How to learn anything in an afternoon, not a month.

A week of evenings, in ten minutes.

Learning a new domain used to mean a week of evenings. Five hours of one expert, four of another, three of a third, and a notebook full of conflicting takes.

This guide installs a pipeline that collapses that into one prompt. You give Claude Code a topic, it pulls 25 YouTube videos, NotebookLM synthesizes them into a research brief plus an infographic. About 10 minutes from prompt to output.

After this guide, you can go deep on any topic an afternoon at a time instead of a week at a time.

Two pieces. One paid, one free.

You need Claude Code on a Pro or Max plan, and a free Google account with NotebookLM access. That's the whole stack. Claude Code installs Python for you if it's not already there. NotebookLM is free at notebooklm.google.com.

There's no pre-made skill to download. One prompt tells Claude Code to build two skills on the fly using two open-source libraries.

One thing to know up front. notebooklm-py is unofficial. Google hasn't blessed it and could change the underlying interface at any time and break this pipeline. It works today. It might not work next quarter. If that risk matters to you, this isn't the right fit.

Paste this into Claude Code.

This one prompt builds the YouTube research skill, installs notebooklm-py, and wires everything together. Open Claude Code, paste, and accept everything it asks for.

I want to set up an automated research pipeline connecting Claude Code to NotebookLM. Please perform the following steps and I will 'accept' all your proposed changes:

1. Build a YouTube Research Skill: Create a custom Python-based skill using the yt-dlp dependency. This skill should be able to scrape YouTube metadata, including video titles, views, author, duration, and URLs based on a search query.

2. Integrate NotebookLM-PY: I want to use the unofficial Python API for NotebookLM created by Teng Lin. You can find the repository and installation instructions here: https://github.com/teng-lin/notebooklm-py. Please install the necessary packages and set up a skill that allows you to:
   - Create new notebooks
   - Upload YouTube URLs as sources
   - Request analysis and deliverables like infographics, slide decks, and flashcards

3. Guide me through Authentication: Once the tools are installed, remind me to open a separate terminal window to run the notebooklm login command so I can authenticate with my Google account.

4. Confirm Readiness: Once everything is installed and the skills are recognized, let me know you are ready for a test run.

The goal is that once this is finished, I should be able to give you a single command like this:

"Use the yt-research skill to find the 25 latest trending videos on [YOUR TOPIC]. Once we have those videos, send them over to NotebookLM using the notebooklm skill. Give me its analysis on the top findings, then have NotebookLM create an infographic in a handwritten / chalkboard style depicting that analysis."

Important: If I give you the research command without specifying a topic, ask me what topic I want to research before proceeding.

The one step people get wrong.

When Claude Code tells you to authenticate with NotebookLM, open a completely separate terminal window. Not the one Claude Code is running in. A new one.

On Mac, press Cmd+Space, type Terminal, hit Enter. On Windows, press Win+R, type cmd, hit Enter. In that fresh terminal, run:

notebooklm login

A browser opens, you log in with Google, you're done. Close that terminal when it finishes. Go back to Claude Code. It'll confirm the skills are installed and ask what topic you want to research.

One command. Ten minutes. Done.

Once setup is confirmed, give Claude Code a research command. Swap the bracket for your topic.

Use the yt-research skill to find the 25 latest trending videos on [YOUR TOPIC]. Once we have those videos, send them over to NotebookLM using the notebooklm skill. Give me its analysis on the top findings, then have NotebookLM create an infographic in a handwritten / chalkboard style depicting that analysis.

Paste it. Replace the bracket. Hit enter and walk away for ten minutes.

The output is a synthesized brief plus a visual summary, both built from 25 expert sources. Not a Google summary. Not a generic answer. The actual positions of the actual people you wanted to hear from.

What this is actually for.

The trick is asking the right question. The pipeline is only as good as the prompt you give NotebookLM at the end. Generic gets you Wikipedia. Specific and layered gets you the kind of synthesis a paid research analyst would charge for.

Here's one I ran. I wanted to understand how the top creators in the AI tutorial space structure their content. The full prompt:

Use yt-research to find the latest videos from Matt Wolfe, Wes Roth, MrEFlow, and AI Explained. Send them to NotebookLM. Give me a synthesized brief on: (1) what content formats are working right now, (2) where these creators agree on what to cover, (3) where they disagree on what's worth covering, (4) what hooks they each use in the first 5 seconds, (5) what tools they each say are worth learning. Then create an infographic summarizing the patterns and the contradictions.

Same shape works for almost anything that used to be a research project. Market research. Competitive intel. Learning a new domain. Content prep. Decision making with bull and bear cases.

Five things to avoid.

1. Running the login command inside Claude Code's terminal. It has to be a fresh window with no other Claude process running.
2. Skipping the topic specificity. "Tell me about AI agents" gets you Wikipedia. "What do these five builders say about AI agents, where do they agree, where do they disagree" gets you a research brief.
3. Pushing more than 25 videos at once. NotebookLM has a source ceiling and the synthesis quality drops fast above that.
4. Trusting the pipeline forever. notebooklm-py is unofficial. Keep a backup workflow.
5. Reading the brief once and moving on. The output is the input for your own writing or decision. Read it twice. Pull the three things that surprised you.