Build Project Docs

Community

zrt-ai-lab

build-project-docs

为项目构建分层式LLM友好文档体系。已有项目：扫描项目结构→架构分类→生成CLAUDE.md主索引→基础模块文档→业务模块API/数据模型/坑点文档→配置文档→git变更日志(含风险评估+回滚指南)→交叉验证。新项目：解析PRD→按脚手架规范设计架构→需求拆解为开发任务→融合代码规范生成CLAUDE.md开发指南→模块级API设计+数据模型+开发清单。当用户需要为项目创建AI编程文档、建立项目索引、梳理代码、新建项目规划、或提到llm.txt/CLAUDE.md时使用。

Overview

Publisher	zrt-ai-lab
Repository	`opencode-skills`
Skill name	`build-project-docs`
Stars	293
Forks	75
Bundled files	16
Links	Skill source Repository

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.
16 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by zrt-ai-lab on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/zrt-ai-lab/opencode-skills/tree/main/build-project-docs
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.

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/zrt-ai-lab/opencode-skills.git /tmp/opencode-skills
mkdir -p .claude/skills
cp -r /tmp/opencode-skills/build-project-docs .claude/skills/build-project-docs

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Build Project 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 Build Project 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 Build Project 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.

构建项目文档体系 (build-project-docs)

为项目创建完整的分层式 LLM 友好文档。支持两种模式：已有项目梳理文档、新项目从 PRD 驱动开发。

核心理念

LLM上下文窗口有限，文档必须分层：

.claude/CLAUDE.md = 主索引（项目地图，始终加载到上下文）
.claude/docs/{模块}/README.md = 模块级文档（按需加载）
.claude/docs/{模块}/*.md = 深度参考文档（API详情、数据模型、坑点）
.claude/docs/{模块}/CHANGELOG.md = 模块变更历史（调试和回滚参考）

模式检测

开始前先判断当前模式：

文档模式（已有项目，有源代码）

项目已有代码，需要梳理生成文档。

全新（无 .claude/docs/）→ 按顺序执行文档模式全部8个阶段。

增量（.claude/docs/ 已存在）→

先检查 .claude/docs/_progress.md——如果存在，说明上次会话中断，读取它确定：
- 阶段状态：哪些阶段已完成、哪个阶段进行中、哪些待执行
- 模块进度：阶段4/5/7中哪些模块已完成、哪些待处理
- 直接跳到第一个未完成的阶段继续，不重复已完成的阶段
如果 _progress.md 不存在，阅读现有 .claude/CLAUDE.md 和所有 .claude/docs/ 文件
运行阶段1获取当前状态
对比：新模块→加入，文件数变化→更新，缺失→创建，过期→更新
跳过已完成且准确的阶段
阶段7和阶段8 特殊处理：即使 _progress.md 标记为已完成，如果源码比文档更新（find -newer 检测），仍需重新运行

新项目模式（PRD驱动）

用户提到 PRD、需求文档、新项目规划、开发规范，且项目为空或新建 → 执行新项目模式5个阶段。

用户提到 PRD + 项目已有代码 → 先用文档模式梳理现有代码，再用新项目模式的阶段1-3做增量功能的需求拆解。

文档模式（8个阶段）

为已有项目梳理代码、生成分层文档。

阶段	内容	详细流程
1	项目探查	→ phase-1-explore.md
2	架构分类	→ phase-2-classify.md
3	编写 .claude/CLAUDE.md	→ phase-3-index.md
4	基础模块文档	→ phase-4-foundation.md
5	业务模块文档	→ phase-5-business.md
6	配置层文档	→ phase-6-config.md
7	变更日志	→ phase-7-changelog.md
8	交叉验证	→ phase-8-verify.md

执行前必须阅读对应阶段的 reference 文件。

新项目模式（5个阶段）

从 PRD 出发，生成架构设计、需求拆解、开发规范、模块文档。

阶段	内容	详细流程
1	PRD 解析	→ phase-1-prd.md
2	架构设计	→ phase-2-scaffold.md
3	需求拆解	→ phase-3-breakdown.md
4	生成 CLAUDE.md 开发指南	→ phase-4-guide.md
5	模块开发文档	→ phase-5-devdocs.md

开发规范参考：

Java 代码规范
Spring Boot 脚手架规范

执行前必须阅读对应阶段的 reference 文件。

关键规则

上下文管理（最重要！）

处理多模块时，禁止一次性处理所有模块。必须：

逐模块串行处理（从小到大）
每完成一个模块 → 更新 _progress.md → 不再引用该模块源码
处理 3+ 个大模块后 → 主动提示用户开新会话继续

进度追踪（`_progress.md`）

_progress.md 是全局进度文件，两种模式通用：

每完成一个阶段或一个模块 → 立即更新 _progress.md
新会话读取后可直接跳到断点继续
全部完成后删除

文档完整性

❌ 只写 README 不写 api 子文件就算"完成"
✅ 只要模块对外暴露了 API（Controller / @Tool / gRPC / Handler 等），就必须按业务域拆分 api-{域}.md
✅ 每个业务模块必须有 data-model.md + pitfalls.md（文档模式）或 data-model.md + dev-checklist.md（新项目模式）
✅ README 是索引，api-*.md 才是详情，README 中必须链接到所有子文件

文件大小

.claude/CLAUDE.md：150行以内
模块 README.md：200行以内
超过250行必须拆分子文件

核心原则

详见 principles.md

开始执行

根据模式检测结果，进入对应的阶段流程。每个阶段先展示结果给用户确认，再继续下一阶段。

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 Build Project Docs AI skill do?

Why use Build Project Docs on TypingMind?

Because you install it once and use it with any model. Build Project 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 Build Project Docs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zrt-ai-lab/opencode-skills/tree/main/build-project-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 Build Project 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 Build Project Docs?

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

Is the Build Project Docs AI skill free?

It is published on GitHub by zrt-ai-lab. Check the repository for licensing terms. 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

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Openclaw Debugging

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

Openclaw Live Updater

openclaw

OrganizationPopular

Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

构建项目文档体系 (build-project-docs)

核心理念

模式检测

文档模式（已有项目，有源代码）

新项目模式（PRD驱动）

文档模式（8个阶段）

新项目模式（5个阶段）

关键规则

上下文管理（最重要！）

进度追踪（_progress.md）

文档完整性

文件大小

核心原则

开始执行

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now

进度追踪（`_progress.md`）