The argument in one line.
NotebookLM is a free, source-grounded RAG-and-deliverables engine that Claude Code can drive programmatically, replacing a multi-hundred-dollar research stack with a five-minute setup and near-zero ongoing token cost.
Read if. Skip if.
READ IF YOU ARE…
- You use Claude Code regularly and want research capabilities without building or paying for vector database infrastructure.
- You find yourself manually copying YouTube links into NotebookLM or pasting information between tools.
- You want structured deliverables (infographics, slide decks, audio overviews) from a corpus of YouTube content without writing custom RAG code.
- You are comfortable running terminal commands but do not want to build a full embedding pipeline from scratch.
SKIP IF…
- You need a production-grade API with SLAs -- notebooklm-py is browser-automation-based and can break on NotebookLM UI changes.
- You want to analyze private or paywalled content; this pipeline relies on public YouTube captions via yt-dlp.
The full version, fast.
NotebookLM is Google's free source-grounding tool: paste in URLs, it indexes them and generates audio overviews, slide decks, infographics, quizzes, and mind maps. The bottleneck has always been the manual sourcing step. This video eliminates that by connecting Claude Code to NotebookLM via notebooklm-py, an unofficial Python API built on browser automation, plus a custom yt-dlp YouTube search skill. One terminal prompt now handles the full pipeline: search YouTube, push top videos as sources, run analysis, and receive deliverables -- with heavy synthesis compute offloaded to Google at no token cost.
Members feature
Chat with this breakdown.
Modern Creator members can chat with any breakdown — ask for the hook, quote a framework, find the exact transcript moment. Unlocks at T2: refer 3 friends + add your own API key.
Create a free account →Where the time goes.
00:00 – 01:15
01 · Intro
Hook: Claude Code as the most powerful research agent but needing one added tool; promise of a zero-cost research stack; NotebookLM introduced as the missing piece.
01:15 – 04:32
02 · Demo
End-to-end live run: YouTube search skill finds 20 trending Claude Code videos; uploaded to a new NotebookLM notebook; NotebookLM returns top 5 skills and emerging trends; blueprint-style infographic is generated and lands in the project folder.
04:32 – 08:22
03 · Setup
Installing notebooklm-py; running notebooklm login to authenticate via Chrome (one-time); installing the NotebookLM skill; building or downloading the YouTube search skill.
08:22 – 10:08
04 · Walkthrough
Step-by-step replay: /yt-search, reviewing sources, creating a notebook, querying for the number one skill, watching NotebookLM answer, and triggering deliverable generation.
10:08 – 11:08
05 · More Resources
CTA for free School community (YouTube search skill MD file) and Chase AI+ paid Claude Code masterclass.
Lines worth screenshotting.
- NotebookLM is a free RAG-plus-deliverables engine; the bottleneck has always been manual source loading, not the analysis itself.
- When Claude Code orchestrates NotebookLM, the token cost for large-scale synthesis drops to near zero because Google's compute handles it.
- notebooklm-py gives programmatic access to everything the web UI offers, plus batch downloads and exports the UI does not expose.
- The YouTube search skill uses yt-dlp metadata only -- no video download -- so it runs in seconds at zero cost.
- Claude Code skills are markdown files with trigger phrases; Claude lazy-loads them so a large library does not inflate the context window.
- The Skill Creator (Meta-Skill) is the most recommended starting point because it teaches the skill format while building the first skill.
- Querying across 20 YouTube sources simultaneously in NotebookLM would require a custom vector database if built manually; here it is a one-line prompt.
- All NotebookLM deliverable types are accessible via notebooklm-py CLI commands.
- The pipeline fragility is the browser-automation layer; any NotebookLM UI update can break the unofficial API.
- Deterministic steps belong in Python scripts; probabilistic steps belong in the LLM layer -- that split makes the architecture composable.
Claude Code is most powerful as an orchestrator, not a monolith.
WHAT TO LEARN
Routing expensive synthesis work to a free external tool while using Claude Code only for coordination is a structural decision that cuts costs and removes rate limits simultaneously.
- When a task involves reading many sources and producing structured outputs, the model doing that work sets the cost ceiling -- outsourcing it to a free grounded system changes the economics entirely.
- Unofficial APIs built on browser automation are fast paths to integration validation, not production dependencies; they require maintenance on the other party's release schedule.
- A grounded knowledge base (sources you chose, indexed and queryable) produces more reliable synthesis than asking a model to web-search and summarize, because the source set is known, bounded, and citable.
- The yt-dlp metadata-only pattern -- pulling titles, views, duration, and captions without downloading video -- is reusable for any pipeline that needs YouTube data cheaply and quickly.
- Skills that separate deterministic steps (Python scripts) from probabilistic steps (LLM calls) are more debuggable and more reusable than monolithic prompt chains.
Terms worth knowing.
- RAG (Retrieval-Augmented Generation)
- A pattern where a language model answers questions by first retrieving relevant passages from a defined document set, grounding its output in those sources rather than relying solely on training data.
- notebooklm-py
- An open-source Python library by Teng Lin that wraps NotebookLM via browser automation, providing a CLI and Python API for creating notebooks, adding sources, querying, and generating deliverables programmatically.
- yt-dlp
- An open-source command-line tool for downloading video and metadata from YouTube; used here only for metadata scraping without downloading video files.
- Progressive Disclosure (skill loading)
- Claude Code loads only a skill's name and description at startup; full instructions are loaded just-in-time when triggered, keeping context usage low.
- Skill Creator (Meta-Skill)
- An official Anthropic-developed Claude Code skill that guides users through building new custom skills by asking clarifying questions and generating the full skill.md, scripts, and folder structure automatically.
Things they pointed at.
Lines you could clip.
08:32
“Claude Code isn't doing this analysis. Claude Code isn't spending tokens. It's only spending a small amount of tokens to send that request to NotebookLM and bring it back. But all the thinking is done by Google, and they're paying for it.”
03:20
“If you try to recreate what Notebook LM does... it would be a gigantic pain in the butt to do. As someone who has tried it... it's not a simple process. Furthermore, it costs money, and this whole thing is free.”
Word for word.
00:00Claude code might be the most powerful research agent on the planet, but you need to add this one tool to unlock it.
00:08Now most people's version of Claude code research is just telling it to use the web search tool and praying that whatever it comes back with is good enough. But we can do better. Because what if I told you with just five minutes of setup, we could create workflows inside of Cloud Code that are able to scrape any section of YouTube, pull their captions, push that information to a free robust prebuilt rag system that is able to do all the heavy lifting and analysis for us, and then take that analysis and give us deliverables like slide decks, infographics, podcasts, you name it, all while costing us virtually 0 tokens.
00:46Now if that sounds way too good to be true, you would normally be right, but not in this case. So let me introduce you to the most underrated AI tool in the game today, NotebookLM.
00:58So in today's video, I'm gonna show you how to combine the powers of ClaudeCode and NotebookLM to replace a research stack for free that would otherwise cost you hundreds of dollars a month to build and maintain.
01:11I'm really excited to show you guys this one, so let's hop into it. So let's kick this video off with a demo so you can see how we can use Claude code to harness all the features of Notebook LM without us ever leaving the terminal.
01:24Now this prompt's gonna have ClaudeCode do a number of things. First, we are gonna use our custom YouTube search skill to find the latest trending videos on ClaudeCode skills. And don't worry, I will show you all these skills and how to get them in a second.
01:37After we find the video URLs, I want Cloud Code to send those URLs over to NotebookLM using the NotebookLM skill.
01:45I then want NotebookLM to do analysis on those videos to figure out what are the top load skills, and I wanna get that analysis sent to us. Furthermore, I want a deliverable.
01:54I don't just want the text analysis. I want an infographic in a handwritten blueprint style depicting that analysis on the top skills.
02:03So with one prompt, we are going to scrape YouTube. We're going to source all of our data. We're going to essentially put it into a rag system because that's what Notebook LM is.
02:13We're gonna have Notebook LM do all the analysis and the deliverables for us off-site, which means we don't pay for that in tokens, we and get all that for free. So let's see how it works.
02:23So here's what we got. Claude code uploaded 20 YouTube sources into notebook l m for analysis. Notebook l m then came back with the top five Claude code skills that you see here as well as emerging trends for how they're used.
02:36It then created that infographic deliverable for us which automatically populated inside of our project folder. So here's a look at that infographic. Again, this is Nano Banana Pro under the hood.
02:46It's actually being called. And the text here and all the visuals, a, fit the style that we called for, which was like a handwritten blueprint type style. And secondly, and more importantly, all this content is based on the videos and the analysis of those videos.
03:00This is it isn't just making stuff up. And we can also see here inside of Cloud Code the videos it grabbed, the title, the creator, the views, the duration, and the date. And all this is reflected inside of Notebook LM itself.
03:10I can see all the sources it upload. I can see all the analysis. I can see the blueprint guide that we asked for.
03:18And while this demo might seem like a rather simplistic application of this, I cannot stress enough the value add of combining these two tools because this goes way beyond just automating the source process for Notebook LM. Everything we did here, could have done manually inside of NotebookLM. Right?
03:33I could have gone through YouTube manually. I could have found all the videos I want. I could have copy pasted them in.
03:38I could have gotten the analysis and I could have gotten the deliverable. The fact that we can automate that is nice, but it's more than that. It's the fact that I can bring all that analysis into my Cloud Code ecosystem effortlessly, and the use cases of that workflow are pretty much infinite.
03:54And the second reason why this combination of tools is so powerful has everything to do with the straight up power of Notebook LM. If you try to recreate what Notebook LM does, which is like a scraping system into a rag system, into an analysis system, into a deliverable system, right, with the infographics, the slide deck, all of that, it would be a gigantic pain in the butt to do.
04:15As someone who has tried it, at least on the research side with things like NADN, it's not a simple process. Furthermore, it costs money, and this whole thing is free, which is in large part why I'm so excited to share it with And another reason you should be pumped is because how simple it is to set this whole thing up, which is what we're going to cover now.
04:32So when it comes to setting this up, you're probably thinking, hey, Chase, how do we actually connect NotebookLM to Cloud Code? Considering the fact that NotebookLM does not have a public API.
04:41But luckily for us, there's people much smarter than you or I who have already solved this problem. In this case, it is Tang Ling, and we will be standing on his shoulders today as we use the NotebookLM dash py GitHub repo to essentially act as an unofficial Python API for NotebookLM.
04:58But before we set up NotebookLM, we need to solve the first part of our pipeline, which is actually the YouTube search and the sourcing of the data we want NotebookLM to do analysis on.
05:09And for that, I have a custom YouTube search skill for ClaudeCode that does all of this for you. It uses a Python script that relies on the y t dash d o p dependency to scrape YouTube's metadata for us. So when I ask it for, hey, Claude code skills, it's just like us going on YouTube and searching in Claude code skills.
05:28It grabs title, views, author, all that important stuff. And this skill you see right here inside of Claude code teaches Claude code how to best use this script. Now there's two ways to get this skill and this script up and running.
05:42The first is rather simple. You just go inside a Claude code and explain that you wanted to build this custom skill for you, that you wanna use the y t d l p dependency to create a custom YouTube scraper. Or if you want this entire YouTube search skill setup m d file, and you can just download it and hand it to ClotCode, you can do that too.
06:01And you can get it by heading to my free school community, which you can find a description for. Now speaking of my school communities inside of Chase AI plus, you can also find my Claude code master class, which I just released a few days ago. So if you're someone who is kind of in the beginning of their AI journey and is trying to figure out how can I best leverage Claude code even if I'm not technical, I really wanna master what is definitely the most powerful AI tool in the game, well, that's the place for you?
06:25And if you're interested in that, just check the link in the pinned comment. So once you download the YouTube search skill setup file, just give it the Claude code and tell it to go to work or you can just manually prompt Claude code to build it for you. Now let's head back here and set up the notebook l m connection.
06:39So I'll put a link to this down in the description as well, and the install is pretty simple. So to install this, we are just going to copy these commands, paste it inside of our terminal, which means, hey, if you're looking at Claude code, you're wrong. You need to open a second terminal that looks like this and paste in those commands.
06:55After you run these initial installation commands, what you wanna do is scroll down here, and we're gonna have to run one more command in the CLI, that's the notebook lm login command. Same thing as before, head into another terminal, paste this in there. That's going to open a new window in Chrome.
07:09All you have to do is log in. You just have to do it once and you're all set. Now after you authenticate with the Notebook LM login, there's one more thing you have to do and we need to do the skill.
07:20So to do the skill inside of Claude code, right, you can either run this command in the terminal or just tell Claude code to do it. So understand also what we've done. We've done two things on the Notebook LM side.
07:31You have the skill, and then you have, like, the actual API of the program. Remember, skills are just prompts.
07:37It's just text telling Claude code how to do something in a specific manner. So all this information you see here about, hey.
07:44Here's how we generate content. Here's how we create the notebook. This skill is teaching Cloud Code how to do that.
07:50So once it's installed, you just need to tell Cloud Code, hey. I want you to use NotebookLM to create flashcards or an infographic or slide deck.
07:58It's that easy. Everything's just in plain language. And if you're wondering what exactly you can do with this program, well, it's all here inside of the GitHub.
08:04Anything you can do in Notebook LM manually, you can do with the API and some. As you can see here beyond the web UI, we can also do batch downloads, export the quiz and flashcards, etcetera etcetera.
08:16So we actually get more functionality using this program than you would do just loading up NotebookLM yourself. Let's So actually go through it one step at a time so you understand how it's working.
08:25So the first thing is that YouTube search skill. So like any skill, we can either use it as a slash command or you can just use plain language. But if I do y t dash search, you see we have query and then the count.
08:37So what are we looking for? Hey. We're looking for Claude code skills.
08:41And so while in the demo, we did everything at once. I think it's useful to break it up sometimes so you can first get eyes on what your sources are actually going to be. So here's the results it comes back with right at any time.
08:53We can also check the YouTube links ourselves. And what's nice with this skill is it will also give you some insight about what's actually going on with what it brought back. So if you're happy with the sources, now we can push it into NotebookLM.
09:04So again, you can just use plain language. Create a new notebook in Notebook LM titled chase demo with these sources we just pulled. And we can see it created the notebook, now it's gonna be populating it with its sources.
09:14So after a couple minutes, all 20 sources are loaded, and you're limited to 50 sources with Notebook LM. At this point, you can have Notebook do whatever you want. So we can say based on those videos, what does Notebook LM believe is the number one Cloud Code skill?
09:26Now, again, the cool thing with this is all this analysis is offloaded. Cloud Code isn't doing this analysis.
09:33Cloud Code isn't spending tokens. It's only spending a small amount of tokens to send that request to NotebookLM and bring it back. But all the thinking is done by Google, and they're paying for it.
09:43So Cloud Code grabbed NotebookLM's analysis, and we can see that reflected here inside of notebook l m itself.
09:50So you can always double check and click inside of notebook l m if you want to see like what captions it's referencing to. And this cadence also applies for all the deliverables. So right, if you want the audio overview, the mind map, flashcards, the infographics, anything you see over here on the right, just prompt Claude code and it will do it for you.
10:06It's that easy. So how you end up leveraging this research workflow is ultimately up to you, but I really can't stress enough how wild this thing is. It seems pretty simple on the surface, but I'm telling you, if you've tried to deal with anything like this, especially with the YouTube video stuff and actually trying to create some, like, corpus of knowledge from these videos in a way that Claude code or some other agentic coder can interact with it, it's pretty difficult.
10:31Right? And it's very time consuming, and it can be rather brittle. Yet all of this is abstracted away for free with Notebook LM.
10:39So I think this is an awesome tool. I hope you can get some use out of it. As always, like I said before, all the resources can be found in my school communities.
10:48If you need the MD file for the, uh, skill, for the YouTube search skill, make sure you see that in the free one. And, if you're a little more serious about this stuff and you're like, I really just wanna have, like, a Cloud Code master class that gets me from, like, zero to AI dev, make sure to check out Chase AI plus. So let me know what you thought of this in the comments.
11:05And as always, I'll see you around.
The Hook
The bait, then the rug-pull.
The promise sounds absurd: one terminal prompt that searches YouTube, indexes results into a grounded knowledge base, runs cross-source analysis, and ships a blueprint-style infographic -- all while Claude Code spends almost no tokens doing it. That is the actual demo in this video, and it holds up.
Named ideas worth stealing.
00:12model
The Token-Offload Pipeline
- Search (yt-dlp skill)
- Source (notebooklm-py upload)
- Ground (NotebookLM indexes)
- Analyze (NotebookLM query)
- Deliver (notebooklm-py generate)
A five-stage orchestration pattern where Claude Code handles coordination and a free external tool handles the expensive synthesis.
Steal forany research or content-production workflow where analysis is the expensive part
03:40model
Claude Code Skill Anatomy
- skill.md entry point with trigger phrases
- Progressive disclosure loading
- scripts/ subfolder (Python/JS)
- /references/ folder for assets
- Deterministic steps in scripts; probabilistic steps in LLM
The structural blueprint for a Claude Code skill, synthesized by NotebookLM across 20 YouTube tutorials in the live demo.
Steal forbuilding any reusable Claude Code skill
How they asked for the click.
10:08link
“All the resources can be found in my school communities. If you need the MD file for the YouTube search skill, make sure you see that in the free one.”
Soft double CTA: free community for the skill file, paid masterclass for deeper training. No hard sell.
Visual structure at a glance.
