anything-to-notebooklm

Multi-source content → NotebookLM intelligent processor

Automatically fetch content from multiple sources, upload to NotebookLM, and generate podcasts, PPT, mind maps and other formats based on natural language instructions.

Supported content sources

1. WeChat official account articles

Automatically scrape WeChat official account article content via MCP server (bypassing anti-scraping)

2. Any web page link

Supports any publicly accessible web page (news, blogs, documents, etc.)

3. YouTube videos

Automatically extract subtitles and metadata from YouTube videos

4. Office documents

Word (DOCX) - Preserves tables and formatting
PowerPoint (PPTX) - Extracts slides and notes
Excel (XLSX) - Tabular data

5. E-books and documents

PDF - Full-text extraction
EPUB - E-book full-text extraction
Markdown (.md) - Native support

6. Images and scanned documents

Images (JPEG, PNG, GIF, WebP) - OCR text recognition
Scanned PDF documents - OCR text extraction

7. Audio files

Audio (WAV, MP3) - Speech-to-text

8. Structured data

CSV - Comma-separated data
JSON - JSON data
XML - XML documents

9. Compressed archives

ZIP - Automatically extract and process all supported files

10. Plain text

Text content entered or pasted directly

11. Search keywords

Search keywords via Web Search and aggregate information from multiple sources

Prerequisites

1. Install wexin-read-mcp

MCP server is installed at:~/.claude/skills/anything-to-notebooklm/wexin-read-mcp/

Configure MCP(needs to be manually added to the Claude configuration file):

macOS: Edit ~/.claude/config.json

{
  "primaryApiKey": "any",
  "mcpServers": {
    "weixin-reader": {
      "command": "python",
      "args": [
        "/Users/joe/.claude/skills/anything-to-notebooklm/wexin-read-mcp/src/server.py"
      ]
    }
  }
}

After configuration, Claude Code needs to be restarted.

2. notebooklm authentication

Authentication is required before first use:

notebooklm login
notebooklm list  # 验证认证成功

Trigger methods

WeChat official account articles

/anything-to-notebooklm [微信文章链接]
"Upload this WeChat article to NotebookLM"
"Generate a podcast from this WeChat article"

Web page links

"Make this web page into a podcast [URL]"
"Help me make this article into a PPT [URL]"
"Help me analyze this web page [URL]"

YouTube videos

"Make this YouTube video into a podcast [YouTube URL]"
"Help me generate a mind map from this video [YouTube URL]"

Local files

"Upload this PDF to NotebookLM /path/to/file.pdf"
"Generate a PPT from this Markdown file /path/to/file.md"
"Generate a podcast from this EPUB e-book /path/to/book.epub"
"Make a mind map from this Word document /path/to/doc.docx"
"Generate a Quiz from this PowerPoint /path/to/slides.pptx"
"Make a report from this scanned PDF /path/to/scan.pdf" (automatic OCR)

Search keywords

"Search for 'AI development trends' and generate a report"
"Search for materials about 'quantum computing' and make a podcast"

Mixed use

"Upload this article, this video and this PDF together and generate a report"

Natural Language → NotebookLM Feature Mapping

What the user says	Intent recognition	NotebookLM command
"Generate podcast" / "Make into audio" / "Convert to speech"	audio	`generate audio`
"Make a PPT" / "Generate slides" / "Make a presentation"	slide-deck	`generate slide-deck`
"Draw a mind map" / "Generate a mind map" / "Make a diagram"	mind-map	`generate mind-map`
"Generate Quiz" / "Make questions" / "Make a quiz"	quiz	`generate quiz`
"Make a video" / "Generate video"	video	`generate video`
"Generate a report" / "Write a summary" / "Organize into a document"	report	`generate report`
"Make an infographic" / "Visualize"	infographic	`generate infographic`
"Generate a data table" / "Make a table"	data-table	`generate data-table`
"Make flashcards" / "Generate memory cards"	flashcards	`generate flashcards`

If there is no explicit instruction, by default only upload without generating any content, and wait for the user's follow-up instructions.

Workflow

Step 1: Identify the content source type

Claude automatically identifies the input type:

Input feature	Identified as	Processing method
`https://mp.weixin.qq.com/s/`	WeChat Official Account	MCP tool fetching
`https://youtube.com/...` or `https://youtu.be/...`	YouTube	pass directly to NotebookLM
`https://` or `http://`	web page	pass directly to NotebookLM
`/path/to/file.pdf`	PDF file	markitdown convert to Markdown → TXT
`/path/to/file.epub`	EPUB e-book	markitdown convert to Markdown → TXT
`/path/to/file.docx`	Word document	markitdown convert to Markdown → TXT
`/path/to/file.pptx`	PowerPoint	markitdown convert to Markdown → TXT
`/path/to/file.xlsx`	Excel	markitdown convert to Markdown → TXT
`/path/to/file.md`	Markdown	upload directly
`/path/to/image.jpg`	Image (OCR)	markitdown OCR → TXT
`/path/to/audio.mp3`	audio	markitdown transcribe → TXT
`/path/to/file.zip`	ZIP archive	extract → markitdown batch conversion
Keyword (no URL, no path)	search query	WebSearch → summarize → TXT

Step 2: Obtain content

WeChat Official Account：

Use MCP tool read_weixin_article
Returns: title, author, publish_time, content
Save as TXT:/tmp/weixin_{title}_{timestamp}.txt

Web page/YouTube：

Directly use the URL to call notebooklm source add [URL]
NotebookLM automatically extracts content

Office documents/e-books/PDF：

Use markitdown to convert to Markdown
Command:markitdown /path/to/file.docx -o /tmp/converted.md
Save as TXT:/tmp/{filename}_converted_{timestamp}.txt

Local Markdown：

Upload directly:notebooklm source add /path/to/file.md

Image (OCR)：

markitdown automatically performs OCR text recognition
Extract EXIF metadata
Save as TXT

Audio file：

markitdown automatically transcribes speech to text
Extract audio metadata
Save as TXT

ZIP archive：

Automatically extract to a temporary directory
Traverse all supported files
Batch convert using markitdown
Merge into a single TXT or multiple Sources

Search keywords：

Use the WebSearch tool to search keywords
Summarize the first 3-5 results
Save as TXT:/tmp/search_{keyword}_{timestamp}.txt

Step 3: Upload to NotebookLM

Call notebooklm skill：

notebooklm create "{title}"  # 创建新笔记本
notebooklm source add /tmp/weixin_xxx.txt --wait  # 上传文件并等待处理完成

Waiting for processing to complete is important, otherwise subsequent generation will fail.

Step 5: Generate content based on intent (optional)

If the user specifies a processing intent, automatically call the corresponding command:

Intent	Command	Wait	Download
audio	`notebooklm generate audio`	`artifact wait`	`download audio ./output.mp3`
slide-deck	`notebooklm generate slide-deck`	`artifact wait`	`download slide-deck ./output.pdf`
mind-map	`notebooklm generate mind-map`	`artifact wait`	`download mind-map ./map.json`
quiz	`notebooklm generate quiz`	`artifact wait`	`download quiz ./quiz.md --format markdown`
video	`notebooklm generate video`	`artifact wait`	`download video ./output.mp4`
report	`notebooklm generate report`	`artifact wait`	`download report ./report.md`
infographic	`notebooklm generate infographic`	`artifact wait`	`download infographic ./infographic.png`
flashcards	`notebooklm generate flashcards`	`artifact wait`	`download flashcards ./cards.md --format markdown`

Generation workflow：

Initiate a generation request (returns task_id)
Wait for generation to complete (artifact wait <task_id>）
Download the generated file locally
Inform the user of the file path

Complete examples

Example 1: WeChat public account article → Podcast

User input：

把这篇文章生成播客 https://mp.weixin.qq.com/s/abc123xyz

Execution flow：

Recognize as a WeChat public account link
MCP tool fetches the article content
Create a TXT file
Upload to NotebookLM
Generate podcast (generate audio）
Download the podcast locally

Output：

✅ 微信文章已转换为播客！

📄 文章：深度学习的未来趋势
👤 作者：张三
📅 发布：2026-01-20

🎙️ 播客已生成：
📁 文件：/tmp/weixin_深度学习的未来趋势_podcast.mp3
⏱️ 时长：约 8 分钟
📊 大小：12.3 MB

Example 2: YouTube video → Mind map

User input：

这个视频帮我画个思维导图 https://www.youtube.com/watch?v=abc123

Execution flow：

Recognize as a YouTube link
Pass directly to NotebookLM (automatically extracts subtitles)
Generate mind map (generate mind-map）
Download the mind map

Output：

✅ YouTube 视频已转换为思维导图！

🎬 视频：Understanding Quantum Computing
⏱️ 时长：23 分钟

🗺️ 思维导图已生成：
📁 文件：/tmp/youtube_quantum_computing_mindmap.json
📊 节点数：45 个

Example 3: Search keywords → Report

User input：

搜索 'AI发展趋势 2026' 并生成报告

Execution flow：

Recognize as a search query
WebSearch searches the keywords
Summarize the first 5 results
Create a TXT file
Upload to NotebookLM
Generate report (generate report）

Output：

✅ 搜索结果已生成报告！

🔍 关键词：AI发展趋势 2026
📊 来源：5 篇文章

📄 报告已生成：
📁 文件：/tmp/search_AI发展趋势2026_report.md
📝 章节：7 个
📊 大小：15.2 KB

Example 4: Mixed multiple sources → PPT

User input：

把这篇文章、这个视频和这个PDF一起做成PPT：
- https://example.com/article
- https://youtube.com/watch?v=xyz
- /Users/joe/Documents/research.pdf

Execution flow：

Create a new Notebook
Add 3 Sources in sequence
Generate PPT based on all Sources

Output：

✅ 多源内容已整合为PPT！

📚 内容源：
  1. 网页文章：AI in 2026
  2. YouTube：Future of AI
  3. PDF：Research Notes (12 页)

📊 PPT 已生成：
📁 文件：/tmp/multi_source_slides.pdf
📄 页数：25 页
📦 大小：3.8 MB

Example 5: EPUB e-book → Podcast

User input：

把这本电子书做成播客 /Users/joe/Books/sapiens.epub

Execution flow：

Recognize as an EPUB file
markitdown converts to Markdown
Save as TXT
Upload to NotebookLM
Generate podcast

Output：

✅ EPUB 电子书已转换为播客！

📚 电子书：Sapiens: A Brief History of Humankind
📄 页数：约 450 页
📊 字数：约 15 万字

🎙️ 播客已生成：
📁 文件：/tmp/sapiens_podcast.mp3
⏱️ 时长：约 45 分钟（精华版）
📊 大小：48.2 MB

Example 6: Word document → Quiz

User input：

这个Markdown生成Quiz /Users/joe/notes/machine_learning.md

Execution flow：

Recognize as a local Markdown file
Upload directly to NotebookLM
Generate Quiz (generate quiz）

Output：

✅ Markdown 已转换为Quiz！

📄 文件：machine_learning.md
📊 大小：8.5 KB

📝 Quiz 已生成：
📁 文件：/tmp/machine_learning_quiz.md
❓ 题目：15 道（10选择 + 5简答）

Error handling

URL format error

❌ 错误：URL 格式不正确

必须是微信公众号文章链接：
https://mp.weixin.qq.com/s/xxx

你提供的链接：https://example.com

Article retrieval failed

❌ 错误：无法获取文章内容

可能原因：
1. 文章已被删除
2. 文章需要登录查看（暂不支持）
3. 网络连接问题
4. 微信反爬虫拦截（请稍后重试）

建议：
- 检查链接是否正确
- 等待 2-3 秒后重试
- 或手动复制文章内容

NotebookLM authentication failed

❌ 错误：NotebookLM 认证失败

请运行以下命令重新登录：
  notebooklm login

然后验证：
  notebooklm list

Generation task failed

❌ 错误：播客生成失败

可能原因：
1. 文章内容太短（< 100 字）
2. 文章内容太长（> 50万字）
3. NotebookLM 服务异常

建议：
- 检查文章长度是否适中
- 稍后重试
- 或尝试其他格式（如生成报告）

Advanced features

1. Multi-intent processing

Users can specify multiple processing tasks at once:

这篇文章帮我生成播客和PPT https://mp.weixin.qq.com/s/abc123

Skill will execute in sequence:

Generate podcast
Generate PPT

2. Custom Notebook

By default, a new Notebook is created for each article, but an existing Notebook can also be specified:

把这篇文章加到我的【AI研究】笔记本 https://mp.weixin.qq.com/s/abc123

Skill will:

Search for a Notebook named "AI研究"
Add the article as a new Source
Generate content based on all Sources

3. Custom generation instructions

Add specific requirements for the generation task:

这篇文章生成播客，要求：轻松幽默的风格，时长控制在5分钟

The Skill will pass the requirements to NotebookLM as instructions.

Notes

Rate limits：
- Interval between requests > 2 seconds to avoid being banned by WeChat
- NotebookLM generation tasks have concurrency limits (at most 3 at the same time)
Content length：
- WeChat articles are usually 1000-5000 characters, suitable for generating podcasts (3-8 minutes)
- Long articles over 10000 characters may require longer generation time
- Short articles under 500 characters may produce poor results
Copyright compliance：
- For personal study and research only
- Comply with WeChat Official Account copyright regulations
- Generated content must not be used for commercial purposes
Generation time：
- Podcast: 2-5 minutes
- Video: 3-8 minutes
- PPT: 1-3 minutes
- Mind map: 1-2 minutes
- Quiz/flashcards: 1-2 minutes
File cleanup：
- TXT source files are saved in /tmp/, and are automatically cleaned up after a system restart
- Generated files (MP3/PDF/MD, etc.) are saved by default in /tmp/
- You can specify a custom save path

Related Skills

notebooklm - NotebookLM core features
notebooklm-deep-analyzer - In-depth analysis of NotebookLM content
markitdown - Convert documents in other formats

Configure MCP (important)

⚠️ Must be configured before first use

Edit ~/.claude/config.json：

{
  "primaryApiKey": "any",
  "mcpServers": {
    "weixin-reader": {
      "command": "python",
      "args": [
        "/Users/joe/.claude/skills/anything-to-notebooklm/wexin-read-mcp/src/server.py"
      ]
    }
  }
}

Restart Claude Code after configuration!

Troubleshooting

1. MCP tool not found

# 测试 MCP 服务器
python ~/.claude/skills/anything-to-notebooklm/wexin-read-mcp/src/server.py

# 如果报错，检查依赖
cd ~/.claude/skills/anything-to-notebooklm/wexin-read-mcp
pip install -r requirements.txt
playwright install chromium

2. NotebookLM command failed

# 检查认证状态
notebooklm status

# 重新登录
notebooklm login

# 验证
notebooklm list

3. File permission issue

# 确保临时目录可写
chmod 755 /tmp

# 测试写入
touch /tmp/test.txt && rm /tmp/test.txt

4. Generation task stuck

# 检查任务状态
notebooklm artifact list

# 如果显示 "pending" 超过 10 分钟，取消重试
# （目前 CLI 不支持取消，需要在网页端操作）

Typical use cases

Scenario 1: Quick learning

我想学习这篇文章，帮我生成播客，上下班路上听
链接：https://mp.weixin.qq.com/s/abc123

→ Generate an 8-minute podcast and listen during your commute

Scenario 2: Share with the team

这篇文章不错，做成PPT分享给团队
https://mp.weixin.qq.com/s/abc123

→ Generate a 15-page PPT, ready for team sharing

Scenario 3: Review and reinforce

这篇技术文章帮我出题，想测试一下掌握程度
https://mp.weixin.qq.com/s/abc123

→ Generate 10 multiple-choice questions + 5 short-answer questions

Scenario 4: Visual understanding

这篇文章概念比较多，画个思维导图帮我理清结构
https://mp.weixin.qq.com/s/abc123

→ Generate a mind map for an at-a-glance view

Skill creation time：2026-01-25 Last updated：2026-01-25 Version：v1.0.0

About this skill

Supported content sources

1. WeChat official account articles

2. Any web page link

3. YouTube videos

4. Office documents

5. E-books and documents

6. Images and scanned documents

7. Audio files

8. Structured data

9. Compressed archives

10. Plain text

11. Search keywords

Prerequisites

1. Install wexin-read-mcp

2. notebooklm authentication

Trigger methods

WeChat official account articles

Web page links

YouTube videos

Local files

Search keywords

Mixed use

Natural Language → NotebookLM Feature Mapping

Workflow

Step 1: Identify the content source type

Step 2: Obtain content

Step 3: Upload to NotebookLM

Step 5: Generate content based on intent (optional)

Complete examples

Example 1: WeChat public account article → Podcast

Example 2: YouTube video → Mind map

Example 3: Search keywords → Report

Example 4: Mixed multiple sources → PPT

Example 5: EPUB e-book → Podcast

Example 6: Word document → Quiz

Error handling

URL format error

Article retrieval failed

NotebookLM authentication failed

Generation task failed

Advanced features

1. Multi-intent processing

2. Custom Notebook

3. Custom generation instructions

Notes

Related Skills

Configure MCP (important)

Troubleshooting

1. MCP tool not found

2. NotebookLM command failed

3. File permission issue

4. Generation task stuck

Typical use cases

Scenario 1: Quick learning

Scenario 2: Share with the team

Scenario 3: Review and reinforce

Scenario 4: Visual understanding