LaunchKit · 2026
Back to Skills

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded.

3
1.3k downloads
by @magicseek

Setup & Installation

openclaw skills install @magicseek/nblm

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install nblm

What This Skill Does

A skill that lets you query Google NotebookLM notebooks directly from Claude Code. It handles Google authentication via browser automation, manages a local notebook library, and supports uploading sources including PDFs, URLs, and YouTube videos. Answers come from Gemini grounded in your uploaded documents with citations.

Responses are constrained to your uploaded documents, so you get fewer hallucinations than asking a general-purpose LLM about your materials.

When to use it

  • Querying research notes for citation-backed answers
  • Syncing a local docs folder to a NotebookLM notebook
  • Generating a podcast or slide deck from notebook content
  • Adding a YouTube video or web URL as a notebook source
  • Managing multiple Google accounts to work around query rate limits

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: What does my notebook say about transformer attention mechanisms?

AGENT
  1. 1Check Google auth status with auth_manager.py status
  2. 2List local notebook library with notebook_manager.py list
  3. 3Activate the relevant notebook with notebook_manager.py activate
  4. 4Query the notebook with ask_question.py --question '...'
  5. 5Ask follow-up questions if the first answer is incomplete
OUTPUT

Citation-backed answer drawn from the notebook's uploaded sources

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

Google account for NotebookLM accessZ-Library account (only if using the Z-Library book download feature)