deep-research-notebooklm

Conducts multi-source research via NotebookLM MCP and generates structured briefs and studio artifacts.

30.5k|3.5k|Updated Jul 4, 2025
One-click install
npx skills add https://github.com/davila7/claude-code-templates --skill deep-research-notebooklm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research-notebooklm
Source: https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/ai-research/deep-research-notebooklm
Command: npx skills add https://github.com/davila7/claude-code-templates --skill deep-research-notebooklm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Conducting thorough market, competitive, or prospect research requires gathering sources, synthesizing findings, and producing deliverables, which is slow and inconsistent when done manually. This Skill automates the full research pipeline using Google NotebookLM as the research engine.

Core Features & Use Cases

  • Structured Multi-Source Research: Creates a NotebookLM notebook, seeds it with URLs and documents, runs fast or deep research queries, and imports discovered sources for analysis.
  • Formatted Research Briefs: Delivers consistent markdown briefs covering key findings, opportunities, risks, recommended actions, and sources, saved to a local research directory.
  • Studio Artifact Generation: Optionally produces slides, audio podcasts, videos, infographics, reports, and mind maps from the research notebook.
  • Use Case: A sales rep asks for competitive intel on a prospect's market. The Skill scopes the angle, runs NotebookLM research, saves a dated brief with headline findings, and generates a slide deck for the pitch meeting.

Quick Start

Research the competitive landscape for AI coding assistants and save a brief with the top findings and recommended actions.

Frequently Asked Questions about deep-research-notebooklm

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

FAQPage Schema
How do I run deep research with NotebookLM in Claude Code?

Install the NotebookLM MCP server with nlm setup add claude-code, restart your session, then invoke the skill with your research topic. It creates a notebook, adds sources, runs the research query, and saves a structured brief.

What research types does NotebookLM deep research support?

It supports market research, competitive intelligence, client and prospect research, trend analysis, proposal research, and academic or technical research. Each type uses targeted query questions to extract relevant insights.

What is the difference between fast and deep research mode?

Fast mode takes about 60 seconds and gathers roughly 10 sources, making it the recommended default. Deep mode is more exhaustive but can take over 10 minutes and may occasionally stall at zero sources.

Can NotebookLM generate podcasts or slides from research?

Yes, the studio_create tool generates slide decks, audio podcasts, videos, infographics, reports, and mind maps from a research notebook. Audio and video take 5-15 minutes; slides and infographics take 2-5 minutes.

Why is NotebookLM research not starting in my session?

The NotebookLM MCP server must be configured first by running nlm setup add claude-code and restarting the session. If the MCP tools are unavailable, the skill will prompt you to complete this setup.