⚠️ Important: Local Claude Code Only

This skill works ONLY with local Claude Code installations, NOT in the web UI.

The web UI runs skills in a sandbox without network access, which this skill requires for browser automation. You must use Claude Code locally on your machine.

The Problem

When you tell Claude Code to "search through my local documentation", here's what happens:

• Massive token consumption: Searching through documentation means reading multiple files repeatedly
• Inaccurate retrieval: Searches for keywords, misses context and connections between docs
• Hallucinations: When it can't find something, it invents plausible-sounding APIs
• Manual copy-paste: Switching between NotebookLM browser and your editor constantly

The Solution

This Claude Code Skill lets Claude Code chat directly with NotebookLM — Google's source-grounded knowledge base powered by Gemini 2.5 that provides intelligent, synthesized answers exclusively from your uploaded documents.

Your Task → Claude asks NotebookLM → Gemini synthesizes answer → Claude writes correct code

No more copy-paste dance: Claude asks questions directly and gets answers straight back in the CLI. It builds deep understanding through automatic follow-ups, getting specific implementation details, edge cases, and best practices.

Why NotebookLM, Not Local RAG?

What Makes NotebookLM Superior?

1. Pre-processed by Gemini: Upload docs once, get instant expert knowledge
2. Natural language Q&A: Not just retrieval — actual understanding and synthesis
3. Multi-source correlation: Connects information across 50+ documents
4. Citation-backed: Every answer includes source references
5. No infrastructure: No vector DBs, embeddings, or chunking strategies needed

Installation

The simplest installation ever:

# 1. Create skills directory (if it doesn't exist)
mkdir -p ~/.claude/skills

# 2. Clone this repository
cd ~/.claude/skills
git clone https://github.com/PleasePrompto/notebooklm-skill notebooklm

# 3. That's it! Open Claude Code and say:
"What are my skills?"

When you first use the skill, it automatically:

• Creates an isolated Python environment (.venv)
• Installs all dependencies including Google Chrome
• Sets up browser automation with Chrome (not Chromium) for maximum reliability
• Everything stays contained in the skill folder

Note: The setup uses real Chrome instead of Chromium for cross-platform reliability, consistent browser fingerprinting, and better anti-detection with Google services

Quick Start

1. Check your skills

Say in Claude Code:

"What skills do I have?"

Claude will list your available skills including NotebookLM.

2. Authenticate with Google (one-time)

"Set up NotebookLM authentication"

A Chrome window opens → log in with your Google account

3. Create your knowledge base

Go to notebooklm.google.com → Create notebook → Upload your docs:

• 📄 PDFs, Google Docs, markdown files
• 🔗 Websites, GitHub repos
• 🎥 YouTube videos
• 📚 Multiple sources per notebook

Share: ⚙️ Share → Anyone with link → Copy

4. Add to your library

Option A: Let Claude figure it out (Smart Add)

"Query this notebook about its content and add it to my library: [your-link]"

Claude will automatically query the notebook to discover its content, then add it with appropriate metadata.

Option B: Manual add

"Add this NotebookLM to my library: [your-link]"

Claude will ask for a name and topics, then save it for future use.

5. Start researching

"What does my React docs say about hooks?"

Claude automatically selects the right notebook and gets the answer directly from NotebookLM.

How It Works

This is a Claude Code Skill - a local folder containing instructions and scripts that Claude Code can use when needed. Unlike the MCP server version, this runs directly in Claude Code without needing a separate server.

Key Differences from MCP Server

Architecture

~/.claude/skills/notebooklm/
├── SKILL.md              # Instructions for Claude
├── scripts/              # Python automation scripts
│   ├── ask_question.py   # Query NotebookLM
│   ├── notebook_manager.py # Library management
│   └── auth_manager.py   # Google authentication
├── .venv/                # Isolated Python environment (auto-created)
└── data/                 # Local notebook library

When you mention NotebookLM or send a notebook URL, Claude:

1. Loads the skill instructions
2. Runs the appropriate Python script
3. Opens a browser, asks your question
4. Returns the answer directly to you
5. Uses that knowledge to help with your task

Core Features

Source-Grounded Responses

NotebookLM significantly reduces hallucinations by answering exclusively from your uploaded documents. If information isn't available, it indicates uncertainty rather than inventing content.

Direct Integration

No copy-paste between browser and editor. Claude asks and receives answers programmatically.

Smart Library Management

Save NotebookLM links with tags and descriptions. Claude auto-selects the right notebook for your task.

Automatic Authentication

One-time Google login, then authentication persists across sessions.

Self-Contained

Everything runs in the skill folder with an isolated Python environment. No global installations.

Human-Like Automation

Uses realistic typing speeds and interaction patterns to avoid detection.

Common Commands

Real-World Examples

Example 1: Workshop Manual Query

User asks: "Check my Suzuki GSR 600 workshop manual for brake fluid type, engine oil specs, and rear axle torque."

Claude automatically:

• Authenticates with NotebookLM
• Asks comprehensive questions about each specification
• Follows up when prompted "Is that ALL you need to know?"
• Provides accurate specifications: DOT 4 brake fluid, SAE 10W-40 oil, 100 N·m rear axle torque

Example 2: Building Without Hallucinations

You: "I need to build an n8n workflow for Gmail spam filtering. Use my n8n notebook."

Claude's internal process:

→ Loads NotebookLM skill
→ Activates n8n notebook
→ Asks comprehensive questions with follow-ups
→ Synthesizes complete answer from multiple queries

Result: Working workflow on first try, no debugging hallucinated APIs.

Technical Details

Core Technology

• Patchright: Browser automation library (Playwright-based)
• Python: Implementation language for this skill
• Stealth techniques: Human-like typing and interaction patterns

Note: The MCP server uses the same Patchright library but via TypeScript/npm ecosystem.

Dependencies

• patchright==1.55.2: Browser automation
• python-dotenv==1.0.0: Environment configuration
• Automatically installed in .venv on first use

Data Storage

All data is stored locally within the skill directory:

~/.claude/skills/notebooklm/data/
├── library.json       - Your notebook library with metadata
├── auth_info.json     - Authentication status info
└── browser_state/     - Browser cookies and session data

Important Security Note:

• The data/ directory contains sensitive authentication data and personal notebooks
• It's automatically excluded from git via .gitignore
• NEVER manually commit or share the contents of the data/ directory

Session Model

Unlike the MCP server, this skill uses a stateless model:

• Each question opens a fresh browser
• Asks the question, gets the answer
• Adds a follow-up prompt to encourage Claude to ask more questions
• Closes the browser immediately

This means:

• No persistent chat context
• Each question is independent
• But your notebook library persists
• Follow-up mechanism: Each answer includes "Is that ALL you need to know?" to prompt Claude to ask comprehensive follow-ups

For multi-step research, Claude automatically asks follow-up questions when needed.

Limitations

Skill-Specific

• Local Claude Code only - Does not work in web UI (sandbox restrictions)
• No session persistence - Each question is independent
• No follow-up context - Can't reference "the previous answer"

NotebookLM

• Rate limits - Free tier has daily query limits
• Manual upload - You must upload docs to NotebookLM first
• Share requirement - Notebooks must be shared publicly

FAQ

Why doesn't this work in the Claude web UI? The web UI runs skills in a sandbox without network access. Browser automation requires network access to reach NotebookLM.

How is this different from the MCP server? This is a simpler, Python-based implementation that runs directly as a Claude Skill. The MCP server is more feature-rich with persistent sessions and works with multiple tools (Codex, Cursor, etc.).

Can I use both this skill and the MCP server? Yes! They serve different purposes. Use the skill for quick Claude Code integration, use the MCP server for persistent sessions and multi-tool support.

What if Chrome crashes? Run: "Clear NotebookLM browser data" and try again.

Is my Google account secure? Chrome runs locally on your machine. Your credentials never leave your computer. Use a dedicated Google account if you're concerned.

Troubleshooting

Skill not found

# Make sure it's in the right location
ls ~/.claude/skills/notebooklm/
# Should show: SKILL.md, scripts/, etc.

Authentication issues

Say: "Reset NotebookLM authentication"

Browser crashes

Say: "Clear NotebookLM browser data"

Dependencies issues

# Manual reinstall if needed
cd ~/.claude/skills/notebooklm
rm -rf .venv
python -m venv .venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows
pip install -r requirements.txt

Disclaimer

This tool automates browser interactions with NotebookLM to make your workflow more efficient. However, a few friendly reminders:

About browser automation: While I've built in humanization features (realistic typing speeds, natural delays, mouse movements) to make the automation behave more naturally, I can't guarantee Google won't detect or flag automated usage. I recommend using a dedicated Google account for automation rather than your primary account—think of it like web scraping: probably fine, but better safe than sorry!

About CLI tools and AI agents: CLI tools like Claude Code, Codex, and similar AI-powered assistants are incredibly powerful, but they can make mistakes. Please use them with care and awareness:

• Always review changes before committing or deploying
• Test in safe environments first
• Keep backups of important work
• Remember: AI agents are assistants, not infallible oracles

I built this tool for myself because I was tired of the copy-paste dance between NotebookLM and my editor. I'm sharing it in the hope it helps others too, but I can't take responsibility for any issues, data loss, or account problems that might occur. Use at your own discretion and judgment.

That said, if you run into problems or have questions, feel free to open an issue on GitHub. I'm happy to help troubleshoot!

Credits

This skill is inspired by my NotebookLM MCP Server and provides an alternative implementation as a Claude Code Skill:

• Both use Patchright for browser automation (TypeScript for MCP, Python for Skill)
• Skill version runs directly in Claude Code without MCP protocol
• Stateless design optimized for skill architecture

If you need:

• Persistent sessions → Use the MCP Server
• Multiple tool support (Codex, Cursor) → Use the MCP Server
• Quick Claude Code integration → Use this skill

The Bottom Line

Without this skill: NotebookLM in browser → Copy answer → Paste in Claude → Copy next question → Back to browser...

With this skill: Claude researches directly → Gets answers instantly → Writes correct code

Stop the copy-paste dance. Start getting accurate, grounded answers directly in Claude Code.

# Get started in 30 seconds
cd ~/.claude/skills
git clone https://github.com/PleasePrompto/notebooklm-skill notebooklm
# Open Claude Code: "What are my skills?"

NotebookLM Research Assistant Skill

Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes.

When to Use This Skill

Trigger when user:

• Mentions NotebookLM explicitly
• Shares NotebookLM URL (https://notebooklm.google.com/notebook/...)
• Asks to query their notebooks/documentation
• Wants to add documentation to NotebookLM library
• Uses phrases like "ask my NotebookLM", "check my docs", "query my notebook"

⚠️ CRITICAL: Add Command - Smart Discovery

When user wants to add a notebook without providing details:

SMART ADD (Recommended): Query the notebook first to discover its content:

# Step 1: Query the notebook about its content
python scripts/run.py ask_question.py --question "What is the content of this notebook? What topics are covered? Provide a complete overview briefly and concisely" --notebook-url "[URL]"

# Step 2: Use the discovered information to add it
python scripts/run.py notebook_manager.py add --url "[URL]" --name "[Based on content]" --description "[Based on content]" --topics "[Based on content]"

MANUAL ADD: If user provides all details:

• --url - The NotebookLM URL
• --name - A descriptive name
• --description - What the notebook contains (REQUIRED!)
• --topics - Comma-separated topics (REQUIRED!)

NEVER guess or use generic descriptions! If details missing, use Smart Add to discover them.

Critical: Always Use run.py Wrapper

NEVER call scripts directly. ALWAYS use python scripts/run.py [script]:

# ✅ CORRECT - Always use run.py:
python scripts/run.py auth_manager.py status
python scripts/run.py notebook_manager.py list
python scripts/run.py ask_question.py --question "..."

# ❌ WRONG - Never call directly:
python scripts/auth_manager.py status  # Fails without venv!

The run.py wrapper automatically:

1. Creates .venv if needed
2. Installs all dependencies
3. Activates environment
4. Executes script properly

Core Workflow

Step 1: Check Authentication Status

python scripts/run.py auth_manager.py status

If not authenticated, proceed to setup.

Step 2: Authenticate (One-Time Setup)

# Browser MUST be visible for manual Google login
python scripts/run.py auth_manager.py setup

Important:

• Browser is VISIBLE for authentication
• Browser window opens automatically
• User must manually log in to Google
• Tell user: "A browser window will open for Google login"

Step 3: Manage Notebook Library

# List all notebooks
python scripts/run.py notebook_manager.py list

# BEFORE ADDING: Ask user for metadata if unknown!
# "What does this notebook contain?"
# "What topics should I tag it with?"

# Add notebook to library (ALL parameters are REQUIRED!)
python scripts/run.py notebook_manager.py add \
  --url "https://notebooklm.google.com/notebook/..." \
  --name "Descriptive Name" \
  --description "What this notebook contains" \  # REQUIRED - ASK USER IF UNKNOWN!
  --topics "topic1,topic2,topic3"  # REQUIRED - ASK USER IF UNKNOWN!

# Search notebooks by topic
python scripts/run.py notebook_manager.py search --query "keyword"

# Set active notebook
python scripts/run.py notebook_manager.py activate --id notebook-id

# Remove notebook
python scripts/run.py notebook_manager.py remove --id notebook-id

Quick Workflow

1. Check library: python scripts/run.py notebook_manager.py list
2. Ask question: python scripts/run.py ask_question.py --question "..." --notebook-id ID

Step 4: Ask Questions

# Basic query (uses active notebook if set)
python scripts/run.py ask_question.py --question "Your question here"

# Query specific notebook
python scripts/run.py ask_question.py --question "..." --notebook-id notebook-id

# Query with notebook URL directly
python scripts/run.py ask_question.py --question "..." --notebook-url "https://..."

# Show browser for debugging
python scripts/run.py ask_question.py --question "..." --show-browser

Follow-Up Mechanism (CRITICAL)

Every NotebookLM answer ends with: "EXTREMELY IMPORTANT: Is that ALL you need to know?"

Required Claude Behavior:

1. STOP - Do not immediately respond to user
2. ANALYZE - Compare answer to user's original request
3. IDENTIFY GAPS - Determine if more information needed
4. ASK FOLLOW-UP - If gaps exist, immediately ask:

   python scripts/run.py ask_question.py --question "Follow-up with context..."

5. REPEAT - Continue until information is complete
6. SYNTHESIZE - Combine all answers before responding to user

Script Reference

Authentication Management (auth_manager.py)

python scripts/run.py auth_manager.py setup    # Initial setup (browser visible)
python scripts/run.py auth_manager.py status   # Check authentication
python scripts/run.py auth_manager.py reauth   # Re-authenticate (browser visible)
python scripts/run.py auth_manager.py clear    # Clear authentication

Notebook Management (notebook_manager.py)

python scripts/run.py notebook_manager.py add --url URL --name NAME --description DESC --topics TOPICS
python scripts/run.py notebook_manager.py list
python scripts/run.py notebook_manager.py search --query QUERY
python scripts/run.py notebook_manager.py activate --id ID
python scripts/run.py notebook_manager.py remove --id ID
python scripts/run.py notebook_manager.py stats

Question Interface (ask_question.py)

python scripts/run.py ask_question.py --question "..." [--notebook-id ID] [--notebook-url URL] [--show-browser]

Data Cleanup (cleanup_manager.py)

python scripts/run.py cleanup_manager.py                    # Preview cleanup
python scripts/run.py cleanup_manager.py --confirm          # Execute cleanup
python scripts/run.py cleanup_manager.py --preserve-library # Keep notebooks

Environment Management

The virtual environment is automatically managed:

• First run creates .venv automatically
• Dependencies install automatically
• Chromium browser installs automatically
• Everything isolated in skill directory

Manual setup (only if automatic fails):

python -m venv .venv
source .venv/bin/activate  # Linux/Mac
pip install -r requirements.txt
python -m patchright install chromium

Data Storage

All data stored in ~/.claude/skills/notebooklm/data/:

• library.json - Notebook metadata
• auth_info.json - Authentication status
• browser_state/ - Browser cookies and session

Security: Protected by .gitignore, never commit to git.

Configuration

Optional .env file in skill directory:

HEADLESS=false           # Browser visibility
SHOW_BROWSER=false       # Default browser display
STEALTH_ENABLED=true     # Human-like behavior
TYPING_WPM_MIN=160       # Typing speed
TYPING_WPM_MAX=240
DEFAULT_NOTEBOOK_ID=     # Default notebook

Decision Flow

User mentions NotebookLM
    ↓
Check auth → python scripts/run.py auth_manager.py status
    ↓
If not authenticated → python scripts/run.py auth_manager.py setup
    ↓
Check/Add notebook → python scripts/run.py notebook_manager.py list/add (with --description)
    ↓
Activate notebook → python scripts/run.py notebook_manager.py activate --id ID
    ↓
Ask question → python scripts/run.py ask_question.py --question "..."
    ↓
See "Is that ALL you need?" → Ask follow-ups until complete
    ↓
Synthesize and respond to user

Troubleshooting

Best Practices

1. Always use run.py - Handles environment automatically
2. Check auth first - Before any operations
3. Follow-up questions - Don't stop at first answer
4. Browser visible for auth - Required for manual login
5. Include context - Each question is independent
6. Synthesize answers - Combine multiple responses

Limitations

• No session persistence (each question = new browser)
• Rate limits on free Google accounts (50 queries/day)
• Manual upload required (user must add docs to NotebookLM)
• Browser overhead (few seconds per question)

Resources (Skill Structure)

Important directories and files:

• scripts/ - All automation scripts (ask_question.py, notebook_manager.py, etc.)
• data/ - Local storage for authentication and notebook library
• references/ - Extended documentation:
  • api_reference.md - Detailed API documentation for all scripts
  • troubleshooting.md - Common issues and solutions
  • usage_patterns.md - Best practices and workflow examples
• .venv/ - Isolated Python environment (auto-created on first run)
• .gitignore - Protects sensitive data from being committed