notebooklm-research

Automates AI-driven research workflows using Google NotebookLM and Claude for content creation.

420|53|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/claude-world/notebooklm-skill --skill notebooklm-research-claude-world
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: notebooklm-research
Source: https://github.com/claude-world/notebooklm-skill/tree/main
Command: npx skills add https://github.com/claude-world/notebooklm-skill --skill notebooklm-research-claude-world

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires notebooklm, playwright, fastmcp, python-dotenv, httpx, and includes scripts (resource) and references (resource) and mcp-server (resource) components.

What problem does it solve?

This Skill automates the entire research-to-content pipeline, from ingesting diverse sources into Google NotebookLM to generating polished articles, podcasts, videos, and more, all powered by AI.

Core Features & Use Cases

  • End-to-End Research: Ingests URLs, PDFs, YouTube videos, and Google Drive files into NotebookLM.
  • Deep Research & Synthesis: Runs automated web research, asks cited questions, and generates 10 types of artifacts (audio, video, slides, reports, quizzes, etc.).
  • Content Creation: Uses Claude to draft articles, social posts, and newsletters based on research findings.
  • Use Case: Research a trending topic, get a podcast script and audio, and have Claude draft a blog post summarizing the findings, all with a single prompt.

Quick Start

Use the notebooklm-research skill to research the topic 'AI agent frameworks' and generate a podcast.

Frequently Asked Questions about notebooklm-research

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

FAQPage Schema
How do I automate research and content generation from multiple sources like PDFs and URLs?

Automating research and content generation is handled by ingesting URLs, PDFs, YouTube videos, and Google Drive files into NotebookLM, then synthesizing findings into drafts using Claude.

Can I generate a podcast script and audio directly from ingested research sources?

Generating a podcast from research sources is supported through NotebookLM's automated synthesis, which produces audio artifacts alongside reports and slides from ingested URLs and PDFs.

What is the best way to draft original articles using AI from deep web research findings?

Drafting original articles from deep web research is achieved by running automated web queries through NotebookLM, then passing the synthesized cited findings to Claude for content creation.

Does this research workflow support exporting diverse artifact types like quizzes and videos?

Supporting 10 distinct artifact types including videos, quizzes, slides, and audio reports is integrated within the synthesis phase of the automated research pipeline.

Do I need Playwright and Python-dotenv to run the NotebookLM research pipeline?

Playwright and Python-dotenv are required dependencies for executing the MCP server scripts that automate the NotebookLM ingestion and artifact creation workflow.

Why use an automated ingestion and synthesis workflow instead of manual web research?

Automated ingestion and synthesis eliminates manual source processing by running a four-phase pipeline that directly generates cited artifacts and Claude-drafted content from diverse inputs.