Skill Detail

Automate grounded NotebookLM research and artifact export with notebooklm-py

Lets agents operate Google NotebookLM/Gemini Notebook through a Python API, CLI, skill, MCP server, or REST server to create notebooks, add sources, ask cited questions, generate artifacts, and download exports.

Research & ScrapingMulti-Framework
Research & Scraping Multi-Framework Security Reviewed
⭐ 18.2k GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill automate-grounded-notebooklm-research-and-artifact-export-with-notebooklm-py Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
notebooklm-py CLI or Python package, Google NotebookLM/Gemini Notebook account, browser authentication or master-token authentication, optional MCP or REST server
Install & setup
Install the CLI with uv tool install "notebooklm-py[browser]" or pipx install "notebooklm-py[browser]", run notebooklm login, verify with notebooklm auth check –test –json, then install the agent skill with notebooklm skill install or npx skills add teng-lin/notebooklm-py.
Author
teng-lin
Publisher
Independent
Last updated
Jul 27, 2026
Quick brief

## What the agent does
The agent uses notebooklm-py to create and select notebooks, add URLs, PDFs, YouTube links, Google Drive files, or research results as sources, ask cited questions, generate audio, video, reports, quizzes, flashcards, slide decks, mind maps, and data tables, then download the generated artifacts to local files.

How it works

What this skill actually does

## When to use it
Use this when a user wants NotebookLM’s grounded reading and artifact generation inside an unattended or repeatable agent workflow instead of clicking through the web UI. It is a strong fit for research pipelines, source-grounded support answers, study-set generation, briefing creation, and bulk export tasks.

## Scope boundary
This is not a generic Google product card or a simple SDK listing. The workflow is bounded to agent-operated NotebookLM automation: authenticate, create/use a notebook, add sources, ask or generate with citations, export artifacts, and optionally expose the same actions through MCP or REST.

## Source evidence
The upstream repository documents the CLI, Python API, local skill installer, npx skills install route, MCP server, REST server, authentication modes, NotebookLM artifact coverage, and concrete command examples for create, source add, ask, generate, and download.