WEBVTT

00:00:00.000 --> 00:00:02.160
You've probably seen Claude everywhere

00:00:02.160 --> 00:00:06.960
lately, and I'm gonna say something that might sound like hype, but I genuinely

00:00:06.960 --> 00:00:12.800
mean it. Claude is currently the strongest AI tool available to most people in 2026,

00:00:13.175 --> 00:00:17.495
not because of just one feature, but because of the combination.

00:00:17.655 --> 00:00:19.975
Claude is built around three pillars.

00:00:20.055 --> 00:00:21.255
Claude itself,

00:00:21.335 --> 00:00:28.750
the assistant which we are going to be using today, Claude code, is for shipping software, and then Claude

00:00:28.750 --> 00:00:51.065
co work which is the agentic layer that runs tasks on your computer while you are doing something else. Now I want you to watch this. I can just type in one sentence to offer me a video about why most people get bad results from AI tools, and then Claude pulls in my voice, my audience, my hook formula, my structure introduces

00:00:51.065 --> 00:00:55.705
a script that I'd actually film, and all it took was just one prompt.

00:00:56.050 --> 00:02:17.115
The whole system fires just from using that one prompt. Now that doesn't happen out of the box. There's a full setup, and I'll show you exactly how to build your very own in this video. And also, I've got dedicated walk throughs on Cowork and also Claude. Those are linked inside our free school community. The link is down in the description below. Go and check it out. But right now, let's get on to the video. Okay. So we are starting off with step number one that is picking the model, turning on web search, and basically so that you know what you are paying for. Okay. So there are three set of decisions and they take about thirty seconds each. So the first one is the model. So Sonnet is what I'm gonna be using today. It's fast, it's sharp, it handles about 90% of what you'll throw at it. And then Opus is what I switch to when I need Claw to actually think. So that's more for strategy and research. So anything where the answer matters more than the speed, if you get what I mean. And on that note, Haiku, I never ever touch it. And then the second part is web search. Okay. So in settings, I'm gonna toggle it on and then make sure to leave it on and half the claw doesn't know recent stuff, complaints that people are actually filling out these days. Literally, it's because they never ever flipped on the switch. Now we get on to step number two and that is the prompt rewrite. So I typed in, write me a content plan for my YouTube channel, and here's what it came back with. Consistent posting schedule, know your audience, mix educational

00:02:17.115 --> 00:02:18.315
and entertaining.

00:02:18.635 --> 00:02:22.315
And, I mean, you could have googled this all the way back in 2015,

00:02:22.315 --> 00:02:34.500
and that was eleven years ago. Now Claude isn't isn't necessarily bad, it's just that the prompt here is bad. So Google trained us to ask short questions and to expect good answers.

00:02:34.820 --> 00:02:58.530
Now that works for search, but when it comes to Claude, it doesn't necessarily work. So what I would say is the way you should reframe this, it will change everything. So Claude is good when you treat it like like it's a new person that you are hiring for your business. It's bad when you treat it like Google. Now if you hired someone on Monday and on day one, you said write me a content plan, what would they do? They produce exactly what Claude just produced,

00:02:58.850 --> 00:03:01.810
uh, to be generic, to be pretty basic.

00:03:01.970 --> 00:03:27.380
But to change it up, you can brief them on who you serve, what you've tried, and also what is working. You want to give them something that is usable. Now it's the same thing here. Make sure that you have three things in every prompt. So number one, the role. So what is Claude operating as? Not you are the expert because that's pretty vague. You are helping me to build a YouTube channel in the AI tool space targeting small business owners.

00:03:27.540 --> 00:03:43.135
That's a lot better. Then you wanna make sure that you're giving it context. So your situation, what you've tried, what's working, what isn't working. The more specific you are, the better the output is. And I mean, it gets so much better. So now let's get on to number three, and that is the output shape.

00:03:43.295 --> 00:03:43.695
So

00:03:44.130 --> 00:04:00.285
the format, the length, the tone that you are going for. If you want a table, then say that you want a table. Don't just expect that it's going to give you a table. If you want three options, say give it to me in three options. If you want it to sound like you without it, then paste in a writing sample and say match this.

00:04:00.605 --> 00:04:17.030
Now watch me rebuild this. Okay? So I'm gonna say, you are helping me plan content for a YouTube channel in the AI tools niche. My audience is small business owners curious about AI but not technical. I post once a week. My last three videos got between 8,022

00:04:17.030 --> 00:04:35.545
views. The 22,000 view video was a tutorial. Give me five video ideas leaning into the tutorial format with a one line hook for each and make it a numbered list. There you go. It's the same model, the same Claude, but it's now output that you can actually use.

00:04:35.785 --> 00:04:37.865
Now if you wanna play or move over here,

00:04:38.505 --> 00:05:16.990
when you don't know what context to give it, and most of the time you really don't, just flip the script. End the prompt with before you write anything, ask me questions that you need answers to do this well. Claude will then interview you. You give it answers and then it writes. The output is almost always better than anything that you'd have prompted yourself because Klaud knows what it needs better than you do. So now that is prompting at its finest. The ceiling breaks when you stop typing context every single time and start building it in. Now we get on to step number three and that is the memory.

00:05:16.990 --> 00:05:24.030
So just a quick detail from what we are doing because this is the gap in every other Claude tutorial.

00:05:24.365 --> 00:05:27.885
Claude has a global memory across every conversation,

00:05:28.205 --> 00:05:44.400
not just a project, not just the skill, the whole account. It learns who you are, what you are working on, and how you like to be talked to. Now here's the move that actually unlocks this. You've got months of context built up in another AI tool. Let's say GPT,

00:05:44.480 --> 00:06:08.220
let's say Gemini, whatever it is. You don't have to start over. In the memory settings, there's an import memory option. So Claude gives you a prompt and then you paste it into your old AI tool and it spits out a summary of everything it knows about you. Then you just copy that back into Claude and now hit add to memory and then years of context. That's all being ported in just about five minutes.

00:06:08.460 --> 00:06:13.820
The single highest leverage hour that you'll spend on your AI setup this entire

00:06:13.820 --> 00:06:26.255
year, and it's such a game changer. And almost nobody ever talks about this. Now Claude knows you. The rest of the bold assumes that's too. That takes us perfectly onto step number four, that is the artifacts.

00:06:26.335 --> 00:06:31.855
So this is what I built in the time my coffee took to brew. Okay? Working

00:06:31.855 --> 00:06:33.135
IOI calculator.

00:06:33.360 --> 00:06:47.280
There's an hourly rate. It's manual hours per week, weeks worked a year, calculates annual cost, time saved at automation, IOI on a $5 setup. It runs in the browser in just one prompt,

00:06:47.705 --> 00:06:49.225
no code whatsoever.

00:06:49.705 --> 00:06:50.905
That's an artifact.

00:06:51.225 --> 00:07:08.050
So when you ask Claude for something substantial like a tool, a calculator, a dashboard, a landing page, it doesn't reply in chat. It opens a panel and then it builds the thing. So here's the prompt that I use. Bold me an ROI calculator for business owners considering AI automation inputs

00:07:08.290 --> 00:07:09.170
hourly

00:07:09.170 --> 00:07:10.050
rate,

00:07:10.210 --> 00:07:15.730
manual hours per week, weeks per year, and the outputs must be annual cost

00:07:16.025 --> 00:07:22.025
time saved with 70% automation, annual savings, ROI on a $5,000

00:07:22.025 --> 00:07:24.185
setup, clean, simple,

00:07:24.265 --> 00:07:25.625
mobile, usable,

00:07:26.025 --> 00:07:31.530
simple. But you see, I'm going into detail. And that took me about ninety seconds, maybe even shorter,

00:07:31.770 --> 00:07:34.730
and and now I have a working calculator.

00:07:34.970 --> 00:07:43.290
And I mean, I didn't actually love the colors. So what I did was I just typed in, make the button dark and the background white.

00:07:43.725 --> 00:07:45.645
And it updated it live.

00:07:45.805 --> 00:08:18.495
Now you can just talk to it like you were giving it feedback or like you were giving feedback to a designer, I should say. Then what you're do is you're hit publish, you're gonna copy the link, and now you have a tool that can be embedded on your site. Can send this to clients or you can use it as a lead magnet. Developer would have taken so long to create this and on top of it they would have charged you so much, but here you just got it done. ArtFX also handle the file uploads. Keep that in mind. So what you can do is you can drop a PDF, a CSV, a screenshot, a 200 page contact right into the chat if you want and then just watch this.

00:08:18.735 --> 00:08:21.775
So now I'm exporting my YouTube analytics as a CSV

00:08:22.120 --> 00:08:53.140
for the last ninety days, and then we just drag it over, we drop it, and then we say analyze my performance trends and visualize the key metrics. And then Claude actually generates a full analytics dashboard inside an artifact. It gives me charts, top performers, all the patterns that I would have missed. It gives it all to me, and the same move works with screenshots, contacts, photos of a whiteboard. All you do is just drop it in, and then you ask the question, and you get the analysis. Now artifacts are insane on their own, but they are disposable.

00:08:53.140 --> 00:09:01.380
I mean, a new chat, fresh slate, Claude basically forgets everything. Now the next feature is what makes Claude actually remember

00:09:01.380 --> 00:09:04.340
who you are, and that takes us on to projects.

00:09:04.635 --> 00:09:09.195
So a project is a workspace with its own memory, its own files, its own instructions.

00:09:09.355 --> 00:09:16.635
You basically just come back to it. So for our YouTube workflow, I'm creating a project called YouTube scripting

00:09:16.890 --> 00:09:39.365
and three things happen inside this project. Okay? So that is the files, I doubt my brand guidelines, a sample script in my voice, and a one pager of my audience. And these are going to live permanently over here. Every So conversation in this project has access to them. And then the next thing that happens is instructions. This is where I tell Claude how to behave inside this workspace.

00:09:39.445 --> 00:09:47.550
I basically tell it, you are helping me write YouTube scripts. My audience is small business owners learning AI tools, my tone is direct and conversational,

00:09:47.630 --> 00:10:16.820
there's no corporate language, no bullet points in the script body, always reference the uploaded brand guidelines and voice sample before nighting. And then the next thing is conversations. So now I'm inside the project. I'm typing the same prompt that I used at minute three, and I'm saying give me five YouTube video ideas. And now take a look at the defense. It knows my niche. It knows my tone. It knows that tutorials outperform opinion pieces. Why? Because I told it that in the project files.

00:10:16.900 --> 00:10:19.460
So it's not a better prompt.

00:10:19.700 --> 00:10:34.375
It's basically a better environment. And now if you wanna pair it up, account level memory is for you. The name, level, the communication style, the project instructions are for the slice of work. Voice format deliverables,

00:10:34.455 --> 00:10:44.870
keep all of them separate and if you claim everything into account level, then Claude actually starts giving you weird hybrid responses when you switch context.

00:10:44.950 --> 00:10:53.675
Now projects only work inside one project. Now what if you want Claude to behave a certain way everywhere?

00:10:54.155 --> 00:10:57.435
That's what we are going to be talking about next, and that is skills.

00:10:57.595 --> 00:11:05.035
So here's where most people stop, and it's the most expensive mistake in your whole setup. Right now, every recurring task, proposals,

00:11:05.115 --> 00:11:07.620
LinkedIn posts, script outlines,

00:11:07.700 --> 00:11:44.270
you either retype a long prompt or you paste one that you saved somewhere else every single time, and over time it adds up to quite a lot of wasted time. Now skills breaks that ceiling. A skill file is instructions that Claude reads automatically when the task matches. So you describe the workflow once, then Claude learns it, and from that point on, you just say, write me a LinkedIn post. And now Claude already knows your format and knows your tone and knows your hook style, your CTA without you having to re explain everything. And I mean, the mechanic that makes this work is progressive disclosure.

00:11:44.430 --> 00:11:52.345
Claude only loads the skill that is relevant right now. You can have 50 skills installed and Klawd doesn't get any slower,

00:11:52.585 --> 00:12:05.000
just more capable over time. So a quick note, projects are a workspace. MCP, which is the model context protocol, is the connection layer. So it's basically how Claude talks to your other tools.

00:12:05.160 --> 00:12:12.520
Skills are the how to sitting on top of both. So now in one line, MCP is the kitchen and skills

00:12:12.760 --> 00:12:19.665
are the recipe. You don't write the skill file yourself. Claude writes it based on what you described.

00:12:19.825 --> 00:12:29.610
So I would say I want a skill that writes LinkedIn posts for me. The tone is direct and a little punchy and short sentences, no corporate language, no hashtag spam,

00:12:30.090 --> 00:12:33.850
and every post opens with a one line curiosity

00:12:33.850 --> 00:12:39.850
hook and delivers one specific insight and ends with a question or CTA in under 150

00:12:39.850 --> 00:12:50.525
words. So then Claude is gonna ask me a couple of questions, I answer it, and then it generates the skill file, and then I just scan through it, I give it the few tweaks here and there, and then I just simply hit install.

00:12:50.685 --> 00:13:35.320
So now in a new chat, would say write me a LinkedIn post about why most people get bad results from AI tools. Okay. Then just watch what happens. Now the hook is under a 150 words. It sounds just like me, and I didn't explain any of that in this prompt. The skill handled all of it for me. And when it doesn't necessarily work, then the one line debug that no one else shows you, you're about to see now. So sometimes you install a skill and Claude just for some reason ignores it. Now if it does, then here's the fix. What you need to do is type in when would you use the LinkedIn post skill and then Claude quotes the skill descriptions back to you and the second it does that, you'll see exactly

00:13:35.320 --> 00:13:50.475
what's vague. So maybe the trigger condition is too narrow, maybe the description doesn't match how you actually phrase the task. Edit just one line and then you reinstall and then it works. And that's the entire troubleshooting process

00:13:50.715 --> 00:13:57.515
right there. Now you don't have to build every skill from scratch. Anthropic ships a directory, Notion, Figma, Atlassian

00:13:57.700 --> 00:14:07.460
plus official ones for Word, Excel, PowerPoint, PDF. All you do is just click the plus, you browse, and then you install. So if you've never ever used skills,

00:14:07.860 --> 00:14:16.255
that's how I'd start. Now what you do is you pick one that matches something that you would actually do, and then you just watch it fire, and then you build your own.

00:14:16.575 --> 00:14:26.735
Every recurring task in your work is now a skill. Not a prompt that you have to retype over and over, not a doc that you have to copy from. A skill that fires automatically and produces

00:14:27.330 --> 00:14:44.845
the right output every single time. Now we have to go into step number seven and that is the custom instructions. So custom instructions are the always on briefing that every Claude conversation starts with. Now before you type a word, before Claude reads your prompt, it reads your instructions,

00:14:44.845 --> 00:14:53.645
every chat, every time. Some people will tell you not to use account level instructions because they bleed into context where they don't fit.

00:14:54.045 --> 00:15:19.565
They have a point with that. Now if you write a generic 800 word bio, then the fix isn't avoiding custom instructions. It's writing them tight enough that they apply universally. Now let's explain this in five sections. Who am I? The name, what I do, what I'm building, who I serve, two or three sentences and not a not a full massive bio. And then the second thing is how I want Claude to talk to me. So the tone, the length, the formatting.

00:15:19.565 --> 00:15:23.420
I want direct short sentences, no bullet points unless I ask,

00:15:23.580 --> 00:15:25.100
no great question,

00:15:25.260 --> 00:15:27.500
um, no em dashes.

00:15:27.740 --> 00:15:41.315
Just write it down and Claude follows it. And then what I'm working on right now, which is the current goals, the current projects, and what I'm pushing on this month, Update this every week, and it keeps Claw pointed at what actually matters.

00:15:41.635 --> 00:15:57.350
So how I work, um, when do I sleep, how I make decisions, or what I need when I'm stuck versus when I'm in a flow. Now this is cool because it changes the quality of strategic conversations. And then what to never do, the deal breakers. So my no corporate hedging,

00:15:57.590 --> 00:16:10.525
no important to note, no suggesting I hire someone when I'm asking how to do it myself, no lists when I ask for a paragraph. So the sharper this section is, the less you'll correct Claude midsection

00:16:10.605 --> 00:16:22.300
or mid conversation, I should say. And then the last thing is keep it tight. So mine are always about 200 words across all five. So if you are writing more, then step out anything that isn't

00:16:22.300 --> 00:16:23.260
load bearing.

00:16:23.500 --> 00:16:27.580
And this is a briefing. Keep that in mind. It's not a biography,

00:16:27.580 --> 00:16:35.775
so you don't need to give it so much. Cool. Now I'll give it the same prompt. So before the custom instructions, it was generic. It was formal. It was bullet pointed. Now after,

00:16:35.935 --> 00:16:42.335
it's direct. It's in my voice. It's formatted the way I want it, and it's the same model, but different briefing.

00:16:42.495 --> 00:16:59.270
So now we have to go on to step number eight, and that is the connectors and the research mode. So two more pieces and the workflow is complete. So connectors, it's the plus icons and then it's the add connectors. So this is where Claude plugs into the tool that your work actually lives in. The Gmail, the dive, the calendar,

00:16:59.270 --> 00:17:37.925
the Notion, those Slack. So I'm connecting it to my Google dive and now when I'm inside the YouTube scripting project and I say pull my channel positioning dock and use it to inform the next script, then Claude doesn't need me to upload anything. It reaches into my dive, it finds the dock, it reads it, and it applies it, and the information lives where it lives. Claude pulls it on demand whenever it needs it. So now the connectors that save the most times are the ones that are plugging into wherever your actual work happens. So for a content creator, that's Google Drive or your Google Calendar. For an agency owner, it's Gmail or even Notion.

00:17:38.085 --> 00:17:50.940
And all you have to do is that they just pick one to start. Now for the research mode, it's plus icon and then it goes over to research. So it's different from web searches because web searches gives Claude the Internet for one quick answer.

00:17:51.100 --> 00:18:22.380
Research mode is autonomous. So you give it a question and it builds a research plan. It runs multiple searches that build on each other and the cross references the sources and it comes back with a fully cited report, so five to fifteen minutes for most queries. Now for YouTube, I use it for competitive research. I would give it something like research the top five AI tutorial channels above 100 k subs, what hook formulas do they use, what video links perform, what topics overlap, synthesize it into a positioning brief, and then it comes back with citations,

00:18:22.540 --> 00:18:25.355
patterns, gaps that I could actually exploit.

00:18:25.595 --> 00:18:35.355
And it used to take about half a day of manual work on my side. Now it's about five minutes while I'm making a lunch. Then all you do is just use it for anything that needs thoroughness,

00:18:35.355 --> 00:18:37.595
not speed, competitive analysis,

00:18:37.595 --> 00:18:51.270
market research, big decisions that you need to make. And now just one little bonus for you in the model selector, there's an extended thinking toggle. So turn it on for hard problems. So such as like things like strategy,

00:18:51.270 --> 00:18:52.630
financial analysis,

00:18:52.790 --> 00:18:54.390
multi step reasoning.

00:18:54.390 --> 00:18:56.230
Claude actually takes longer,

00:18:56.230 --> 00:18:57.505
but it reasons

00:18:57.905 --> 00:19:03.985
through the problem step by step. So your result is actually better. The output is noticeably

00:19:04.145 --> 00:19:30.915
better across the board when the thinking actually matters more than the speed. So here's the payoff. If you start the bandwidth chat inside the YouTube sketching project, then custom instructions are loaded, memory is loaded, the skills is installed, and the dive is connected. So I just type in one sentence, draft a video about why most people get bad results from AI tools. Then it pulls in my channel positioning dock from the dive and it uses my standard script structure. Now watch how it works.

00:19:31.475 --> 00:19:39.300
Custom structure is hit. The the project loads my voice and my audience. The dive connector pulls the positioning dock, the skill triggers,

00:19:39.300 --> 00:19:41.220
and it applies my script structure.

00:19:41.300 --> 00:19:48.260
And now the output that I get is a draft that I actually film with my hook, with my pacing, my CTA preferences,

00:19:48.340 --> 00:19:53.885
and it's all in my voice. Now compare that to the cold start prompt that we had earlier.

00:19:54.125 --> 00:20:02.685
Write me a content plan for my YouTube channel. And here you can see the difference isn't even close. It's the same model, the same chord, but completely different results

00:20:02.970 --> 00:20:06.970
because the system is doing the work, not the prompt itself.

00:20:07.290 --> 00:20:10.010
And that's the workflow rebuild.

00:20:10.010 --> 00:20:14.650
Now that's pillar one. Everything else Claude co work, Claude code,

00:20:14.650 --> 00:20:17.610
it sits on top of what you just built.

00:20:18.105 --> 00:20:22.265
So if you like code, if you build internal tools, or if you automate anything technical,

00:20:22.265 --> 00:20:40.440
then my Claude code walkthrough is next. That's where Claude builds apps, websites, read your entire code base, and it ships features from a single prompt. If you want Claude actually doing work on your computer while you are in another tab, opening up apps, moving files, running multistep tasks autonomously,

00:20:40.680 --> 00:20:43.240
then my coworker walkthrough

00:20:42.945 --> 00:20:58.305
is the one for you. The templates, my custom instructions, the exact skills that I use, and the rest of my workflows are all in our free school community. The links are down in the description below. Go and check it out and also check out the video that's popping up on screen right now. Like and subscribe, and I will catch you on the next one.