What makes 微信读书 AI 阅读助手 notable?

966 downloads. Trust evidence available

How should 微信读书 AI 阅读助手 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

微信读书 AI 阅读助手

微信读书 AI 阅读助手 - 扫码登录、阅读进度跟踪、章节内容存档、AI 对话、标注笔记拉取 Skill: 微信读书 AI 阅读助手 Owner: colorlessboy Summary: 微信读书 AI 阅读助手 - 扫码登录、阅读进度跟踪、章节内容存档、AI 对话、标注笔记拉取 Tags: latest:1.2.0 Version history: v1.2.0 | 2026-05-13T13:52:59.375Z | user 新增标注/笔记自动拉取功能 (get-notes.js) v1.1.0 | 2026-05-13T01:49:16.161Z | user 改用 DOM 渲染文本提取代替 API 解码，解决章节内容乱码问题；不翻页不影响阅读进度 v1.0.0 | 2026-05-12T08:28:06.377Z | user 首次发布：扫码登录、章节解码、书架管理、阅读存档 Archive index: Archive v1.2.0: 11 files, 20906 bytes Files: packag

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

966

Updated

Oct 12, 2026

Version

1.2.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 966 downloads reported by the source. Last updated 10/12/2026.

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 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 966 downloadsadoption · observed Oct 12, 2026
Latest release: 1.2.0release · observed May 13, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.2.0release
新增标注/笔记自动拉取功能 (get-notes.js)
Observed May 13, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s17526h2nvhczex8emjnnxnkbs86j6dx:weread-dl

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
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-colorlessboy-weread-dl/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

21,014 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: weread-dl
description: 微信读书 AI 阅读助手 - 扫码登录、阅读进度跟踪、章节内容存档、AI 对话、标注笔记拉取
allowed-tools: Bash(node:*)
---

# 微信读书 AI 阅读助手 (weread-dl)

通过 Playwright 实现扫码登录 → 获取阅读进度 → 从浏览器渲染 DOM 提取章节全文 → 存档和 AI 对话 → 自动拉取标注和笔记。

## 文件结构

```
weread-dl/
├── SKILL.md                      # 本文档
├── scripts/
│   ├── login.js                  # 扫码登录
│   ├── read-chapter.js           # 打开书籍，获取章节/进度/笔记，保存到文件夹
│   └── get-notes.js              # 单独拉取标注+笔记（不读章节）
├── profile/
│   └── weread-cookies.json       # 持久化 cookies（自动生成）
└── books/
    └── <书名>/
        ├── metadata.json         # 书籍信息 + 目录 + 阅读进度 + 阅读历史 + 标注/笔记统计
        ├── chapters/
        │   └── chapter_text.md   # 渲染后的章节全文（从 DOM 提取）
        ├── screenshots/
        │   └── YYYY-MM-DD.png    # 每次阅读的页面截图
        ├── notes.md              # 标注（划线）+ 笔记全文
        └── chat.md               # 聊天记录
```

## 工作原理

### 章节提取
微信读书网页版使用 CSS 绝对定位打散字符进行版权保护。本工具通过 Playwright 打开书籍阅读页，从渲染后的 DOM 中获取所有 `position: absolute` 的文本元素，按视觉坐标（top/left）排序重组，重建完整章节文本。

**不涉及翻页操作**，不影响用户阅读进度。

### 阅读进度
从页面目录元素自动提取当前章节和百分比进度，记录在 metadata.json 中。

### 标注 & 笔记拉取
通过拦截微信读书网页版 API 请求，自动获取用户在该书上的全部划线（高亮）和笔记。每次 `read-chapter.js` 执行时会自动拉取，也可单独运行 `get-notes.js` 刷新。

## 使用

### 登录
```bash
cd ~/.openclaw/workspace/skills/weread-dl
NODE_PATH=/home/peng/.npm-global/lib/node_modules node scripts/login.js
```
生成二维码 → 微信扫一扫 → 自动保存 cookies

### 读一本书（自动拉取标注+笔记）
```bash
NODE_PATH=/home/peng/.npm-global/lib/node_modules node scripts/read-chapter.js <bookId>
```
可选 --chat 参数记录聊天：
```bash
node scripts/read-chapter.js <bookId> --chat "讨论内容"
```

### 单独拉取标注+笔记（不读章节）
```bash
node scripts/get-notes.js <bookId>
```

## AI 对话功能

1. 运行 `read-chapter.js` 打开指定书籍
2. 获取当前章节（第X章，进度Y%）和相关上下文
3. **自动拉取标注和笔记**，据此理解用户的阅读关注点
4. 基于目录结构、历史阅读记录、标注/笔记与用户讨论
5. 聊天记录自动保存到 books/<书名>/chat.md

## 注意事项
- ⚠️ 使用工具有封号风险，建议小号
- 加密章节数据需配合解密端使用

README.md

# 微信读书 AI 阅读助手 (weread-dl-skill)

基于 [Playwright](https://playwright.dev) 浏览器自动化的微信读书 AI 阅读助手。扫码登录后，可获取阅读进度、解码章节内容、存档聊天记录。

## 功能

- **扫码登录** — 通过微信扫码登录 weread.qq.com，cookies 持久化
- **书架列表** — 列出所有书籍及阅读进度
- **章节解码** — 拦截 `/web/book/chapter/e_X` API，解码 base64 HTML 章节内容
- **本地解码器** — `scripts/decode.js` 独立解码脚本，无需外部服务
- **阅读存档** — 每本书一个文件夹，保存 metadata / 章节加密数据 / 截图 / 聊天记录
- **标注笔记拉取** — 自动获取划线/高亮和笔记，保存到 notes.md，帮助理解阅读关注点
- **AI 对话** — 基于当前章节内容、标注和笔记与用户深度讨论书中观点

## 快速开始

### 环境要求

- Node.js >= 18
- Chromium / Chrome（Playwright 自动管理）

### 安装

```bash
git clone https://github.com/ColorlessBoy/weread-dl-skill.git
cd weread-dl-skill
export NODE_PATH=$(npm root -g)
```

### 1. 扫码登录

```bash
node scripts/login.js
```

脚本会打开 headless Chromium → 弹出微信二维码 → 截图二维码路径 → 等待扫码 → 保存 cookies。

### 2. 打开书籍（自动拉取标注+笔记）

```bash
node scripts/read-chapter.js <bookId>
```

bookId 从书架列表或阅读 URL（`/web/reader/{bookId}`）获取。

### 3. 单独拉取标注+笔记（不读章节）

```bash
node scripts/get-notes.js <bookId>
```

结果保存在 `books/<书名>/notes.md`。

### 3. 解码章节内容

```bash
node scripts/decode.js books/<书名>/chapters
```

解码结果保存在 `books/<书名>/chapters/` 下。

## 文件结构

```
weread-dl-skill/
├── SKILL.md                          # 完整文档
├── package.json
├── .gitignore
├── scripts/
│   ├── login.js                      # 扫码登录
│   ├── read-chapter.js               # 打开书籍 + API 拦截 + 存档 + 标注笔记
│   ├── get-notes.js                  # 单独拉取标注+笔记
│   ├── decode.js                     # 本地章节解码器
│   └── list-books.js                 # 书架列表
└── books/
    └── <书名>/
        ├── metadata.json             # 书籍信息 + 目录 + 阅读进度 + 标注/笔记统计
        ├── current-chapter.md        # 当前章节标记
        ├── chapters/
        │   ├── chapter_e0.enc        # 加密章节数据
        │   ├── chapter_e1.enc
        │   ├── chapter_e2.enc        # CSS 样式
        │   ├── chapter_e3.enc
        │   └── toc.json              # 目录结构数据
        ├── screenshots/
        │   └── YYYY-MM-DD.png        # 阅读页面截图
        ├── notes.md                  # 标注（划线）+ 笔记全文
        └── chat.md                   # 聊天记录
```

## 解码算法

微信读书章节 API 数据格式并非 AES 加密，而是：

```
32位hex校验码 + 1位分隔符 + base64(UTF-8 HTML)
```

| 端点 | 内容 |
|------|------|
| `chapter_e_0` | 完整 HTML 文档（含 `<body>`） |
| `chapter_e_1` | 续文片段 |
| `chapter_e_3` | 续文片段 |
| `chapter_e_2` | CSS 样式 |

解码即：去除前 33 个字符 → base64 decode → UTF-8 解码。
运行 `node scripts/decode.js books/<书名>/chapters` 即可获取纯文本。

## 技术实现

- **浏览器**: Playwright + Chromium (headless)
- **登录**: 微信开放平台 OAuth 扫码
- **数据**: API 响应拦截 + base64 解码
- **持久化**: cookies 保存到 `profile/weread-cookies.json`

## 注意事项

- ⚠️ 使用第三方工具有封号风险，建议使用小号
- VIP 专享内容需要 VIP 权益才能缓存导出

## License

MIT

_meta.json

{
  "ownerId": "kn78nw4yqmetaz10dvak20pwch86k3d8",
  "slug": "weread-dl",
  "version": "1.2.0",
  "publishedAt": 1778680379375
}

skill-card.md

## Description:

微信读书 AI 阅读助手支持扫码登录、阅读进度跟踪、章节内容存档、AI 对话以及标注和笔记拉取。

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

## Publisher:

[colorlessboy](https://clawhub.ai/user/colorlessboy)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to automate WeRead login, list books, extract reading progress, archive chapter content, screenshots, notes, and chat records, and discuss current reading context with an AI assistant.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Reusable WeRead login cookies are stored locally and can grant account access if exposed.

Mitigation: Treat profile/weread-cookies.json like a password and avoid storing it in shared, synced, backed-up, or source-controlled workspaces.

Risk: The skill writes private reading exports, screenshots, notes, metadata, and chat records to local folders.

Mitigation: Keep books/, output/, screenshots, notes, metadata, and chat files private and review them before sharing or committing workspace contents.

Risk: QR-code download during login uses a shell command and was flagged by ClawScan as risky for higher-risk environments.

Mitigation: Review the login workflow before installation and replace QR download with a shell-free, host-validated implementation before higher-risk use.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/colorlessboy/skills/weread-dl)
- [Playwright documentation](https://playwright.dev)
- [WeRead web application](https://weread.qq.com)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown and command-oriented guidance; generated local artifacts can include JSON metadata, Markdown notes and chat logs, chapter files, and screenshots.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires Node.js, Playwright, a browser session, and local storage for cookies and private reading exports.]

## Skill Version(s):

1.2.0 (source: server release evidence)

## 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.

package-lock.json

{
  "name": "weread-dl-skill",
  "version": "1.0.0",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "weread-dl-skill",
      "version": "1.0.0",
      "license": "MIT",
      "dependencies": {
        "playwright": "^1.60.0"
      }
    },
    "node_modules/fsevents": {
      "version": "2.3.2",
      "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
      "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
      "hasInstallScript": true,
      "license": "MIT",
      "optional": true,
      "os": [
        "darwin"
      ],
      "engines": {
        "node": "^8.16.0 || ^10.6.0 || >=11.0.0"
      }
    },
    "node_modules/playwright": {
      "version": "1.60.0",
      "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.60.0.tgz",
      "integrity": "sha512-hheHdokM8cdqCb0lcE3s+zT4t4W+vvjpGxsZlDnikarzx8tSzMebh3UiFtgqwFwnTnjYQcsyMF8ei2mCO/tpeA==",
      "license": "Apache-2.0",
      "dependencies": {
        "playwright-core": "1.60.0"
      },
      "bin": {
        "playwright": "cli.js"
      },
      "engines": {
        "node": ">=18"
      },
      "optionalDependencies": {
        "fsevents": "2.3.2"
      }
    },
    "node_modules/playwright-core": {
      "version": "1.60.0",
      "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.60.0.tgz",
      "integrity": "sha512-9bW6zvX/m0lEbgTKJ6YppOKx8H3VOPBMOCFh2irXFOT4BbHgrx5hPjwJYLT40Lu+4qtD36qKc/Hn56StUW57IA==",
      "license": "Apache-2.0",
      "bin": {
        "playwright-core": "cli.js"
      },
      "engines": {
        "node": ">=18"
      }
    }
  }
}

Github ReposUpdated 3d 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