notebooklm

Automate Google NotebookLM queries for source-grounded answers and library management.

8|4|Updated Jan 15, 2026
One-click install
npx skills add https://github.com/jscraik/Agent-Skills --skill notebooklm-jscraik
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: notebooklm
Source: https://github.com/jscraik/Agent-Skills/tree/main/utilities/notebooklm
Command: npx skills add https://github.com/jscraik/Agent-Skills --skill notebooklm-jscraik

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill bridges the gap between Claude Code and Google NotebookLM, allowing you to query your documents directly from your AI assistant, eliminating manual copy-pasting and improving research accuracy.

Core Features & Use Cases

  • Source-Grounded Answers: Get answers exclusively from your uploaded documents, drastically reducing hallucinations.
  • Direct Integration: Claude Code asks questions directly to NotebookLM and receives answers programmatically.
  • Intelligent Source Filtering: Uses LLM-based relevance scoring to only query the most pertinent documents.
  • Use Case: Ask Claude Code to "Research my API documentation notebook for details on authentication methods" and get precise, citation-backed answers without leaving your terminal.

Quick Start

Ask Claude Code to research your API documentation notebook for authentication methods.

Frequently Asked Questions about notebooklm

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

FAQPage Schema
How do I query my uploaded documents in Google NotebookLM directly from Claude Code?

This Skill automates browser interaction with Google NotebookLM via Patchright, sending questions programmatically and returning source-grounded answers without manual copy-pasting.

Does querying NotebookLM from Claude Code require Google authentication?

Yes, querying NotebookLM from Claude Code requires local Claude Code installation and Google authentication to enable browser automation for accessing your knowledge base.

What is the best way to reduce hallucinations when asking Claude Code about my research documents?

The best way to reduce hallucinations is to use NotebookLM for source-grounded question answering, ensuring Claude Code receives answers exclusively from your uploaded documents.

How does intelligent source filtering work when querying a knowledge base through Claude Code?

Intelligent source filtering uses LLM-based relevance scoring to evaluate your knowledge base, ensuring Claude Code only queries the most pertinent uploaded documents for accurate answers.

Can I use Claude Code to manage my NotebookLM library and research documentation?

Yes, you can use Claude Code to manage your NotebookLM library and research documentation, as this Skill supports knowledge base management and direct querying of uploaded documents.

What are the limitations of automating NotebookLM interaction via Claude Code?

Limitations include requiring local Claude Code installation, active Google authentication for browser automation, and dependency on Patchright and python-dotenv for executing knowledge base queries.