs/adr/`。大多数 repos 是这样。 - **Multi-context** — 根目录 `CONTEXT-MAP.md` 指向每个 context 的 `CONTEXT.md` 文件(通常是 monorepo)。 **Section D — Project document system.** > Explainer: `to-prd`、`to-plan`、`to-spec`、`to-issues` 和 `grill-with-docs` 应共享同一条文档链。这样 PRD 不会变成 implementation spec,Plan 不会变成任务清单,Spec 不会丢失验证命令,Issue 也不会绕开 `docs/features/<feature>/SPEC.md`。 默认使用 AI-native Markdown 结构: - agent adapter(例如 `AGENTS.md`、`CLAUDE.md`、Cursor rules)只作为入口指针 - `CONTEXT.md` + `docs/adr/` 作为领域和架构基准 - `docs/features/<feature>/PRD.md` - `docs/plans/<plan>.md` 或 `docs/features/<feature>/PLAN.md`(可选) - `docs/features/<feature>/SPEC.md` - `docs/features/<feature>/issues/` **Section E — Optional BMad Level 3 extension.** > Explainer: BMad 可以作为复杂项目的展开、readiness、story cycle、review 和 retro 层。AI-native `docs/` 仍是长期真相源;BMad 输出进入 `_bmad-output/`,只有晋升到 `docs/` 后才成为正式约束。启用 BMad story cycle 时,BMad stories 是执行队列,local issues 只记录 blocker、HITL、跨 story 风险、技术债、review follow-up 和 documentation fix。 确认是否启用 BMad extension: - **Disabled** — 仅使用 AI-native 文档链。 - **Enabled, AI-native issues remain execution queue** — BMad 只用于复杂性展开、readiness、review 或 retro;实现仍走 local issues。 - **Enabled, BMad story cycle owns execution queue** — `_bmad-output/implementation-artifacts/sprint-status.yaml` 和 story files 是执行编排层;issues 只是控制面板。 ### 3. Confirm and edit 向用户展示草稿: - 要写入或更新的 agent adapter 指针(选择规则见 step 4) - `docs/agents/issue-tracker.md`、`docs/agents/triage-labels.md`、`docs/agents/domain.md`、`docs/agents/document-system.md` 的内容 允许用户在写入前修改。 ### 4. Write **选择 agent adapter:** - 如果 repo 已有 `AGENTS.md`、`CLAUDE.md` 或其他 agent entry file,优先更新用户实际使用的入口。 - 如果多个入口同时存在,询问用户本次更新哪个,或是否都只加入同一段简短指针。 - 如果没有入口文件,询问用户是否创建;不要替用户选择默认文件名。 - 如果用户不想写任何 adapter 文件,只写 `docs/agents/*.md`,并在完成信息中说明后续 agent 需要手动读取这些文件。 如果所选文件已经有 `## Agent skills`、`## AI-native document system` 或类似 block,就原地更新其内容,而不是追加重复 block。不要覆盖周围 section 的用户编辑。 如果 block 中已有未列入模板的自定义子章节,保留它们;只更新本 skill 管理的子章节。 Adapter block: ```markdown ## AI-native document system
From pop1414/ai-native-doc-system, MIT.
More from pop1414/ai-native-doc-system
- 0.479score
git-guardrails-claude-code
pop1414
设置 Claude Code hooks,在危险 git commands(push, reset --hard, clean, branch -D 等)执行前阻止它们。Use when user wants to prevent destructive git operations, add git safety…
SkillCFreshness: CClaude Code +9 - 0.479score
diagnose
pop1414
面向棘手 bug、性能回退和 BMad story execution failures 的纪律化 diagnosis loop。Reproduce → minimise → hypothesise → instrument → fix → regression-test.
SkillCFreshness: CClaude Code +9 - 0.474score
caveman
pop1414
超压缩 communication mode。Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.
SkillCFreshness: CClaude Code +9 - 0.474score
to-plan
pop1414
Converts a feature PRD, spec, BMad epics/stories, release goal, or conversation context into an execution plan at `docs/plans/<plan>.md` or…
SkillCFreshness: CClaude Code +9 - 0.474score
to-prd
pop1414
将当前 conversation context 或 BMad PRD 输出转成 `docs/features/<feature>/PRD.md`,并接入 AI-native 文档链。Use when user wants to create a PRD, write product requirements…
SkillCFreshness: CClaude Code +9 - 0.474score
to-spec
pop1414
Converts a feature PRD, plan, BMad architecture/epics/stories output, or conversation context into `docs/features/<feature>/SPEC.md` with functional behavior…
SkillCFreshness: CClaude Code +9 - 0.474score
write-a-skill
pop1414
创建结构正确、支持 progressive disclosure 并带 bundled resources 的新 agent skills。Use when user wants to create, write, or build a new skill.
SkillCFreshness: CClaude Code +9 - 0.474score
grill-with-docs
pop1414
Grilling session that challenges a plan against the existing domain model, feature docs, and documented decisions, then updates CONTEXT.md and ADRs as…
SkillCFreshness: CClaude Code +9 - 0.474score
improve-codebase-architecture
pop1414
根据 CONTEXT.md 中的 domain language 和 docs/adr/ 中的 decisions,寻找 codebase 的 deepening opportunities。Use when the user wants to improve architecture, find…
SkillCFreshness: CClaude Code +9 - 0.474score
migrate-to-shoehorn
pop1414
将 test files 从 `as` type assertions 迁移到 @total-typescript/shoehorn。Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
SkillCFreshness: CClaude Code +9 - 0.474score
scaffold-exercises
pop1414
创建包含 sections、problems、solutions 和 explainers 的 exercise directory structures,并确保通过 linting。Use when user wants to scaffold exercises, create exercise stubs…
SkillCFreshness: CClaude Code +9 - 0.474score
setup-pre-commit
pop1414
在当前 repo 设置 Husky pre-commit hooks,集成 lint-staged (Prettier)、type checking 和 tests。Use when user wants to add pre-commit hooks, set up Husky, configure…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 3, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/pop1414/ai-native-doc-system
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from pop1414
- 0.479score
git-guardrails-claude-code
pop1414
设置 Claude Code hooks,在危险 git commands(push, reset --hard, clean, branch -D 等)执行前阻止它们。Use when user wants to prevent destructive git operations, add git safety…
SkillCFreshness: CClaude Code +9 - 0.479score
diagnose
pop1414
面向棘手 bug、性能回退和 BMad story execution failures 的纪律化 diagnosis loop。Reproduce → minimise → hypothesise → instrument → fix → regression-test.
SkillCFreshness: CClaude Code +9 - 0.474score
improve-codebase-architecture
pop1414
根据 CONTEXT.md 中的 domain language 和 docs/adr/ 中的 decisions,寻找 codebase 的 deepening opportunities。Use when the user wants to improve architecture, find…
SkillCFreshness: CClaude Code +9 - 0.474score
grill-with-docs
pop1414
Grilling session that challenges a plan against the existing domain model, feature docs, and documented decisions, then updates CONTEXT.md and ADRs as…
SkillCFreshness: CClaude Code +9 - 0.474score
caveman
pop1414
超压缩 communication mode。Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.
SkillCFreshness: CClaude Code +9 - 0.474score
migrate-to-shoehorn
pop1414
将 test files 从 `as` type assertions 迁移到 @total-typescript/shoehorn。Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
SkillCFreshness: CClaude Code +9
Cite this page
setup-ai-document-system skill. Agent Mart. https://agentmart.dev/skills/pop1414-setup-ai-document-system (last updated 2026-10-24)