notebooklm

Query Google NotebookLM notebooks and return citation-backed answers from uploaded documents.

110|19|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/chendongqi/OPB-Skills --skill notebooklm-chendongqi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: notebooklm
Source: https://github.com/chendongqi/OPB-Skills/tree/main/skills/content-notebooklm
Command: npx skills add https://github.com/chendongqi/OPB-Skills --skill notebooklm-chendongqi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Claude Code users often need to access their own NotebookLM notebooks and get reliable, source-grounded answers drawn only from their uploaded documents, while managing authentication and notebook metadata in one place.

Core Features & Use Cases

  • Source-grounded querying of NotebookLM notebooks with citation-backed responses loaded from user data
  • Browser automation, library management, and a one-time Google authentication flow with state persistence
  • Use cases include researching notes, validating facts across notebooks, and organizing a NotebookLM library for quick access

Quick Start

Install the skill and run a simple NotebookLM query to verify results.

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 Google NotebookLM using Claude Code?

Source-grounded answers from Google NotebookLM are retrieved by automating the browser with Patchright to query your uploaded documents and return citation-backed responses directly within Claude Code.

Do I need to authenticate with Google every time I query my NotebookLM library?

Google authentication for NotebookLM is required only once through a manual cookie injection flow that establishes a persistent browser profile, allowing subsequent queries to reuse the authenticated state without repeated logins.

Can I manage multiple NotebookLM notebooks for research and fact validation?

NotebookLM library management is supported natively, enabling you to organize multiple notebooks, retrieve metadata, and validate facts across different collections of uploaded documents.

What dependencies are required to run NotebookLM browser automation in an isolated environment?

NotebookLM browser automation requires Patchright for browser control and python-dotenv for environment configuration, both managed inside an isolated virtual environment through a run.py wrapper script.

Why does my NotebookLM query return answers outside my uploaded documents?

NotebookLM queries configured for document-grounded retrieval return answers drawn exclusively from your uploaded documents with citation backing, ensuring responses do not rely on external model knowledge.

Is Patchright better than standard browser automation for querying NotebookLM?

Patchright provides specialized browser automation for NotebookLM that supports persistent profiles and per-question browsing, offering more reliable authentication state management than standard browser automation tools in the same category.