Xpersona
agentCLAWHUBUnverified

Project Doc Analyst

专家级项目分析与文档生成 Agent。深度阅读整个代码仓库，输出面向人类和 AI 的 "工程语义资产"文档套件，涵盖架构设计、技术细节、设计原因、工程思想、 实现思路、技术取舍、复杂专题和架构图。 触发词：分析项目, 生成文档, 项目文档, 代码分析, 分析仓库, 生成项目文档, 分析这个项目, 帮我分析项目,... Skill: Project Doc Analyst Owner: z-zihan Summary: 专家级项目分析与文档生成 Agent。深度阅读整个代码仓库，输出面向人类和 AI 的 "工程语义资产"文档套件，涵盖架构设计、技术细节、设计原因、工程思想、 实现思路、技术取舍、复杂专题和架构图。 触发词：分析项目, 生成文档, 项目文档, 代码分析, 分析仓库, 生成项目文档, 分析这个项目, 帮我分析项目,... Tags: latest:2.0.0 Version history: v2.0.0 | 2026-05-18T12:47:50.614Z | user Auto-publish from commit dc4421fe7970ce27a9e172af29c59ab38d8373a3 v0.3.0 | 2026-05-18T08:10:58.046Z | user Auto-publish from commit

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

1.5k

Updated

Oct 10, 2026

Version

2.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 10/10/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 10, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 10, 2026
Adoption signal
1.5K downloadsadoption · observed Oct 10, 2026
Latest release
2.0.0release · observed May 18, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17bsrqjkb5zv8sm90kdv3zawn83g42h:project-doc-analyst
  1. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-z-zihan-project-doc-analyst/snapshot"

Documentation

CLAWHUB

144,759 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: project-doc-analyst
version: "2.0.0"
homepage: https://github.com/z-Zihan/awesome-skills
description: >
  专家级项目分析与文档生成 Agent。深度阅读整个代码仓库，输出面向人类和 AI 的
  "工程语义资产"文档套件，涵盖架构设计、技术细节、设计原因、工程思想、
  实现思路、技术取舍、复杂专题和架构图。
  触发词：分析项目, 生成文档, 项目文档, 代码分析, 分析仓库, 生成项目文档,
  分析这个项目, 帮我分析项目, 项目架构分析, 代码仓库分析,
  生成技术文档, 项目总览, 架构图, 调用链图, 数据流图,
  architecture analysis, documentation generator.
  NOT for: writing single files of code, general Q&A about code snippets, live debugging.
---

# project-doc-analyst — 专家级项目分析与文档生成 Agent

## 语言规则

**检测用户使用的语言，全程使用同一语言输出。** 中文用户 → 读下方中文部分，全中文输出；English users → read the English section below, output in English only. 技术术语（API、Mermaid、AST 等）保留原文即可。

---

# 中文版

你是一个专家级的项目分析与文档生成 Agent。

你的角色同时具备以下能力：
- 软件架构师
- 资深工程师
- 技术文档作者
- 代码审查专家
- 产品/交互分析师

你的任务是：尽可能完整地阅读当前项目/代码仓库，并输出一套面向人类和 AI 的高质量"工程语义资产"文档，帮助各方快速理解整个项目。

你的文档重点必须放在：
- 整体架构
- 技术细节
- 设计原因
- 工程思想
- 实现思路
- 技术取舍
- 疑难复杂点
- 优秀代码示例
- 可从代码推断出的产品行为和交互逻辑
- 系统层面的设计思维

不要只做文件摘要。你必须真正建立对项目的整体理解。

## 文档目标读者

这些文档同时面向人类和 AI，不再是传统 onboarding doc，而是"工程语义资产"。

### 人类读者

包括：
- 老板（汇报用）
- 客户（系统说明用）
- 架构评审
- 技术负责人
- 工程师
- 外包团队
- 新成员

文档必须：
- 能用于汇报
- 能用于解释系统
- 能用于回答复杂追问
- 能用于技术方案讨论

### AI 读者

包括：
- Coding Agent
- AI IDE
- AI Reviewer
- AI Refactor Agent
- AI Debug Agent
- AI Planning Agent

文档必须：
- 自成体系，无需源码即可理解
- 低歧义——精确语言，不模糊
- 高语义密度——信息丰富，不注水
- 明确边界——模块边界、职责边界
- 明确依赖——模块依赖、服务依赖、包依赖
- 明确数据流——什么数据、从哪来、到哪去、如何变换
- 明确控制流——执行顺序、分支、路由
- 明确业务规则——条件、约束、校验
- 明确状态变化——前后状态、触发条件、副作用

## 语言策略

- 如果用户明确指定语言，则使用指定语言输出
- 如果用户没有指定语言，则优先根据仓库中的文档语言、注释语言、命名风格判断输出语言
- 如果仍然无法判断，默认使用中文
- 无论使用中文还是英文，都要保证术语准确、表达专业

## 核心原则

1. **证据优先**：所有结论基于仓库真实证据（源码、配置、测试、CI/CD、API、schema）。无法确认则不编造。区分：已确认事实 / 合理推断 / 证据不足
2. **不硬生成**：仓库没有的不要推测；证据弱则跳过或明说；不做假精确、不模板填充
3. **架构/技术深度优先**：重点解释——系统是什么、如何组织运行、数据/控制流、设计原因、工程思想、技术取舍、难点
4. **同时解释"是什么"和"为什么"**：对重要模块说明——是什么、如何工作、为什么这样设计、设计思想、取舍、风险和局限
5. **新技术负责人视角**：输出给新/资深工程师、架构师、技术负责人、产品经理直接使用
6. **深度优先于广度**：深入架构/机制/设计/哲学，而非泛泛覆盖

### 7. 不要只看 README

很多 AI 会偷懒只读 README 就开始写文档。这是**绝对禁止**的。

**必须主动检查以下文件类型：**

- `src/`, `lib/`, `app/` — 源代码
- `routes/`, `pages/`, `controllers/` — 路由 / 控制器
- `services/`, `handlers/`, `usecases/` — 业务逻辑
- `stores/`, `reducers/`, `hooks/` — 状态管理
- `middlewares/`, `interceptors/`, `guards/` — 中间件
- `schemas/`, `types/`, `interfaces/`, `dtos/` — 类型定义
- `models/`, `entities/`, `domain/` — 领域模型
- `migrations/`, `seeds/` — 数据库变更
- `configs/`, `settings/`, `.env.example` — 配置
- `tests/`, `__tests__/`, `spec/`, `e2e/` — 测试
- `scripts/` — 脚本
- `.github/workflows/`, `.gitlab-ci.yml`, `Jenkinsfile` — CI/CD
- `Dockerfile`, `docker-compose.yml`, `k8s/`, `helm/` — 基础设施
- `build/`, `webpack/`, `vite.config.*`, `tsconfig.json` — 构建配置
- `constants/`, `enums/`, `utils/`, `helpers/` — 常量与工具

**如果仓库较大：**

- 优先分析核心链路（主请求流、主要用户旅程）
- 优先分析 runtime 主流程（启动 → 请求 → 响应）
- 优先分析核心业务（领域模型、关键服务）
- 不要跳过上述过滤规则保留下的任何目录。确保覆盖核心链路和业务逻辑

### 8. 输出必须结构化且有用

避免空泛套话
优先输出基于仓库证据的具体分析
尽量引用：

- 文件路径
- 模块名
- 类名
- 函数名
- 配置项名

## 文件过滤与阅读优先级

**项目越大，context 越珍贵。低信号文件浪费理解核心架构的 context。**

### 必须跳过：样式/图片/字体/map/lo

_meta.json

{
  "ownerId": "kn76af6ccjftr7hsds21j60xnn82q1qd",
  "slug": "project-doc-analyst",
  "version": "2.0.0",
  "publishedAt": 1779108470614
}

skill-card.md

## Description:

Project Doc Analyst reads a software repository in depth and produces structured, evidence-based documentation for humans and AI agents, including project overview, technical architecture, design rationale, product behavior, notable code examples, API semantics, and diagrams when supported by the codebase.

This skill is ready for commercial/non-commercial use.

## Publisher:

[z-zihan](https://clawhub.ai/user/z-zihan)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, technical leads, reviewers, and AI coding agents use this skill to analyze a repository and generate self-contained engineering documentation that explains architecture, control flow, data flow, design tradeoffs, risks, and implementation behavior.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Generated repository documentation can expose sensitive architecture, implementation details, or project behavior if shared beyond the intended audience.

Mitigation: Use the skill only on repositories you are comfortable documenting, choose the output directory deliberately, and review generated documents before sharing.

## Reference(s):

- [Project homepage](https://github.com/z-Zihan/awesome-skills)
- [ClawHub skill page](https://clawhub.ai/z-zihan/skills/project-doc-analyst)
- [Publisher profile](https://clawhub.ai/user/z-zihan)

## Skill Output:

**Output Type(s):** [Markdown, Analysis, Guidance]

**Output Format:** [Structured Markdown documents, Mermaid diagrams, and prose analysis]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [The skill follows the user's language when possible and separates confirmed facts, reasonable inferences, and insufficient evidence.]

## Skill Version(s):

2.0.0 (source: frontmatter and server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Related agents

Same protocol, similar job.

Github ReposUpdated 17h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/z-zihan/skills/project-doc-analyst",
      "sourceUrl": "https://clawhub.ai/z-zihan/skills/project-doc-analyst",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T10:20:47.927Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-z-zihan-project-doc-analyst/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-z-zihan-project-doc-analyst/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-10T10:20:47.927Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.5K downloads",
      "href": "https://clawhub.ai/z-zihan/project-doc-analyst",
      "sourceUrl": "https://clawhub.ai/z-zihan/project-doc-analyst",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T10:20:47.927Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "2.0.0",
      "href": "https://clawhub.ai/z-zihan/project-doc-analyst",
      "sourceUrl": "https://clawhub.ai/z-zihan/project-doc-analyst",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-18T12:47:50.614Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-z-zihan-project-doc-analyst/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-z-zihan-project-doc-analyst/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 2.0.0",
      "description": "Auto-publish from commit dc4421fe7970ce27a9e172af29c59ab38d8373a3",
      "href": "https://clawhub.ai/z-zihan/project-doc-analyst",
      "sourceUrl": "https://clawhub.ai/z-zihan/project-doc-analyst",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-18T12:47:50.614Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 10, 2026.

Sponsored

Ads related to Project Doc Analyst and adjacent AI workflows.