nblm

Query Google NotebookLM notebooks for source-grounded, citation-backed answers via Gemini.

33|4|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/magicseek/nblm --skill nblm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nblm
Source: https://github.com/magicseek/nblm/tree/main
Command: npx skills add https://github.com/magicseek/nblm --skill nblm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser, notebooklm-py, python-dotenv, ebooklib, beautifulsoup4, lxml, pypdf, patchright, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows you to interact with your Google NotebookLM notebooks directly from your AI coding assistant, enabling you to ask questions and get answers grounded in your own documents.

Core Features & Use Cases

  • Source-Grounded Answers: Get answers directly from your uploaded documents, minimizing hallucinations.
  • Notebook Management: Easily add, list, activate, and manage your NotebookLM notebooks.
  • Document Upload: Upload local files or URLs directly into your notebooks.
  • Use Case: Imagine you've uploaded a large research paper to NotebookLM. You can now ask your AI assistant specific questions about the paper's content, like "What does the paper say about the methodology?" and receive a precise answer with citations.

Quick Start

Use the nblm skill to ask your active notebook what the main findings of the document are.

Frequently Asked Questions about nblm

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

FAQPage Schema
How do I get source-grounded answers from my documents using an AI assistant?

You can get source-grounded answers by querying your Google NotebookLM notebooks directly from your AI coding assistant using Gemini. This ensures responses are derived exclusively from your uploaded documents, significantly reducing hallucinations and providing citation-backed answers.

Can I use browser automation to upload local files to NotebookLM?

Yes, you can upload local files or URLs directly into your NotebookLM notebooks using browser automation. The Skill leverages agent-browser and patchright to manage library content and provides persistent authentication for reliable document uploads.

What's the best way to manage multiple NotebookLM notebooks within my coding environment?

The best way to manage multiple NotebookLM notebooks is using this Skill's notebook management features, which allow you to easily add, list, and activate specific notebooks. This ensures your document Q&A queries target the correct active library.

Does querying NotebookLM with Gemini require persistent authentication?

Yes, querying NotebookLM requires persistent authentication to maintain access to your Google notebooks. The Skill handles this authentication process automatically, allowing your AI coding agent to continuously interact with your document libraries without manual login interruptions.

What document formats can I parse and query for AI citation-backed answers?

You can parse and query PDFs, EPUBs, and HTML documents for citation-backed answers. The Skill utilizes pypdf, ebooklib, and beautifulsoup4 dependencies to process these formats, enabling source-grounded document Q&A directly within your AI assistant.

Why does my AI assistant hallucinate when answering questions about my research papers?

AI assistants hallucinate because they lack specific document context. By querying NotebookLM with Gemini through this Skill, responses are derived exclusively from your uploaded research papers, ensuring source-grounded, citation-backed answers that eliminate fabricated information.