Found another useful Skill — turn any content into podcasts, PPTs, mind maps, and more with just one sentence. Supports over 15 content sources, including WeChat official accounts, Xiaoyuzhou podcasts, YouTube videos, PDFs, e-books, and more. Also automatically detects and attempts to bypass paywalls, covering 300+ sites like The New York Times, The Wall Street Journal, and others.
GitHub: http://github.com/joeseesun/qiaomu-anything-to-notebooklm
Can be installed into any Agent tool that supports Skills, such as Claude Code, Codex, etc. Just say “turn this WeChat article into a podcast,” and it will automatically fetch the content and generate an .mp3 audio file.
If you often need to convert various content into different formats for learning or sharing, this Skill is worth trying.

joeseesun/qiaomu-anything-to-notebooklm

Source: https://github.com/joeseesun/qiaomu-anything-to-notebooklm

🎯 Anything → NotebookLM

Multi-source content smart processor: anything → podcast / PPT / mind map / Quiz

License: MIT (https://opensource.org/licenses/MIT)
Python 3.9+ (https://www.python.org/downloads/)
PRs Welcome (http://makeapullrequest.com)

GitHub stars (https://github.com/joeseesun/qiaomu-anything-to-notebooklm/stargazers)
GitHub forks (https://github.com/joeseesun/qiaomu-anything-to-notebooklm/network/members)
GitHub issues (https://github.com/joeseesun/qiaomu-anything-to-notebooklm/issues)
GitHub last commit (https://github.com/joeseesun/qiaomu-anything-to-notebooklm/commits/main)

Quick Start • Supported Formats • Usage Examples • Paywall Bypass • FAQ

✨ What is this?

A Claude Code Skill that uses natural language to turn any content into any format.

``
You: Turn this WeChat article into a podcast
AI : ✅ 8-minute podcast generated → podcast.mp3

You: Turn this paywalled article into a mind map
AI : ✅ Paywall automatically bypassed → mind map generated

You: Turn this podcast (Xiaoyuzhou) into a PPT
AI : ✅ Audio automatically transcribed → 25-page PPT generated
``

Core capability: Multi-source content acquisition (including paywall bypass) → upload to Google NotebookLM (https://notebooklm.google.com/) → AI generates the target format

🚀 Supported Content Sources (15+)

📱 Social & Media

• WeChat Official Accounts (MCP browser simulation)
• X/Twitter (tweets + long threads)
• YouTube videos (automatic subtitle extraction)
• Podcasts (Xiaoyuzhou / Ximalaya / Bilibili)

🌐 Web (including paywall bypass)

• 300+ paywalled sites (NYT/WSJ/FT/Economist…)
• Any public webpage (news, blogs, docs)
• Search keywords (automatic result aggregation)

📚 E-books & Documents

• PDF (including scanned document OCR)
• EPUB e-books
• Markdown (.md)
• Plain text (.txt)

📄 Office Documents

• Word (.docx)
• PowerPoint (.pptx)
• Excel (.xlsx)

🖼️ Others

• Images (JPEG/PNG, automatic OCR)
• Audio (WAV/MP3, automatic transcription)
• ZIP archives (batch processing)

🛡️ Paywall Bypass

Core feature: Automatically detects and bypasses paywalls on 300+ paywalled news sites.

Bypass Strategies (6-level cascade)

Level 1: Proxy service (r.jina.ai / defuddle.md) ↓ Fails Level 2: Site-specific Bot UA (Googlebot ~50 sites / Bingbot ~4 sites) ↓ Fails Level 3: General bypass (UA spoofing + X-Forwarded-For + Referer spoofing + AMP + EU IP) ↓ Fails Level 4: archive.today archive (CAPTCHA auto-detection) ↓ Fails Level 5: Google Cache ↓ Fails Level 6: agent-fetch local tool

Supported Paywalled Sites (partial)

Bypass Technologies (learned from Bypass Paywalls Clean (https://gitflic.ru/project/magnolia1234/bypass-paywalls-chrome-clean))

🎨 What Can Be Generated?

⚡ Quick Start

Prerequisites

• ✅ Python 3.9+
• ✅ Git (built-in on macOS/Linux)

That’s all! Other dependencies installed automatically with one command.

Installation (3 steps)

``bash

1. Clone into Claude skills directory

cd ~/.claude/skills/
git clone https://github.com/joeseesun/qiaomu-anything-to-notebooklm
cd qiaomu-anything-to-notebooklm

2. Install all dependencies with one command

./install.sh

3. Configure MCP as prompted, then restart Claude Code

``

First Use

``bash

NotebookLM authentication (one time only)

notebooklm login
notebooklm list # Verify success

Environment check (optional)

./check_env.py
``

Podcast Transcription Configuration (optional)

If you need transcription from Xiaoyuzhou / Ximalaya / Bilibili, configure Get Notes API:
bash export GETNOTE_API_KEY="your_api_key" export GETNOTE_CLIENT_ID="your_client_id"

💡 Usage Examples

Scenario 1: Paywalled article → Podcast

You: Turn this The Information article into a podcast https://www.theinformation.com/articles/... AI automatically: ✓ Detects paywall → bypasses with Googlebot UA ✓ Gets full article content ✓ Uploads to NotebookLM ✓ Generates podcast ✅ Result: /tmp/article_podcast.mp3

Scenario 2: Podcast (Xiaoyuzhou) → PPT

You: Turn this Xiaoyuzhou podcast into a PPT https://xiaoyuzhoufm.com/episode/... AI automatically: ✓ Get Notes API transcribes audio (2-5 minutes) ✓ Uploads transcript to NotebookLM ✓ Generates PPT ✅ Result: /tmp/podcast_slides.pdf (25 pages)

Scenario 3: E-book → Deep Analysis

You: Deeply analyze this book /Users/joe/Books/sapiens.epub AI automatically: ✓ Extracts full EPUB text ✓ Uploads to NotebookLM ✓ Generates 12 questions (3 progressive rounds: overview → deep dive → synthesis) ✓ Asks questions round by round, later rounds benefit from previous dialogue context ✓ Outputs structured JSON ✅ Result: /tmp/sapiens_analysis.json (12 Q&As, including core ideas, argument breakdown, contradiction analysis, cognitive change)

Scenario 4: X/Twitter Thread → Mind Map

You: Turn this tweet thread into a mind map https://x.com/user/status/123... AI automatically: ✓ Proxy cascade fetches tweet content (including full thread) ✓ Uploads to NotebookLM ✓ Generates mind map ✅ Result: /tmp/tweet_mindmap.json

Scenario 5: WeChat Article → Feishu Document (Deep Analysis)

You: Deeply analyze this WeChat article and write to Feishu https://mp.weixin.qq.com/s/abc123 AI automatically: ✓ MCP browser simulation fetches WeChat article ✓ Uploads to NotebookLM ✓ Generates 10 questions and recursively asks ✓ Formats into Feishu Markdown ✓ Automatically creates Feishu document ✅ Result: Feishu document created (with full Q&A)

🎯 Core Features

🧠 Smart Recognition

Automatically identifies input type, no manual specification needed.
https://mp.weixin.qq.com/s/xxx → WeChat Official Account https://xiaoyuzhoufm.com/episode/xxx → Xiaoyuzhou podcast https://x.com/user/status/xxx → X/Twitter https://youtube.com/watch?v=xxx → YouTube video /path/to/file.epub → EPUB e-book "Search 'AI trends'" → Search query

🛡️ Automatic Paywall Bypass

No manual handling needed, automatically detects and bypasses.
Detect paywall → Choose best strategy → Get full content 〈________Fully automatic________〈

🚀 Fully Automatic Processing

From acquisition to generation, all in one go.
Input → Fetch → Convert → Upload → Generate → Download 〈___________Fully automatic___________〈

🌐 Multi-source Integration

Supports mixing multiple content sources.
Paywalled article + YouTube video + EPUB + Podcast → Comprehensive report

📦 Technical Architecture

┌──────────────────────────────────────────┐ │ User natural language input │ │ "Turn this paywalled article into a │ │ podcast https://..." │ └──────────────────┬───────────────────────┘ │ ▼ ┌──────────────────────────────────────────┐ │ Claude Code Skill │ │ • Smart recognition of content source │ │ • Automatic tool invocation │ └──────────┬───────────────────────────────┘ │ ┌───────┴───────┐ │ │ ▼ ▼ ┌──────────┐ ┌──────────────┐ ┌──────────┐ ┌──────────┐ │ WeChat │ │ Paywall │ │ Podcast │ │ markitdown│ │ MCP │ │ Bypass │ │ Transcription│ │ File │ │ Browser │ │ 6-level │ │ Get Notes│ │ Conversion│ │ Simulation│ │ cascade │ │ API │ │ │ └─────┬────┘ └──────┬───────┘ └─────┬────┘ └─────┬────┘ │ │ │ │ └──────────────┴────────────────┴──────────────┘ │ ▼ ┌────────────────────────┐ │ NotebookLM API │ │ • Upload content source│ │ • AI generates target │ │ format │ └───────────┬────────────┘ │ ▼ ┌────────────────────────┐ │ Generated files │ │ .mp3 / .pdf / .json │ └────────────────────────┘

📂 Project Structure

qiaomu-anything-to-notebooklm/ ├── SKILL.md # Skill definition file ├── README.md # This file ├── main.py # Main entry: CLI smart processor ├── install.sh # One-click install script ├── check_env.py # 13-item environment check ├── package.sh # Packaging & sharing script ├── requirements.txt # Python dependencies ├── LICENSE # MIT ├── scripts/ │ ├── fetch_url.sh # URL fetching + paywall bypass (6-level cascade) │ └── get_podcast_transcript.py # Podcast/video transcription (Get Notes API) ├── wexin-read-mcp/ # WeChat Official Account MCP server │ └── src/ │ ├── server.py # MCP entry │ ├── scraper.py # Playwright browser simulation │ └── parser.py # HTML parsing └── feishu-read-mcp/ # Feishu document MCP server └── src/ ├── server.py # MCP entry ├── scraper.py # Feishu document fetching ├── parser.py # HTML → Markdown └── image_handler.py # Image processing

🔧 Advanced Usage

Deep Analysis Mode

``bash
python main.py https://example.com/article –deep-analysis

Automatically generates 12 questions (3 progressive rounds: overview → deep dive → synthesis), asks round by round, outputs structured JSON

``

Three-round Progressive Strategy:

NotebookLM maintains context within the same session; later questions automatically benefit from previous answers, forming a true “progressive” deep analysis.

Feishu Document Output

``bash
python main.py ./book.epub –deep-analysis –to-feishu

Automatically creates Feishu document after deep analysis

``

Batch Processing

``
Turn these articles into podcasts:

1. https://mp.weixin.qq.com/s/abc123
2. https://www.wsj.com/articles/…
3. /Users/joe/notes.md
   ``

🐛 Troubleshooting

MCP Tool Not Found

bash python ~/.claude/skills/qiaomu-anything-to-notebooklm/wexin-read-mcp/src/server.py cd ~/.claude/skills/qiaomu-anything-to-notebooklm/wexin-read-mcp pip install -r requirements.txt playwright install chromium

NotebookLM Authentication Failed

bash notebooklm login # Re-login notebooklm list # Verify

Paywall Bypass Failed

Some hard paywalled sites (e.g., The Information) do not send content server-side; an archive.today archive is needed. The script will automatically detect and prompt:
⚠️ archive.ph needs human verification. Browser opened automatically. Please complete verification and retry.

Environment Check

bash ./check_env.py # Comprehensive 13-item check ./install.sh # Reinstall

❓ FAQ

Q: Which languages are supported?
A: NotebookLM supports multiple languages; Chinese and English work best.

Q: Whose voice is used in podcasts?
A: Google AI voice synthesis. English has two AI hosts conversing; Chinese is single narration.

Q: Is paywall bypass legal?
A: This tool is for personal learning and research only. Its technical principle is based on search engine whitelisting (Googlebot/Bingbot); it does not crack any encryption. We recommend supporting quality news media by purchasing subscriptions.

Q: Content length limits?
A:

• Minimum: ~500 words
• Maximum: ~500,000 words
• Recommended: 1,000–10,000 words for best results

Q: Why is MCP needed?
A: WeChat Official Accounts have anti-crawling measures; MCP uses Playwright browser simulation to bypass. Other content sources (web, YouTube, PDF) do not require MCP.

Q: Which platforms does podcast transcription support?
A: Via Get Notes API: Xiaoyuzhou, Ximalaya, Bilibili videos. YouTube is handled directly by NotebookLM.

🙏 Acknowledgements

• Google NotebookLM (https://notebooklm.google.com/) – AI content generation
• Microsoft markitdown (https://github.com/microsoft/markitdown) – file conversion
• Bypass Paywalls Clean (https://gitflic.ru/project/magnolia1234/bypass-paywalls-chrome-clean) – paywall bypass strategy reference
• wexin-read-mcp (https://github.com/Bwkyd/wexin-read-mcp) – WeChat fetching
• notebooklm-py (https://github.com/teng-lin/notebooklm-py) – NotebookLM CLI

📄 License

MIT License – for personal learning and research only

If you find it useful, please give a ⭐ Star!
Made with ❤️ by Joe (https://github.com/joeseesun) · Twitter @vista8 (https://x.com/vista8) · WeChat Official Account「向阳乔木推荐看」