Content
# notebooklm-skill
> NotebookLM does the research, Claude writes the content.
The only tool that connects trending topic discovery → NotebookLM deep research → AI content creation → multi-platform publishing. Works as a Claude Code Skill or standalone MCP Server.
[](LICENSE)
**[繁體中文版 README](README.zh-TW.md)**
---
## Demo
| Language | YouTube | Slides |
|----------|---------|--------|
| English | [Watch](https://youtu.be/q1kj_OccaVE) | 6 pages, auto-generated |
| 繁體中文 | [Watch](https://youtu.be/6M3K4sxahdE) | 5 pages, auto-generated |
All slides, podcasts, and videos were generated by NotebookLM using this tool.
---
## What is this?
**notebooklm-skill** bridges NotebookLM's research capabilities with Claude's content generation. Feed it URLs, PDFs, or trending topics — it creates a NotebookLM notebook, runs deep research queries, and hands structured findings to Claude for polished output: articles, social posts, newsletters, podcasts, or any format you need.
Built on [notebooklm-py](https://pypi.org/project/notebooklm-py/) v0.3.4 — pure async Python, no OAuth setup needed.
```
Sources (URLs, PDFs) NotebookLM Claude Artifacts & Platforms
+-----------------+ +------------------+ +-----------------+ +----------------------+
| Web articles |--->| Create notebook |--->| Draft article |--->| Blog / CMS |
| Research papers | | Add sources | | Social posts | | Threads / X |
| YouTube videos | | Ask questions | | Newsletter | | Newsletter |
| Trending topics | | Extract insights | | Any format | | Any platform |
+-----------------+ +------------------+ +-----------------+ +----------------------+
Phase 1 Phase 2 Phase 3 Phase 4
|
v
+------------------+
| Generate artifacts|
| Audio (podcast) |
| Video |
| Slides |
| Report |
| Quiz |
| Flashcards |
| Mind map |
| Infographic |
| Data table |
| Study guide |
+------------------+
Phase 2b
```
## Quick Start
```bash
# 1. Install
git clone https://github.com/claude-world/notebooklm-skill.git
cd notebooklm-skill
pip install -r requirements.txt # installs notebooklm-py v0.3.4
# 2. Authenticate with Google (one-time, opens browser)
python3 -m notebooklm login
# -> Opens Chromium, sign in to Google
# -> Session saved to ~/.notebooklm/storage_state.json
# -> All subsequent calls use pure HTTP (no browser needed)
# 3. Create your first notebook
python scripts/notebooklm_client.py create \
--title "My Research" \
--sources https://example.com/article
# 4. Ask research questions
python scripts/notebooklm_client.py ask \
--notebook "My Research" \
--query "What are the key findings?"
# 5. Generate a podcast
python scripts/notebooklm_client.py podcast \
--notebook "My Research" \
--lang en \
--output podcast.m4a
# 6. Verify auth status
python scripts/auth_helper.py verify
```
See [docs/SETUP.md](docs/SETUP.md) for the full setup guide.
## Authentication
notebooklm-py uses browser-based Google login (no OAuth Client ID needed):
| Step | Command | What happens |
|------|---------|-------------|
| **Login** | `python3 -m notebooklm login` | Opens Chromium, user logs into Google |
| **Session storage** | Automatic | Saved to `~/.notebooklm/storage_state.json` |
| **Subsequent use** | `NotebookLMClient.from_storage()` | Reads saved session, pure HTTP calls |
| **Verify** | `python scripts/auth_helper.py verify` | Loads client + calls `notebooks.list()` |
| **Clear** | `python scripts/auth_helper.py clear` | Removes `~/.notebooklm/` directory |
Session typically lasts weeks. Re-run `login` if you get authentication errors.
## Two Ways to Use
| | **Claude Code Skill** | **MCP Server** |
|---|---|---|
| **Best for** | Claude Code users who want NotebookLM in their workflow | Any MCP-compatible client (Cursor, Gemini CLI, etc.) |
| **Setup** | Copy skill to `.claude/skills/` | Add server to MCP config |
| **Invocation** | Claude auto-detects when relevant | Tools appear in client tool list |
| **Config** | `SKILL.md` + `.env` | `mcp.json` + `.env` |
| **Requirements** | Python 3.10+, notebooklm-py | Python 3.10+, notebooklm-py |
## Features
| Feature | Description | Status |
|---|---|---|
| **Notebook CRUD** | Create, list, delete notebooks | Available |
| **Source ingestion** | Add URLs, PDFs, YouTube links, plain text | Available |
| **Research queries** | Ask questions against notebook sources with citations | Available |
| **Structured extraction** | Get key facts, arguments, timelines | Available |
| **Content generation** | Use research output as context for Claude | Available |
| **Batch operations** | Process multiple sources or queries at once | Available |
| **trend-pulse integration** | Auto-discover trending topics to research | Available |
| **threads-viral-agent integration** | Publish research-backed social posts | Available |
### Artifact Generation (10 types)
| Artifact | Format | Description |
|---|---|---|
| **Audio** | M4A | AI-generated podcast discussion |
| **Video** | MP4 | Video summary with visuals |
| **Slides** | PDF | Presentation deck |
| **Report** | PDF | Comprehensive written report |
| **Quiz** | JSON | Multiple-choice assessment questions |
| **Flashcards** | JSON | Study flashcard deck |
| **Mind map** | SVG | Visual concept map |
| **Infographic** | PNG | Visual data summary |
| **Data table** | CSV | Structured data extraction |
| **Study guide** | PDF | Structured learning material |
All artifacts support language selection (e.g., `--lang zh-TW`).
> **Note**: NotebookLM returns audio in MPEG-4 (M4A) format, not MP3.
## Architecture
```
+---------------------------------------------------------------+
| notebooklm-skill |
| |
| +---------+ +--------------+ +----------+ +------------+ |
| | Phase 1 | | Phase 2 | | Phase 3 | | Phase 4 | |
| | Collect |->| Research |->| Generate |->| Publish | |
| +---------+ +--------------+ +----------+ +------------+ |
| | | | | |
| +--------+ +-------------+ +-----------+ +-----------+ |
| | URLs | | NotebookLM | | Claude | | Threads | |
| | PDFs | | (via | | Content | | Blog | |
| | RSS | | notebooklm | | Engine | | Email | |
| | Trends | | -py 0.3.4) | | | | CMS | |
| +--------+ | - notebooks | +-----------+ +-----------+ |
| | - sources | | |
| | - chat/ask | +-----------+ |
| | - artifacts | | Artifacts | |
| +-------------+ | audio | |
| | video | |
| | slides | |
| | report | |
| | quiz | |
| | flashcards| |
| | mind-map | |
| | infographic| |
| | data-table| |
| | study-guide| |
| +-----------+ |
| |
| +-----------------------------------------------------------+ |
| | Interfaces | |
| | +-- scripts/ CLI tools (notebooklm-py direct) | |
| | +-- mcp-server/ MCP protocol server | |
| | +-- SKILL.md Claude Code skill definition | |
| +-----------------------------------------------------------+ |
+---------------------------------------------------------------+
^ ^
| |
+-----------+ +-----------+
|trend-pulse| |threads- |
|(optional) | |viral-agent|
+-----------+ |(optional) |
+-----------+
```
## Usage Examples
### 1. Research to Article
```bash
python scripts/pipeline.py research-to-article \
--sources "https://arxiv.org/abs/2401.00001" \
"https://blog.example.com/ai-agents" \
--title "AI Agent Survey"
```
### 2. Research to Social Posts
```bash
python scripts/pipeline.py research-to-social \
--sources "https://example.com/ai-news" \
--platform threads \
--title "AI News This Week"
```
### 3. Trending Topics to Content
```bash
python scripts/pipeline.py trend-to-content \
--geo TW \
--count 5 \
--platform threads
```
### 4. RSS Batch Digest
```bash
python scripts/pipeline.py batch-digest \
--rss "https://example.com/feed.xml" \
--title "Weekly AI Digest"
```
### 5. Generate All Artifacts
```bash
python scripts/pipeline.py generate-all \
--sources "https://example.com/article" \
--title "Research" \
--output-dir ./output \
--language zh-TW
```
### 6. Slides + Podcast → YouTube Video
Combine NotebookLM-generated slides and podcast into a YouTube-ready video:
```bash
# Generate slides and podcast
python scripts/notebooklm_client.py generate --notebook "Research" --type slides
python scripts/notebooklm_client.py podcast --notebook "Research" --lang en --output podcast.m4a
python scripts/notebooklm_client.py download --notebook "Research" --type slides --output slides.pdf
# Convert PDF to PNG + compose video
./scripts/make_video.sh slides.pdf podcast.m4a output.mp4
```
## Pipeline Workflows
| Workflow | Input | Output | Steps |
|---|---|---|---|
| `research-to-article` | URLs, text | Article draft JSON | Create notebook → 5 research questions → article draft |
| `research-to-social` | URLs, text | Social post draft | Create notebook → summarize → platform-specific post |
| `trend-to-content` | Geo, count | Content per trend | Fetch trends → create notebooks → research → draft |
| `batch-digest` | RSS URL | Newsletter digest | Fetch RSS → create notebook → digest + Q&A |
| `generate-all` | URLs, text | Audio, video, PDF, etc. | Create notebook → generate all artifacts → download |
## MCP Server Setup
Add to your project's `.mcp.json`:
```json
{
"mcpServers": {
"notebooklm": {
"command": "python",
"args": ["-m", "mcp-server"],
"cwd": "/path/to/notebooklm-skill"
}
}
}
```
Works with Claude Code, Cursor, Gemini CLI, and any MCP-compatible client.
## Claude Code Skill Setup
```bash
mkdir -p .claude/skills/notebooklm
cp /path/to/notebooklm-skill/SKILL.md .claude/skills/notebooklm/
cp /path/to/notebooklm-skill/scripts/*.py .claude/skills/notebooklm/scripts/
cp /path/to/notebooklm-skill/requirements.txt .claude/skills/notebooklm/
# Authenticate (one-time)
python3 -m notebooklm login
```
Claude will automatically detect the skill when you ask about research, NotebookLM, or content creation.
## API Reference
### CLI Commands (11)
| Command | Description |
|---|---|
| `create` | Create a notebook with URL/text sources |
| `list` | List all notebooks |
| `delete` | Delete a notebook |
| `add-source` | Add a source (URL, text, or file) to existing notebook |
| `ask` | Ask a research question (returns answer + citations) |
| `summarize` | Get notebook summary |
| `generate` | Generate an artifact (audio, video, slides, etc.) |
| `download` | Download a generated artifact |
| `research` | Run deep web research |
| `podcast` | Shortcut for `generate --type audio` (auto-downloads) |
| `qa` | Shortcut for `generate --type quiz` |
### MCP Tools (13)
| Tool | Description |
|---|---|
| `nlm_create_notebook` | Create notebook with sources |
| `nlm_list` | List all notebooks |
| `nlm_delete` | Delete a notebook |
| `nlm_add_source` | Add source to existing notebook |
| `nlm_ask` | Ask question (returns answer + citations) |
| `nlm_summarize` | Get notebook summary |
| `nlm_generate` | Generate artifact (10 types) |
| `nlm_download` | Download generated artifact |
| `nlm_list_sources` | List sources in notebook |
| `nlm_list_artifacts` | List generated artifacts |
| `nlm_research` | Deep web research |
| `nlm_research_pipeline` | Full research pipeline |
| `nlm_trend_research` | Trend → research pipeline |
## Integrations
- **[trend-pulse](https://github.com/claude-world/trend-pulse)** — Real-time trending topic discovery from 7 sources
- **[threads-viral-agent](https://github.com/claude-world/claude-world.com)** — Auto-publish research-backed social posts
## Contributing
1. Fork the repository
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes
4. Push and open a Pull Request
```bash
# Development setup
git clone https://github.com/claude-world/notebooklm-skill.git
cd notebooklm-skill
pip install -r requirements.txt
python3 -m notebooklm login
python -m pytest tests/
```
## License
MIT License. See [LICENSE](LICENSE).
