Dev Docs logo

Dev Docs

Organization
devcodex-labs
dev-docs

文档开发子类型规范 — 技术文档/API文档/README 编写规范

Overview

Publisherdevcodex-labs
Repositorydevcodex
Skill namedev-docs
Stars
433
Forks
44
Bundled files
1
LicenseAGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by devcodex-labs on GitHub. Read the source before you install it.

Installation

Install the Dev Docs AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/devcodex-labs/devcodex/tree/main/content/skills/dev-docs
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/devcodex-labs/devcodex.git /tmp/devcodex
mkdir -p .claude/skills
cp -r /tmp/devcodex/content/skills/dev-docs .claude/skills/dev-docs
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dev Docs in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dev Docs on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dev Docs is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Dev Docs Skill

触发条件

用户要求编写/更新技术类文档:API/契约说明、架构文档、开发指南、迁移实现说明、通用技术 Markdown 等。

⛔ 入口分流(DocsAudienceIntent,强制)
写文档任务由模型依据用户目的与预期读者判定 docsAudience + docsSurface;scripts/lib/docs-audience-intent.js 只校验结构化决策,不依据关键词选择:

  • public-user(用户使用站 / README / 用户手册 / 用户向 changelog·operations·reference)→ 必须 handoff user-manual-authoring(+ 条件 readme-authoring),不得以本 Skill 为主写作入口。
  • maintainer-dev(维护者开发站 / contributing / 发版 runbook / ADR 站)→ 必须 handoff maintainer-docs-site-authoring。
  • ambiguous → 先补上下文,确实影响交付时再消歧;multi-audience → 按读者组织交付物,保留已确认任务范围。
  • 仅当受众已是技术读者且 surface 为契约/架构/通用技术文时,本 Skill 才作为主入口(light-api / frontend-api / general-doc)。

豁免项

  • 豁免 plan-review(业务文档内容任务不需要实施计划审查)
  • 豁免 impact-review(文档变更不涉及代码影响评估)
  • 豁免 CP3(仅 dev.docs 子类型写业务项目文档时);必须记录 CP3: N/A(docs 子类型豁免)
  • ⚠️ 控制面 / Skill / 规范包变更(如本仓库改 skills)走 dev.default,不享受本豁免
  • CP2 简化为文档大纲确认(业务文档内容任务;控制面任务仍完整技术方案)

目标文档分流

当任务属于“契约驱动型文档”且已锁定为技术契约(非用户站 narrative)时,优先先冻结目标文档,再让后续实现或联动产物围绕它落地。
用户侧 reference 可由 user-manual-authoring 编排 本 Skill 的 light-api,但 Owner 仍是用户站。

何时视为契约驱动型文档

满足任一条件即可:

  1. 文档本身定义了对外 API 契约
  2. 文档面向前端联调、页面调用或外部调用方
  3. 若不先冻结文档,后续实现容易产生接口或交互漂移

三种目标文档模式

模式适用场景产物形态
light-api普通接口说明、调用方说明、轻量联调文档Markdown 轻量 API 文档
frontend-api前端联调、页面/模块接口说明、字段映射说明Markdown 前端接口文档
general-doc架构文档、开发指南、迁移指南、治理说明、运行手册Markdown 通用文档

README / 用户站 / 维护者站 handoff(强制)

目标handoff
用户站、用户手册、README、quick start、接入手册、公开能力页user-manual-authoring(+ 条件 readme-authoring)
维护者开发站、CONTRIBUTING 站区、发版 runbook 主叙事maintainer-docs-site-authoring
light-api / frontend-api / 架构 general-doc(技术读者)本 Skill 主入口

README / 最终用户使用文档专项仍由 user-manual-authoring + readme-authoring 承接(默认受众=使用者;开发/贡献后置),README 专项写作分支完成后由 audit-readme / audit-user-manual 复审。

文档质量标准

共享门禁:user-manual / docs-ia-readability / docs-semantics-examples / expert-output-quality 等完整 Gate 字段与探针以 ../spec-governance/gate-registry.json 与 Owner Skill(优先 user-manual-authoring、audit-user-manual、expert-output-quality)为准;本 Skill 只保留 dev-docs 差分(契约文档、结构/示例基线、技术文档同步)。

维度要求
结构完整必含:目的/使用者/快速开始/详细说明/示例
示例可执行代码示例经过验证,可直接运行
版本同步文档中的 API/配置项与代码实现一致
链接有效内部/外部链接均可访问
导航可读长篇独立 Markdown 默认包含 ## 目录导航;自动 outline/侧栏已覆盖、短跳转页或等价导航时可 N/A + skipReason,并做重复导航检查
契约/公开面(差分)契约驱动型或公开模块文档:区分公开 API vs 内部实现;未发布能力只写 unreleased/草案/preview
用户手册类站点文档 / README / 用户使用文档 → 转入 user-manual-authoring(+ 条件 readme-authoring),不在此复制用户主路径 Gate 百科
专家产物 / 语义·示例真相命中时调用 expert-output-quality 与 registry docs-semantics-examples;记录 gateGroup / ownerSkill / skipReason
操作说明合同面向用户或维护者的步骤、命令、按钮、工具调用或最终回复必须补 OperationExplanationContractV1:operationId/userGoal/preconditions/input/stateEffect/resultShape/resultSource/failureSemantics/nextAction/evidence
消费链命令/配置/字段/路径/阅读顺序变更时同步 README / website / Profile / examples / nav / validate / 部署副本

API 文档规范

轻量 API 文档(light-api)

每个公开 API 至少包含:

  • 接口用途
  • 服务归属
  • 模块 / 资源域
  • base path
  • 方法 / 路径
  • 参数 / 请求体
  • 返回结构
  • 错误码(如适用)
  • 最小示例

前端接口文档(frontend-api)

在轻量 API 文档基础上,额外补充:

  • 页面 / 模块 / 组件入口
  • 调用触发场景
  • 登录态 / 鉴权 / 前置依赖
  • 页面字段与接口字段的映射关系(如适用)

与 api-verification 的边界

  • dev-docs 负责阅读型目标文档
  • api-verification 负责归档级、可执行的接口验证双产物
  • 当用户只要求接口说明或前端联调文档时,不强制生成 .http + .cjs
  • 当需求明确进入接口验收、回归验证或正式归档时,再联动 api-verification

通用文档规范(general-doc)

当任务不属于契约驱动型接口文档,而是以下类型时,优先使用通用文档模板:

  • 架构文档
  • 开发指南
  • 迁移指南
  • 治理说明
  • 运行手册

文档同步守门(dev-docs 差分)

用户手册 / 文档站 / 示例语义 / 专家产物等共享门禁见 gate-registry.json 与 user-manual-authoring / audit-user-manual / expert-output-quality;此处不重复完整清单。

  • 写“已支持 / 已接入 / 未接入 / 已实现”前先核对代码、命令输出或当前消费者。
  • 正式文档不得混入运行时台账、审查报告或内部待办口吻;人工复核须留范围与证据。
  • 公开主路径只展示当前推荐写法;带全局副作用/兼容 shim 的旧路径不得冒充主路径。
  • DSL/parser/配置语法示例公开前须有最小执行探针,或标未发布。
  • docs/需求类任务推荐确认前检查行为可验证与范围冲突;结论变更须同步真相源状态与 sessions/SUMMARY。
  • 消费者同步失败或故意不同序必须写明原因;用户侧审查走 audit-user-manual 聚合入口。

产出物

  • 文档文件(按项目目录结构放置)
  • 契约驱动型文档优先使用 prompts/light-api-doc.prompt.md 统一骨架
  • 站点文档 / 用户使用文档 / 最终用户手册优先使用 user-manual-authoring
  • README / 主用户使用文档 / 最终用户使用文档中的 README 专项写作分支使用 user-manual-authoring + readme-authoring + prompts/project-readme.prompt.md;完成后由 audit-readme / audit-user-manual 承接用户侧复审
  • 用户侧文档 review / 项目文档审查 / 菜单导航审查优先使用 audit-user-manual
  • 非契约驱动型 Markdown 文档优先使用 prompts/general-doc.prompt.md
  • 若更新 README/CHANGELOG:执行 document-sync 确认同步状态

同步锚点(validate / consumer)

ExpertOutputQualityGate · ProductionRecommendedPathGate · fixture/mock/demo/legacy · DocumentationTranslationParityGuard

额外同步锚点

ChinesePrimaryExpressionGate · SidebarPageRoleMaterializationProbe · SidebarGroupSemanticModelProbe · BehaviorSemanticDocsParityGate · NegativeTranslationParityProbe · DocsExampleTruthSurfaceGate · CallbackExampleScopeProbe

FormalDocsDevCodexBoundary · CodeTruthRequirementGate · PackageNameAuthorityGate · PublicModuleDifferentiationGate · ProductRequirementTraceabilityGate · FlowchartNodeExplanationGate · DocsSiteVisualAcceptanceGate · PublicDocsReleasedVersionGate · UIConfirmedSourceConflictTraceGate · UserPerspectiveDocsGate · DocsConsumerSweep · 心智负担 · 维护者验收 SideEffectCompatibilityDocsGate · ExecutableExampleTruthProbeGate · RequirementPreConfirmGate · RequirementVerdictStateSyncGate · UserDocsImmediateComprehensionGate · UserDocsPrimarySurfaceGate · public docs site · requirement deliverable · UserFacingDeliveryChainGate · FinalUserManualFirstGate · GeneratedSiteGate · ManualTocDuplicationGate · UserPathContractSweep · UserManualProductizationGate · UserManualRenderedFlowAndRealWorkflowProbe · CompleteUserManualSiteMatrixGate · DocsThemeRuntimeVisualProbeGate · PublicUserDocsMaintainerBoundaryGate

自动生成 outline/侧栏已覆盖导航

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Dev Docs AI skill do?

文档开发子类型规范 — 技术文档/API文档/README 编写规范

Why use Dev Docs on TypingMind?

Because you install it once and use it with any model. Dev Docs is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dev Docs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devcodex-labs/devcodex/tree/main/content/skills/dev-docs. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dev Docs?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dev Docs?

As many as you like. As long as a model supports skills, you can use Dev Docs with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dev Docs AI skill free?

Yes. It is published on GitHub by devcodex-labs under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇