notebooklm

Query Google NotebookLM for citation-backed answers from uploaded documents.

63|6|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/Security-Phoenix-demo/security-skills-claude-code --skill notebooklm-security-phoenix-demo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: notebooklm
Source: https://github.com/Security-Phoenix-demo/security-skills-claude-code/tree/main/skills/notebooklm
Command: npx skills add https://github.com/Security-Phoenix-demo/security-skills-claude-code --skill notebooklm-security-phoenix-demo

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves the problem of manual document search and the potential for hallucinations in AI-generated answers. It allows Claude Code to directly query Google NotebookLM for accurate, citation-backed answers from your uploaded documents.

Core Features & Use Cases

  • Source-Grounded Responses: Reduces hallucinations by answering exclusively from your uploaded documents.
  • 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.
  • Automatic Authentication: One-time Google login, then authentication persists across sessions.
  • Self-Contained: Everything runs in the skill folder with an isolated Python environment.
  • Use Case: Imagine you have a complex technical document. Use this Skill to ask Claude Code to query the document for specific information and get precise, well-sourced answers.

Quick Start

Add your NotebookLM notebook to your library by sharing its link with Claude Code and saying, "Add this NotebookLM to my library: [your-link]".

Frequently Asked Questions about notebooklm

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

FAQPage Schema
How do I get source-grounded answers from my documents without hallucinations?

Source-grounded answers are retrieved by automating Google NotebookLM queries, ensuring responses are citation-backed and drawn exclusively from user-uploaded materials to eliminate hallucinations. This requires browser automation via Playwright.

How do I automate document analysis queries to NotebookLM programmatically?

You automate document analysis by adding your NotebookLM link to the library and letting Claude Code query it directly. This removes manual copy-pasting between your browser and editor, providing programmatic answers through an isolated Python environment.

Do I need patchright and python-dotenv to use this NotebookLM automation?

Yes, you need patchright and python-dotenv dependencies along with browser automation. These dependencies run the Skill's isolated Python environment and manage the required session cookies to bypass a known Playwright bug for authentication.

Why does my Playwright browser automation fail when accessing NotebookLM?

Playwright browser automation fails accessing NotebookLM due to a known bug requiring manual injection of session cookies. This Skill applies a patchright workaround to maintain your one-time Google login across multiple query sessions.

Can I save and manage multiple NotebookLM links for technical documentation analysis?

Yes, you can save and manage multiple NotebookLM links for technical documentation analysis. The Smart Library Management feature allows you to store notebook links with specific tags and descriptions for organized knowledge retrieval.