notebooklm

Query NotebookLM notebooks from Claude Code with source-grounded answers.

Updated Dec 17, 2025
One-click install
npx skills add https://github.com/miethe/meatycapture --skill notebooklm-miethe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: notebooklm
Source: https://github.com/miethe/meatycapture/tree/main/.claude/skills/notebooklm-skill
Command: npx skills add https://github.com/miethe/meatycapture --skill notebooklm-miethe

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires patchright, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill enables Claude Code to query NotebookLM notebooks directly and receive source-grounded, citation-backed answers, all through a local browser workflow.

Core Features & Use Cases

  • Grounded Q&A: Answers are derived exclusively from uploaded NotebookLM content, reducing hallucinations.
  • Library Management: Create, list, search, and activate notebooks in a local library, enabling quick context switching.
  • Authentication & Automation: Hybrid authentication with a persistent browser profile and session cookies injection for reliability.

Quick Start

  • Install and run via the run.py wrapper: python scripts/run.py auth_manager.py setup
  • Add a NotebookLM notebook: python scripts/run.py notebook_manager.py add --url "<notebook-url>" --name "<name>" --description "<description>" --topics "<topics>"
  • Ask a question: python scripts/run.py ask_question.py --question "Your question" --notebook-id <id>

Frequently Asked Questions about notebooklm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query NotebookLM notebooks from Claude Code?

You can query NotebookLM notebooks from Claude Code by running a local Python script that uses a persistent browser profile and manual cookie injection to return source-grounded answers.

How does grounded Q&A with NotebookLM reduce hallucinations?

Grounded Q&A with NotebookLM reduces hallucinations by deriving answers exclusively from your uploaded notebook content, ensuring the responses are backed by citations from the source material.

Do I need a specific browser environment to automate NotebookLM queries?

Yes, you need a local Python environment with a Chrome browser installed via Patchright to automate NotebookLM queries and maintain session persistence.

How do I manage multiple NotebookLM notebooks for quick context switching?

You manage multiple NotebookLM notebooks by using the local library management feature to create, list, search, and activate notebooks based on their URLs, names, and topics.

Can I use session cookies for authentication when automating NotebookLM?

Yes, the automation workflow uses a hybrid authentication approach that injects session cookies into a persistent browser profile during each query for reliable access.

What are the limitations of running a stateless NotebookLM browser workflow?

The stateless workflow requires manual cookie injection for each query session and depends on having NotebookLM URLs pre-configured in your local library before querying.