Skill Listing

Review the skill and install it into your account in one click.

Sign in
← Back to Skills

NotebookLM Research Assistant

Queries NotebookLM notebooks through browser automation for source-grounded answers.

Free

Category

research

Provider

Open Source

Code Files

14

View on GitHub

AI review

Quality 75Trust 45Discovery 44

Well-documented, functional-looking skill that automates querying Google NotebookLM for source-grounded answers. However, it requires direct access to a Google account via browser automation and lacks explicit security/privacy guarantees, so it should be treated with caution.

This skill appears to be a practical, well-documented implementation for querying NotebookLM notebooks via automated browser sessions, with multiple helper scripts, troubleshooting docs, and clear usage patterns. It is useful for researchers who want citation-backed answers pulled from their uploaded documents. Because it requires persistent authentication and browser automation to access a user's Google account, the listing lacks explicit documentation about credential handling, data retention, or security practices — review the code and test in a safe environment before granting account access.

Source full AI review

Strengths

  • Comprehensive documentation, example scripts, and troubleshooting guides
  • Enables source-grounded NotebookLM queries with persistent auth and library management

Considerations

  • Requires browser-based access to the user's Google account; no explicit security/privacy guarantees or credential storage details provided
  • No domain verification or external hosting details are present to increase trust
  • Strong dependence on a fragile run.py wrapper and visible browser sessions — could be brittle in production

Why this ranks

Agent List ranks listings using quality, trust, traction, and freshness instead of follower count alone. Paid Computer Agents badges are identity signals only and do not raise discovery score.

  • The quality review is solid enough to support discovery.
  • The listing is under additional review, which can affect discoverability.

Trust signals

AI review

Review pending.

Badge guide

Paid account badge

Automatic for active Computer Agents Individual, Team, and Enterprise subscriptions. It confirms account status only and does not increase discovery ranking.

Agent List reviewed

Agent List review

Granted after Agent List reviews the creator profile and marketplace presence. This is separate from the blue paid account badge.

name:
notebooklm
description:
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

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:

terminal
Loading...

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]:

terminal
Loading...

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

terminal
Loading...

If not authenticated, proceed to setup.

Step 2: Authenticate (One-Time Setup)

terminal
Loading...

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

terminal
Loading...

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

terminal
Loading...

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

Script Reference

Authentication Management (auth_manager.py)

terminal
Loading...

Notebook Management (notebook_manager.py)

terminal
Loading...

Question Interface (ask_question.py)

terminal
Loading...

Data Cleanup (cleanup_manager.py)

terminal
Loading...

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):

terminal
Loading...

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:

file.env
Loading...

Decision Flow

output
Loading...

Troubleshooting

ProblemSolution
ModuleNotFoundErrorUse run.py wrapper
Authentication failsBrowser must be visible for setup! --show-browser
Rate limit (50/day)Wait or switch Google account
Browser crashespython scripts/run.py cleanup_manager.py --preserve-library
Notebook not foundCheck with notebook_manager.py list

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