10:36Nate Herk | AI Automation · Listicle
I Tried 100+ GitHub Repos for Claude. These 6 Are the Best
A talking-head rundown of ten Claude Code tools the creator uses daily, from scriptable video editing to security testing and SEO.
October 11thThe argument in one line.
A free Claude Code skill turns seven AI personas built from scraped public material into a standing advisory council that debates real decisions in three rounds and returns a scored, conditional verdict.
Read if. Skip if.
READ IF YOU ARE…
- You use Claude Code and want a repeatable way to stress-test a real business decision before you commit to it.
- You're curious how to build persona-based AI sub-agents with a deep, consistent 'brain' instead of a single generic prompt.
- You run or want to run a creator/community business and like seeing the exact install path for a free tool, not just a demo.
SKIP IF…
- You want a line-by-line installation walkthrough inside this video. It's a tour of how it works, not a setup tutorial.
- You're looking for the actual advisor brain files here. You'd need to pull the repo yourself from the link in the description.
The full version, fast.
Nate Herk built the Roast Room, a free Claude Code skill that spins up seven AI advisors modeled on real operators (Jeff Bezos, Alex Hormozi, Gary Vee, Dan Martell, Paul Graham, Gino Wickman, Warren Buffett) to debate a business decision across three rounds: independent opening positions, a forced cross-examination when the group agrees too fast, and a final scored vote. Each advisor is a thin sub-agent routed into a deep 'brain' of markdown files built from roughly 124 sources and 1.3 million scraped words of that person's public material. The payoff is a downloadable verdict PDF plus a reusable pattern: write a good question with real options, numbers, limits, and your current leaning, and the same brain-building approach works for any domain, not just this one council.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Create a free account →Where the time goes.
00:00 – 02:19
01 · Meet the Roast Room
Cold open on the council live: seven advisors (Bezos, Graham, Hormozi, Gary Vee, Martell, Wickman, Buffett) deliberating a real decision, an Austin in-person conference for June 2027 with four lettered options, inside a visual interface sitting on top of an actual running Claude Code session.
02:19 – 03:37
02 · The Advisors Debate
Breaks down what each advisor is actually optimizing for, then shows round 1 opening positions land (all seven pick option B, averaging 7.1/10), after which the chair treats the near-unanimous read as a warning sign and assigns Buffett and Martell to argue hardest for option C.
03:37 – 04:44
03 · The Final Verdict
Round 3 votes land and the council returns a conditional verdict: run option B as a $3,000 annual plus Austin-tier plan, capped at 120 seats, with nothing signed until 50 members have paid $150K by January 15, delivered as a downloadable scored PDF.
04:44 – 06:42
04 · Get the Free Skill
Plugs the two lead magnets (the free Roast Room repo via the Skool classroom's AI Skills section, plus a free 'First AI Automation Client' SOP), shows the past-sessions library where any prior council can be replayed, and notes some questions only pull in a subset of the seven advisors.
06:42 – 07:45
05 · How the Council Works
Opens the actual project folder (renamed from 'Founder Council' to 'Roast Room') and explains the architecture: one Claude Code chair facilitates seven independent sub-agents through three rounds, chosen over running it as an agent team because it's cheaper and better preserves each persona's voice.
07:45 – 10:52
06 · Advisor Brains and Setup
Opens one advisor's files to show the pattern: a short sub-agent file (Hermozi, scoped to offer, pricing, and sales) that routes into a deeper 'brain' built from roughly 124 public sources and 1.3M scraped words, and explains that adding a new advisor means repeating the same research process.
10:52 – 13:02
07 · Asking Better Questions
The actual prompt-writing framework for getting a useful verdict: state the decision, give at least two or three real options, include real numbers, set limits like deadlines and budget, define what success looks like, and state which way you're currently leaning and why.
13:02 – 14:31
08 · Outsourcing Thinking, Keeping Judgment
The explicit thesis: the skill lets you outsource the thinking without outsourcing the understanding, and the same brain-building pattern works for any specialty, like a security agent or a CTO agent, that can then debate a decision with you.
14:31 – 14:44
09 · Next Steps
Quick like-and-subscribe close.
Lines worth screenshotting.
- The Roast Room is a free Claude Code skill that runs seven AI advisors, modeled on real operators like Jeff Bezos and Warren Buffett, through three rounds of debate to reach a scored verdict.
- Each advisor is scoped to one question: Bezos asks if a bet is reversible, Paul Graham asks if it's wanted and growing, Warren Buffett asks what it does to cash, risk, and long-term value.
- When all seven advisors land on the same answer in round one, the system treats that agreement as a warning sign and forces two of them to argue the opposite option as hard as they can.
- The council's actual verdict wasn't a flat yes: it was 'go with conditions' - run the cheaper option, cap seats, and sign nothing until a revenue threshold is hit by a hard date.
- Each advisor sub-agent is a short file that routes into a deeper 'brain' built from about 124 public sources and 1.3 million scraped words of that real person's content.
- An advisor's brain is organized into a hot sheet of 8 decision rules, named frameworks, stated positions, personal stories, and sources, not one giant prompt.
- The creator switched from running this as a multi-agent team back to independent sub-agents coordinated by one chair, because the team version cost more without producing different answers.
- A good question for an AI advisory council needs the decision itself, 2-3 real options, real numbers, hard limits like budget and deadline, a definition of success, and your current leaning.
- The system is deliberately built to not just agree with the user; stating your current leaning in the prompt lets the council push back instead of rubber-stamping it.
- Swapping in a new advisor, for a different industry or persona, just means repeating the same research-and-scrape process used to build the original seven brains.
Build a brain, not just a prompt.
AI DECISION COUNCILS
A persona only argues convincingly once it's backed by a real archive of that person's decisions, not a single prompt, and a good council needs a chair that forces real disagreement.
01Meet the Roast Room
- A panel of differently-scoped AI advisors can debate a single business decision in parallel and surface disagreement a solo prompt would miss.
- Tying a visual interface to a real running Claude Code session makes an otherwise abstract multi-agent process watchable and easy to explain.
02The Advisors Debate
- Giving each advisor exactly one question to own, like reversibility or growth, stops every persona from giving the same generic answer.
- Near-unanimous agreement in round one is itself a signal; forcing dissenting advisors to argue the losing option surfaces risks a quick consensus would hide.
03The Final Verdict
- A useful AI verdict isn't a flat yes or no; it can attach real conditions, like a spending cap and a signed deadline, to the recommended path.
- A scored, downloadable PDF turns a chat debate into something that can be handed to a team or kept as a decision record.
04Get the Free Skill
- Replayable past sessions turn a one-off AI debate into a searchable decision log instead of something you have to trust from memory.
- Not every question needs all seven advisors; a well-built system should pull in only the personas relevant to that specific decision.
05How the Council Works
- Coordinating independent sub-agents through one chair cost less than running the same debate as a full multi-agent team, with no real difference in answer quality.
- Sub-agents preserved each persona's distinct voice better than an agent-team setup, since each one only ever saw its own output plus the chair's prompts.
06Advisor Brains and Setup
- A convincing AI persona takes real research investment, roughly 124 sources and 1.3 million words per advisor here, not a one-line character description.
- Structuring a persona's knowledge into a hot sheet, frameworks, positions, stories, and sources makes it reusable and easy to swap for a different expert.
07Asking Better Questions
- A decision prompt should include the decision itself, two or three real options, concrete numbers, hard limits, and a definition of success, not just an open question.
- Stating your current leaning in the prompt lets an AI advisor system push back on it instead of just validating what you already believe.
08Outsourcing Thinking, Keeping Judgment
- The real unlock is outsourcing the thinking, not the understanding: you still have to process and judge what the council hands back.
- The same brain-building pattern used for these seven advisors can be applied to any domain you lack expertise in, from security to legal review.
Terms worth knowing.
- Roast Room
- A free Claude Code skill that runs a panel of AI advisor sub-agents through three rounds of debate on a real decision and returns a scored verdict.
- Chair
- The Claude Code session that facilitates the advisor sub-agents, reading every round's answers and deciding what each advisor argues next.
- Sub-agent
- An independent AI agent instance, one per advisor persona here, that works alone before its output is read by the chair or other agents.
- Advisor brain
- The set of markdown files behind one advisor persona: a hot sheet of decision rules, frameworks, positions, stories, and sources scraped from that real person's public material.
- Hot sheet
- A short file listing the roughly eight core rules an advisor persona uses to make decisions, the first thing the sub-agent reads before answering.
- AIOS
- The creator's personal Claude Code setup that already holds his business context, so the council can pull relevant data automatically instead of him re-explaining it each time.
Things they pointed at.
Lines you could clip.
07:10
“I used to run the roasts as agent teams but I switched back to sub-agents because I just found that the agent teams and the sub-agents didn't really give me different answers. Sub-agents were cheaper and they felt more like I was able to keep the actual real voice of whoever I was creating.”
12:57
“This roast room is basically set up to make sure that it's not just agreeing with you... they all have their own principles and they all have their own way that they think about things.”
08:22
“We went through about 124 sources, over 1.3 million words, and we put that into his brain.”
13:24
“We all have subject matter expertise in a few domains, but we won't be able to have subject matter expertise in every single domain possible.”
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
metaphoranalogy
So right here, you can see that I've got Jeff Bezos, Paul Graham, Alex Ramosi, Gary Vee, Dan Martell, Gino Wickman, and Warren Buffett sitting here in what I call the roast room. And what's happening is all of these advisors are writing their opening positions, and then they're going to have a debate about the actual question that I submitted to them.
So right here, you can see that this debate is about the Austin in -person conference in June, 2027, and they have four different options to choose from. I gave them A, B, C, or D. And what's actually going on here is this is linked to a Cloud Code session, as you can see right here, where I've shot off this prompt where I basically did a slash roast room, which is the skill that I'm gonna show you guys and give away today.
And I submitted the question with all this information about the options, business information, resources, what would success look like? And now we're able to actually sit here and watch them discuss this live. And so obviously this visual interface is kind of just a fun, visual interface that sits on top of what's actually going on.
And what's really going on is we're still running this skill inside of Cloud Code where we have these different personas and they're going to be discussing this. So I've done things in the past where I actually run a slash roast, but I've made this a little bit more formal and I've made this more formalized personas and I call this the roast room.
Now, what I think is cool is all of these personas were pulled as inspiration from the actual people themselves. Jeff Bezos focuses on one question, which is, is this the right bet and how reversible is it? Paul Graham focuses on one question, which is, is this something people actually want and is it growing?
So all of these, essentially, agents or council members are thinking about one very specific thing. Warren Buffett is thinking about what does it do to cash, risk, and long -term value? And obviously I'm going to break down how I built this and what actually lives inside of each of these specialized agents' brains, because there's a lot of data that lives inside of each of these guys' brains.
So right here you can see they actually start discussing, and there's something going on with Jeff Bezos because I have this sort of like minimized, so it looks kind of goofy, but... We added in these little animations so we can actually see them talking. They're going to give their opinion on what options.
So you can see Jeff Bezos came in with a B and he scored them. So he gave B seven out of 10 and we can see why. We can also see that Paul just went with B and he gave it a six out of 10.
Hermosi is also running B and gave it an eight out of 10. So this is basically how the council works. They're going to go through in one round and then debate.
And then they're going to go through in another round and then debate. And they'll come back to us at the end with a final vote and verdict. And I can go ahead and speed this up because...
All of these decisions have already been made. This is just, like I said, the visual interface. But in this case, you can see that all seven of our advisors here voted B and they scored an average of 7 .1 out of 10.
So now what they're going to do is they're going to read through each other's positions and they're going to fire back. In this example, they're pretty in line already, but it's really interesting when they don't actually agree and they have to try to persuade each other on why their decision is a better decision. And because I have Cloud Code open on the left, we can see what's actually being facilitated.
This is sub -agents, it's not an agent team. So that means that each sub -agent is basically talking to a chair, and the chair is facilitating the debate. So right here it says, all seven seats in round one backed a gated B, which means the chair treats as a warning, so round two is asking Buffett and Martell to argue for option C as hard as they can.
And then we're gonna see how they think about that, and then we'll see what the other founder council members think about as well. And now you can see how they're sort of like starting to make these connections between each other. They're arguing with people or they're agreeing with people.
So Gary Vee right now is talking to Buffett. Dan Martell is saying something about Gary Vee and they all start to actually come together now and hopefully they're trying to get to an overall roast room consensus. And as this is happening, you can sort of go through and you can see the key points.
You can see what round one looked like. You can see what round two looked like. And you can more specifically see what Bezos said to Gary Vee.
You could read through it here. You see, you have things like, I disagree with this. I concede here, blah, blah, blah.
Here's my stance. And you can look through all of this stuff. This is what Hermosi was saying to Bezos.
But now we're moving on to the final round, round three, which is the actual vote. And it looks like it's gonna come back and it's gonna be to go with option B, but we will see. And there you go.
You can see that they're starting to come in with their final votes. And what's going to happen after is we are going to be delivered a final verdict that we can sort of read through and see like the key decisions and the key points that were made. So you don't have to like watch this whole thing.
Usually what I'll do is I'll shoot off a couple prompts. I'll come back and then I'll just read through the verdicts. And it really helps make decisions.
And I don't always just blindly take whatever the counsel gives me. But what's helpful is to read through each of the decisions and read through the perspectives because sometimes that helps me just think about it in a different way, even if I don't actually go with their opinion. So this was basically the final verdict.
It was to go with conditions, run B as a $3 ,000 annual plus Austin tier, capped at 120 seats and signed nothing until 50 members have paid 150 ,000 by January 15th. And what we can do is we can actually download this as a PDF. So if I download this and I open this up, you can see that we get this PDF with our scores and with all of this information on each round, what they weighted and how we can sort of like...
take this, send it to our team or make a decision, whatever we need to do with it. So that was an example of what this looks like and the deliverable. I'm going to break down how exactly this works, but first I want to show you how you can get it for completely free.
You're going to go to my free school community. It's linked in the description. You're going to come in here, go to classroom and click on AI skills.
And there will be a link in there that takes you to the full repo for this roast room setup. So that is what the interface is like. You can see that if I click on past sessions, I can actually look at all the different PDFs that has been created from this roast or from the roast room.
And we could also actually replay the council. So if I went to this first sales hire or keep selling, it will go ahead and basically replay this whole thing for me, which is pretty cool. And what's interesting is sometimes the actual prompts that you use to shoot off for the roast.
it might not use all of the personas here. If it realizes that, oh, we only really need to hear from Buffett and Martell in this specific example, then it will only run Buffett and Martell. The one that we just did utilized all seven, so that was great.
But this specific council, as you can see, about first sales hire or keep selling, it only had to talk to Graham, Hermosi, Martell, and Buffett. By the way, guys, I've got this completely free SOP for you about getting your first AI automation client. It's going to go over the exact steps that has been proven for hundreds of our AIS Plus members to get their first paid gigs.
It goes over the one sentence service pitch that can get you started today, why your first client should cost you money, the five minute video that answers can this person actually deliver before you've actually... received any money. What to do when you have zero case studies.
There's so many good things in here that are going to help you out. Even if you already do have clients, I would recommend grabbing this because like I said, it's yours completely free. So if you want to grab this, there's a link for it down in the description.
Let's get back to the video. So what this means is it stores all of your sessions. So if I come back in here and I go to cloud code and I open up the files, if I go to my projects, And I haven't renamed this yet.
I used to call this Founder Council, but I can go to my Founder Council, I can go to my sessions, and I can see these different sessions that I had run, and then I can actually investigate them and look at the brief, I can look at each round, and that's basically what we're seeing in this interface. We're just seeing it in a nice, pretty way.
But of course, you don't need the interface. You could just run these Founder Council or these Roast Room sessions without the interface, but I thought the interface was a nice touch. But let's talk a little bit more about how this actually works because I think it's super, super interesting.
So what we have is the roast room. So that's basically us. And Cloud Code is essentially a chair.
It's the facilitator of the roast room. We have seven advisors like I showed you guys in the actual demo. And what happens is each of these is their own sub -agent.
It goes through three rounds where they write their opening position. Then they look at each other's positions. And then the chair facilitates, hey, you argue with him, you argue with him.
And then they go through on round three and they vote. and then everything is saved and we get a final verdict PDF. Now the reason I wanted to use sub -agents is because that way we could have one chair facilitating.
It's also cheaper than if we ran this as agent teams. I used to run the roasts as agent teams but I switched back to sub -agents because I just found that the agent teams and the sub -agents didn't really give me different answers. They were giving me very similar answers and sub -agents were cheaper and they felt more like I was able to keep the actual real voice of whoever I was creating.
it just felt more organized. So these are all their own individual sub -agents, and I will show you guys what those sub -agents look like in a sec, because like I said, we scraped through a ton of data to make these. So what that looks like is, for example, Alex Hermozy is focused on offer, pricing, and sales.
We have an actual agent file, so it's a sub -agent file that gets called in the skill, and it says, hey, you're gonna spin up this Alex Hermozy council agent. This file basically contains the way he thinks. who he is, the question he owns, and how he answers, how he makes decisions.
And it also links to all these other files that are . So the eight rules he decides by, his named frameworks, principles, positions, stories, voice, and sources. And all of this was just scraped from public stuff that he's put out there, YouTube videos, X posts, LinkedIn posts, blogs, things like that.
You can see in this specific example, we went through about 124 sources, over 1 .3 million words, and we put that into his brain. So we did that six more times with all of these other members of the actual council, as you can see right here. And the cool thing is, if you wanted to maybe swap out like Dan Martell and swap it in for someone else based on your industry or based on your use case, then you could basically just run the same thing.
You say, hey, you see how these seven advisors are set up? I want you to build me another one that's just like them, but let's build this one for, you know, Barack Obama, I don't know, whoever you want it to be.
And then they go through and they actually score every option, they weight it by relevance, and then that's sort of what's debated on. So when you actually come in here and you clone this repo, you'll basically just give your agent the link to this, and then you'll be able to just say, hey, install this, and it will put it into your project, or you could create a new project for it if you'd like.
Now what's cool is, let me open up this .cloud folder to show you what these agents look like. So in the dot cloud, we have agents. And here's where you can see we have our counsel Bezos with the brain and how you talk, how you debate.
We have Buffett, we have Gary Vee, we have Hermosi, Martel, and Wickman. We've got all of them right in here as subagent files. And you can see the subagent files are not that long.
But what happens is we're routing it to the brain. So we're saying, hey, you can read your hot MD, and then you can look in your frameworks or your positions or all of these things when you need to make decisions. And so what that looks like, if I open up our skills right here, You can see that we have these things called brains.
So in the brains, we have Hermosi, Martel, we have all these people, right? So for example, let me just open up the Hermosi brain. We have the hot, which is basically his hot sheet, which is the eight rules he decides by.
We've also got some frameworks here, like value equation and grand slam. We've got money model and client finance acquisition. These are all things that he talks about a lot if you've read his books or if you watch his YouTube videos, stuff like that.
Decision loops, signature questions, et cetera. We also have information about his books. We have frameworks, we have positions, we have sources, we have stories, stories that he has told, which is really, really interesting and it makes it feel more personal.
And then of course, like I said, we've done the same thing with these other brains. So if we look at Jeff Bezos real quick, same thing, we have the hot. goes over his worldview, eight rules he decides by.
We have his positions on certain things. We have his sources. We have his stories as well.
All of these are just a bunch of different markdown files that were scraped and created by having a bunch of agents go do research on these different people. And now we have this framework of, okay, if I wanted to add another person to our council, here's how we do it. So it's really, really a simple setup, guys.
And like I said, the visual interface I showed you in here, purely visual. You don't actually need this. The skill will do all of the same stuff.
It'll still generate the report for you. It will do all of that. But if you want to watch it, then you can watch it in here.
And the last thing really that I want to talk about here is how to actually create a good question for your council. There is obviously the idea of building a good question, but then there's also like the context. So of course, when I'm asking it questions in here.
it knows everything because it's already in my AIOS, which means if it has other questions, not only can it ask me, because if it doesn't feel like it knows enough to send it off to the council, Cloud Code will ask you, hey, in order to send it off, let me ask you this question, this question, this question. If you have your AIOS set up correctly and you have all your connections and you've got your own personal context and stories and meeting transcripts and whatever it is already loaded into Cloud Code or Cloud Code has the ability to touch those, then it will actually go pull that data and it will help the council make an even better decision because all that context already exists.
So what do you actually want to give it when you're asking a question? Give it the decision. This is what I want you to tell me.
give it options. Giving it two or three options at least is better. Otherwise it's sort of hard to like categorize what potential paths you could go down.
And it may even be more overwhelming because then you might feel like, Oh, I actually have seven paths because each persona gave me a different option. But in reality, maybe all seven are saying some combination of like option B. So give them options, give them real numbers.
So if you feel comfortable telling them like revenue and team size and things like that, that. contextualize this that are really important to actually making a decision, give that information. Give it limits like deadlines, hours, and budgets.
Give it what success looks like. This one's so important. You have to give it context on why do I need this decision?
What does good look like? And how do I get there? How should I be thinking about that?
And then of course, which way you're currently leaning and why? Because as we know, sometimes AI likes to agree with you. but this roast room is basically set up to make sure that it's not just agreeing with you and maybe it's going to convince you the opposite or maybe it's going to validate you but it's not just going to blindly do that because they all have their own principles and they all have their own way that they think about things and of course it should be very very simple once you get into this interface you can click on what to put in your question and you can look through this you can also say hey cloud code look at the roast room and help me turn this into a good roast room prompt and then you just talk for a little bit and it will turn that into a prompt and you can shoot it back in and then You basically just run the skill and the visual interface will pop up and start running through all three of those rounds.
So anyways, guys, I know that this is a very simple skill, honestly, like a very simple walkthrough of the skill and how it works and what it does. But it is something that I do use a lot. And it's something that I think that you should all get in the habit of.
It's a really important idea of being able to sort of outsource your thinking, but not the understanding and be able to leverage other people's subject matter expertise. Because at the end of the day, we're all human. And we all have subject matter expertise in a few domains, but we won't be able to have subject matter expertise in every single domain possible.
But what you can do is you can use agents to go store some of this knowledge. So let's say you're building an app in Cloud Code and you don't really know that much about security. What you could do is you could build a security agent and you would say, hey, go research everything there is to know about security.
Go read these articles, go read these books, go watch YouTube videos and store all of your knowledge in a skill or in your agent brain. And then if I have any security questions, I can just ask you. And it's just about building all these little specialized agents and outsourcing the thinking, but making sure when they come back with, hey, based on my findings, based on my research, here's what I'm recommending.
You still need to take that recommendation, process it, understand it, and don't just blindly accept what it comes back with. But building specialized people like this really helps you feel more confident in the answers you get back, especially when you have them debate each other. You could have a security agent.
And you could have like a CTO agent and you could have them discuss things and bring that verdict back to you. So it's all about figuring out how can you leverage other agents and other perspectives to help you make a decision. But like I said, guys, you can find that for completely free inside of my free school community.
But that is going to do it for today. If you guys enjoyed the video or you learned something new, please give it a like. Helps me out a ton.
And as always, I appreciate you guys making it to the end of the video and I will see you all in the next one. Thanks, everyone.
The Hook
The bait, then the rug-pull.
Nate Herk opens on seven AI advisors, built from the public words of Jeff Bezos, Alex Hormozi, Warren Buffett and four other operators, already mid-debate on one of his own real business decisions. He built the whole thing as a free Claude Code skill and spends the rest of the video taking it apart.
Named ideas worth stealing.
00:00model
The Roast Room 3-round structure
- Round 1: independent opening positions
- Round 2: cross-read + forced debate
- Round 3: final vote + scored verdict PDF
Each of the seven advisor sub-agents writes alone first, then reads every other position, then goes through a chair-assigned round built to force real disagreement before a final scored vote.
Steal forany multi-perspective AI decision tool or panel feature
09:52model
Advisor brain structure
- Hot sheet (8 decision rules)
- Named frameworks
- Stated positions
- Personal stories
- Sources
Each advisor's persona is built from public material (YouTube, X, LinkedIn, blogs, books) organized into a stable file structure any sub-agent can be routed to read before answering.
Steal forbuilding any persona-based or expert-system agent
11:04list
Good council question checklist
- The decision
- 2-3 real options
- Real numbers (revenue, team size, etc.)
- Limits (deadlines, hours, budget)
- What success looks like and why
- Current leaning and why
What to hand an AI advisory system so it has enough context to give a specific, challengeable answer instead of a generic one.
Steal forany AI advisory or decision-support prompt, not just this skill
How they asked for the click.
VERBAL ASK
04:44product
“You're going to go to my free school community. It's linked in the description. You're going to come in here, go to classroom and click on AI skills. And there will be a link in there that takes you to the full repo for this roast room setup.”
Clear single-step instruction (Skool classroom > AI Skills) placed right after the demo payoff, reinforced minutes later with a second lead magnet (free client-acquisition SOP) before the video returns to the technical deep-dive.
MENTIONED ON CAMERA
Visual structure at a glance.
