How AI agents & Claude skills work (Clearly Explained)

Ross, Mike, welcome back to the pod. By the end of this episode, what are people going to learn? I hope I'm going to share some wisdom on how you can use the agents better. There's a lot of information going on right now. I disagree with most of it, and that's what we're going to talk about. So at the end, whether you're building something, using an agent for some sort of work, you have the best output possible. And is this going to be a technical? dive or you know non-technical person can anyone can watch this there's going to be a lot of diagrams that's all you're going to make it clear to understand the concepts right easy okay basics let's go so the first thing that i want to announce previous episodes we probably disagree with this point but now what's true is the models are good the models are exceptionally good Opus 4.6 is amazing. GPT 5.4 is amazing. I know there's like two sets of camp where, especially when it comes to programming, people are like, oh, Opus is the better UI designer. GPT 5.4 is a better backend. Generally speaking, we've reached a point, we're not at AGI yet, where we reached a point where the models are good, but context still matters. And you have the power to steer the models in a direction where you can get quality or you can get slop. And that's what I really want to talk about. But before we get into all that, and feel free to cut me off because this topic excites me, we need to learn how context works. And context is the model assembling information that it needs to execute an action. And the way the context is assembled, let's say in the coding agent, but really in any sort of agent, is there's this general system prompt, usually by the model provider. So for example, cloud code leaked recently. And one of the cool things that especially as a developer, I got to do is I got to read the system prompt. So they have this general system prompt that guides the model on how to act, what to do, what not to do. The system prompt is very important. And then you have a lot of people have agent.md files or cloud.md files. Now I'm just going to say off rip, 95% of people don't need this. The reason being is, again, you have to assume that the models are already good, right? Now imagine I told you, Greg, every time we're about to shoot a podcast, Greg, you need a microphone. You know, you need a microphone, right? You've done this plenty of times, right? So if I'm building like, let's say a website with Cloud Code and I'm telling Cloud Code, this code base uses React. I don't need to because it has the code base in context. It can check the code, right? So there is this disparity where a lot of people are putting a lot of onus on the harness and the context building. And I'm low-key starting to strip things off. Like I'm going super, super minimal because again, not to sound like an anthropic or open AI shill. Unfortunately, I have not been acquired. None of them are paying me, but the models are really, really good. Wait, so 95% of the time, I don't even need to bother with an agent MD file? You don't. Unless this is some sort of proprietary information. Yeah, what is the 5% of the time I should care about it? Proprietary information that maybe is specific to your company or some methodology that is specific to you that has to be referenced in every single conversation. Because the annoying part with an agent.MD file is every time you go back and forth with the agent, it's added in the context. right the cool thing about skills and i'm going to talk about skills in a second the way skills are designed the skills are used in a way that's called progressive disclosure meaning when you have a skill file the entire thing isn't added to context it's just the title and the description so the agent has the title and description in the context and when you let's say you have a notion report skill right and you tell your agent hey i want you to create a notion report it's then going to check its context and be like oh i have this skill Let me check out the entire document. So it's not in the context. What's in the context is the name and the description, but that's enough for the agent to be like, oh, this is a skill I need. Let me go use it, which is fantastic. I'm a skills maxi. And I'm going to show later in the episode, like how you craft the perfect skills. But with agent.md and claw.md files, it's context being added at every turn, right? So let's say you have like a thousand. like line file claw.md and let's say that's like 7 000 tokens you're spending 7 000 tokens on every run now do you need to most likely not it probably should be a skill but if you have some sort of company proprietary information or like there's something specific that you do that the model needs to know at every single turn then you use it the thing is 95 of people don't have that right so i'm not a fan unless that's the case And the reason being is we're wasting tokens, right? It's in every single turn. But this is where the beauty of skills come. I'll show my screen here. Your skill, again, this is not like word for word how it looks, but a skill basically looks like this. There is a name, there is a description, and then underneath is a bunch of information. I'm going to put a bunch of info. When you create a skill.md file, What gets added into the context is actually just the name and the description, right? The bunch of info doesn't get added. So imagine you have two sentences versus an agent on MD that has like a thousand lines that get added into the context. We're talking thousands of tokens compared to a couple hundred. And the agent only gets the bunch of info when it realizes it needs this skill. So if I have, let's say, a certain way of generating a report, a certain way of structuring my code, why would I put that in the agent.md file when I can have the agent call on it progressively when it needs it, right? So this is why skills are honestly like I'm a shill, I'm a maxi, but people do it wrong. And I'm going to share the right way on how do we create skills. So, so far we have the system prompt, the agent.md. the skills, and then we have the tools, right? So if you're using cloud code, there's already built-in tools, a read tool, a write tool, like there's many tools that it uses. This has to be added into the context because the model, the model doesn't call the tools. Like it's the agent harness around it that allows it to call the tools. And then in this case, we also have our code base, right? Like whatever, if we're building a web app, a mobile app, I know most people here won't care for the specific framework. And honestly, we're getting to a point if you're not technical, you really shouldn't. and then we have the user conversation so this is what the complete context window is filled with right and this can total up to let's say like at the beginning this could be like 20 000 tokens and as the conversation continues to grow you might reach your limit of 25 250 000 tokens and that's when you see both cloud code and open ai codex they they'll compact right so beautiful so far right this is how context works why skills are important and how you should generate skills. Let's say I have a specific workflow. For example, for my YouTube channel, we're at a point right now, Greg, where we get sponsors now. Crazy. When I first came to the pod, not a thing. We get sponsors now. It was just your mom sponsoring the channel. Yeah, it was just her showing love, feeding me. But now we get sponsors. I get a lot of emails. some are good some are bad and it's a lot of time i'm sure you're aware to comb through and to check so i have an open claw agent that has its own email right i don't have it i don't haven't given it access to my email because there's like attack vectors and i've been hacked before so i'm very careful with these things but it has its own email and every time i get an email from like a sponsor i forward that email to the agent now the first time i told my open cloud agent i'm going to forward you emails check every 15 minutes when you have an email and when you check the email do research on a sponsor and tell me if they're worth it that's all i told the agent every sponsor email i sent it it was like legit legit legit perfect perfect perfect there was no like there was no rejection there was no this is bad or these guys are a scam or this product's not good like there was no deep research being done by it so then i realized huh okay The model needs a step-by-step guide. This is when I create a skill. But here's the problem. A lot of people will, I'll just write it down here, will identify they have a workflow, right? You have some sort of workflow, and then they'll jump to create the skill right away. This is the, let me click hide here. This is the worst thing you can do. I'm just going to draw arrows to signify that this is bad. You don't do these. And the reason why you don't do this is imagine you hire an employee or you're mentoring somebody. Correct me if I'm wrong. You're probably going to tell them what to do. And if they ask you questions on how to do it, you'll help them. You would ideally like them to fail. And then you want to then tell them, no, this is how you do it. Like there needs to be some sort of experiential learning. The way I've been creating skills, Greg, and I have like 100% hit right now when I tell my agent to do something specific, is I actually walk with it step-by-step on doing the workflow. So in the case of my YouTube analysis, I told the agent, okay, I just sent you an email. Tell me about the company. Companies this, this, that, and that. Okay, check their Twitter, check their YouTube, check their Trustpilot, check if they've raised any money. If two of these don't exist or are not in good standing, automatic rejection it checked and it was like you're absolutely right i was using opus um these uh this is not a good company and then it would just we would we have a spreadsheet in google sheets it'd be like no contact it's so frustrating too right because you're like you give it a task and it seems like so binary like right or wrong and then when you tell it hey like why didn't you look at the trust pilot why didn't you see if they've raised money you're absolutely right yeah absolutely it's like what And the thing is, the reason why this is the case is the models actually don't think. they're predictors of tokens right so when you give it english when i give it english it maps it on this vector graph and then it looks for the closest resemblance and it says this is the response right so when you say what is the capital of france it maps it again on this graph and it says oh paris is pretty close by then it gives you paris it has no it doesn't think it doesn't understand it feels like it understands it feels like it thinks heck it even feels like it has emotion that's because it's been trained on so much data but it actually does not know how to think and this is where a lot of people will be frustrated with like, why is it not understanding me? You have to walk with it. So I told it, okay, this is how you research. And it's like, okay, it researches. And guess what? This is part of the context. And I'm like, okay, now that you're done researching, when it's a good company, these are the qualities you look for. And then when it's really good, send me an email. And then once we had a successful run and we did it again and again, then I converted it to a skill. The reason being is a lot of people create the skills themselves, or I mean, they'll use the AI to create the skill, but it doesn't have the context on what a successful run looks like, right? Because most of the times, especially if you're using OpenClaw, it's probably going to fail at the API call. It's probably going to call the data wrong. Like there's so many places it's going to get wrong. And I see a lot of people saying, it's just so frustrating. This is terrible technology. Why doesn't it work? It's because you don't understand how an agent works, right? It will mimic you perfectly, but you've given it nothing to mimic, right? I will do the workflow myself. So the updated version is identify the workflow, go back and forth and teach it. So I'm doing it. I'll be like, okay, first do the research. Here's the result. And I'm like, what do you think about this? Oh, these guys are terrible. You're absolutely right. Okay. You should go to the Google sheet and mark this as bad company. I've done that. Once I've had that back and forth, then I tell the AI, review what you did, and then create the skill. So now it has actual context with how it worked, and it's going to create the skill beautifully. I don't handwrite skills. I don't think you need to. You can use AI to do it. They even have a skill to create skills, skill exception. But you should have the context of what a successful run looks like. And this is why, by the way, Greg, I don't install skills. Like I've seen people like, oh, this notion skill, this social media skill, whatever. I'll review it. I'll check it out. I'll even give it to my AI and be like, oh, what are some things we can learn from this? But I don't download skills because your agent needs the context of a successful run, which you then turn to skills, right? And this is the big thing I see. You see skills marketplaces. You see download this and that. First of all, it's an easy way to attack somebody. So I would be very, very careful with downloading some random person skills. but second of all again it's all about context right it's all about and you know open claw has a memory layer and all these type of things you want it to do the right thing and the only way it can do the right thing is if you give it the proper context and to me the best way to create a skill is to work with it in your specific workflow once you have a successful run tell it okay review what you just did this is the skill you need to create i'll pause here i mean it makes sense right because If you hired an employee, you would do the same thing. You wouldn't just be like, okay, go do this thing. Good luck. And by the way, this is how you're going to go do things forever. You would map out a workflow. You would identify what right and wrong is. You would do it iteratively. And then once you've gotten to that point, you would codify it. 100%. And I think that's the thing. We should treat models and these agents. like very new employees versus like these black magic boxes that like know everything right they know everything because they've been trained on a lot of data but they don't know your workflow your steps right so i see a lot of people who have you know 15 like right off the rip they'll set up open claw and um 15 sub agents 30 skills Yet you haven't even set up your own workflows, right? And these things are cool right off the bat. And there's a perfect time to use sub-agents. I use sub-agents a lot. But the way you build, like I call it scaling for productivity, not scaling for what looks cool, right? Like I've seen like, for example, Paperclip. Paperclip looks awesome, cool. I used it, I loved it, right? But I think people would be more productive if they built up from scratch their own version. Meaning like, okay, you have your own like, you know, like editor, right? Content creator. So you're, you're asking people to do the work. A hundred percent, a hundred percent. And cause the thing is, it's like, look, I'm in the position where like people using like these beefed up things make a lot more sense. for me and the reason being is like i can build a product like that like i know what your audience wants i know what my audience wants like you know heck i spin up agents and build this thing right but if i'm going to be completely honest if you want to scale for productivity it starts with one agent and you building up the skills and then okay now you've built up some skills and now you add a sub agent and your one agent manages multiple agents right like imagine this like imagine i start a company and off rip i have 10 employees never managed a team in my life, heck, I don't even have a really big family. So like I'm alone, you know what I mean? So it's like you have to sort of, yeah, it's not sexy. And I apologize if this is not the cool thing people wanted to hear, but you sort of have to put in the work and build it up. And I personally believe you're building skills, like your personal human skills, not skill.md files, that when the models get better, when the agents get better, you will be more valuable. Because at the end of the day, as long as there's no new paradigm for models, LLMs just predict tokens. They don't understand or know the way you and I do, right? And this is why, although like the job scene and all this stuff is scary, I genuinely believe anyone who knows how these tools work and like knows how to build agents and like craft skills and like knows how to make them productive, we're in for a good run. So you're saying that if you know how to do this, you won't join the permanent underclass. The permanent underclass. So is the permanent underclass basically like, I've seen this on Twitter a lot. Is that basically AI has replaced you? So now you're just. From what I understand, it's once AGI comes, all these white collar workers are going to lose their jobs. And if you don't know how to build skills, use AI. People say you're joining the permanent underclass. That's the term. It's permanent too. That's scary. So I just have a little bit of time left. Yeah. By the way, it's ridiculous to call it a permanent underclass. Yeah, because that's terrifying. I can understand underclass. But permanent. Like you say, there's no hope. Yeah. I mean, we are in like. knowledge that took 20 people, 20 years to acquire is now like 20 bucks a month, right? So there is like a huge shift, right? People who are non-technical are, I think I saw yesterday, like some guy hit like a hundred million dollars and he vibe coded the whole app. I think it was him. 1.8 billion. Billion? Yeah. So you know what I mean? Like it is the, there is a shift, right? And I think this idea of like, I love how you were like billion, you were about to just leave this podcast and just be like, No, you know what it is? I just realized, man, I overthink things. I just need to drop the thing, release the thing. And there's wisdom in that. There needs to be this level of delusion, which I don't have. I'm trying to work on where you're like, this is just going to work out. We're just going to launch the product. It's going to succeed. And if it doesn't, on to the next one. Because 1.8 billion. Yeah, dude. Like B? B. USD? Yeah, we're not talking Monopoly. Because it was Canadian. it's it's um we're not talking carny coins we're talking we're talking real benjamin yeah yeah that makes sense that makes sense but yeah like i i hope this like understanding of like again i personally don't think you don't need an agent.md file unless you have something proprietary um skills are valuable build your own though build build your own like you know like when you asked your mom when you were a kid oh can we have mcdonald's and she's like we have food at home we have food at home build your own skills for coding perspective from coding wise um a lot of the companies model companies have realized that the agents are really good at writing code particularly typescript and this is why there's been like you see this advancement with like cloud co-work and like even open claw really what they're doing under the hood is they're writing code right they're writing code calling apis and all this stuff so when it comes to building a project um you actually don't need skills or like you don't need an agent md file specific to the tech stack you use like i remember we used to i'm using react and you know convicts or i'm using next.js and superbase i'm using this and i'm using that and you put that in the all these lines for the most part, unless again, you have a specific, specific workflow, unnecessary. And the reason being is code itself has become context now. So the more, the more important thing is starting with a solid foundation. Templates used to be big back in the day. People made lots of money with templates. I believe templates are going to have a Renaissance because if you have a solid like template, right? Like whether it be like for a web app or mobile app, Because that becomes context for the agent, it's going to build on top of that, right? And again, I didn't need some large agent.md file. I didn't need any large cloud.md file. What I needed was, again, minimal context usage and skills. So if there's anything anyone can learn from me is build your own skills. Build your own skills. And there's this methodology. I don't know if I've shared this with you, recursively building skills. So let's say you've built your skill. Right. I have I'll draw a diagram because why not? Let's say I have a workflow. And after you like setting up my workflow with an agent, I've decided, you know what, I'm going to turn this into a skill. Right. So this is my skill.md. Now, here's the thing. Even though you have the skill.md, the agent at some point is still going to mess up because there's probably gaps in the information it has in the skill. when it messes up i'm going to work with it again how do i work with it you messed up try calling the api again try doing this again or even asking when it tells you oh i failed i couldn't do this task believe it or not when you tell the agent why did you fail when you ask it like what's the error that you got it will tell you descriptively oh i got a 505 error you uh you have insufficient credits like oh okay so it's a credit issue fine so i would tell it that and then I would pass that failure back to the agent. So let's say it did something wrong. We identified the failure. All I did was asking it. I will give that failure back to the agent. I'll be like, you failed here. This didn't work. Fix this. It's going to fix. It's going to write code. It's going to do whatever it does. Once it fixes it and it's done it right, now you tell it with the new fix, update the skill so this doesn't happen again. I have like for my YouTube channel, I have like a report generator. It calls Notion, Dubb Analytics, YouTube Analytics, Twitter Analytics, it pulls from like eight data sources. There's no way you're going to one prompt and the agent's going to do it. But every time I tell it to do that work when it takes like 10 minutes, it executes it flawlessly. Why? I went through five loops of this, five iterations of recursively building this skill. And that skill is so good. if anyone's going to if like skills marketplace is going to be a thing there's going to be people who sell skills like really well defined like step-by-step skills because people are just creating them without having built out the workflow with the agent right so use the workflow by hand like telling it each step once it's done it completely create the skill.md file continue to use it it's going to mess up when he messes up you Thank God you don't complain because a lot of people are like, oh, it messed up. I'm angry. No, this is a moment where you identify the error, tell it, this is the error, fix it. It'll fix it itself. And then you tell it to update the skill file so that this doesn't happen again. So that's a little bit about shifting your expectation, right? Because people just assume it's going to work in the beginning. You're saying basically it's not going to work initially. There's going to be two, three, five, six hiccups. And over time, it should be good so this is most people's expectations right yeah and the way i've personally experienced is it's like this so there's like this early area of investment that you have to make that sucks that nobody will tell you especially agent harnesses company because they wouldn't raise as much money if they did but like this maybe i would give it two weeks because it took me two weeks like open claw when i first set up open claw I thought the same thing. I'm like, what is this garbage? Like, it doesn't understand anything. It's confused. And then I realized, like, oh, like, let me go lower level. The models and the agents, like, they don't think like you and me. I could tell you, hey, Greg, we need a report on, like, you know, the financials and notion. Because you probably were in the same business, we worked together, you would understand, based on the context you have of the business, what that means. But imagine a new guy joins, like, yeah, I need a report on the financials. So where do I even start? You know what it reminds me? I wonder if we can put this clip in. But in The Office, you watch The Office? I am not an Office watcher, unfortunately. There's a clip that there's a new boss and the new boss goes to Jim, one of the main characters. Yeah. And he asked for a rundown. So go The Office, The Office, Rundown. Oh, no. Basically, Charles. The whole episode is about Jim trying to ask around and be like, what is a rundown? Like, what is a rundown? He's like calling his dad, like, what is a rundown? You know what I mean? He's just, he didn't have the context. Yeah. He didn't have the context. Yeah. And it goes back to my initial point. the models are really really good now but the context matters more than anything right so when you see like these large agent like companies and sub agents and again i'm not saying those don't work but i'm saying probably won't work for you off rip because you haven't built it up to get to that point right so let's say like for me for example i started with um one agent let me draw this i started with one agent and this was like my main agent this did everything right this checked my spreadsheet this checked my sponsor's email and all these type of things and once i had like predefined workflows let's say for like working with sponsors then i can actually have a sub-agent what's the purpose of the sub-agent the sub-agent does all the marketing stuff right but i'm not creating the sub-agent for the sake of creating it It's going to have skills. It's going to have context. And it actually makes sense for me to have sub-agents, right? So I've built out my thing to like, now I have five sub-agents. I have one for marketing, one for business, one for personal, and that's it. And I'm willing to bet if I want open claw to open claw with anyone, my system is more productive because I didn't scale for what looks cool. I scaled for productivity. That was a bar. That was a huge bar. We got to clip that. I was just thinking that clip, that's going to rip. Yeah, that was a bar. What else do you want to leave people with? This is the main point. Yeah, we've got to the point where the models are good. The models are really good. The context matters plus the harness, right? So for example, there was this benchmark, although I'm not 100% supporting it, that there was a difference between the quality of output. that cursor generated versus cloud code versus codex, right? So what that tells me is that we've reached a point where the models are really, really good. They're probably going to get better. The next iteration is probably going to get better, but the harness and the tools that you surround it, the context that you give it is going to matter even more. And just like in everything in life, less is more. right? Like building up step by step, making it productive for you first before you add the shiny new thing. Like, because I tried all these tools all the time, like especially Paperclip. Paperclip blew up and a lot of people have been talking about it and it's fantastic. But I'm willing to bet if people took two weeks to build up to the version, because you can prompt OpenCloud to do all that stuff. If they built up their own version of Paperclip in two, three weeks where like they're building things that they actually need, their productivity level will skyrocket through the roof. To hot take. It's a hot take. Might get me in trouble. No, it won't. Who's it going to get you in trouble with? Maybe Perfect Clip releases a billion dollars and they don't acquire my podcast. I think, listen, you're out there, you're trying things and you're just sharing what you're learning in real time. Things can change, by the way. Two weeks from now, it could be like, no, give the agent everything. There's this new memory paper that Google released and now it has the ability to index information and stuff. As it pertains to real life, less is more, simple is better, right? If you can't explain it in a few sentences, you probably don't really understand it, right? And I find that the models are trained on so much information, especially when it comes to programming, building and like, and what do you call like day-to-day work, like financial work or like any sort of like, you know, checking contracts and stuff. Like the model companies are focusing on that, like on white collar work. The models are really, really good. What matters more is the harness and the tools you provided. And the one thing that you and I have that the models don't have is my specific workflow, my specific taste, my specific strategy of doing things. And those can be codified in skills, right? This is why like skills make sense when you build them. Not if you download my skill, like I have this one skill, like again, don't download it. I'm telling you now, do not download it. Don't use it. I just put it so I can get some GitHub stars. I have this one skill, and it's literally a code structure skill. And I'll put the mark down so people can see it. It's 116 lines. It's basically after AI has generated a bunch of code. I like it structured in a certain way, so it's easy for me to review it. And like I mentioned earlier with skills, the only thing that gets added into context is the name and description. so when i look at the name it's code structure when i look at the description use when multiple workflows duplicate the same operational logic when deciding that blah blah blah blah some nerd stuff so when i tell the agent i want to clean up the code structure It checks the skills it has. It sees the name. It reads the description. It's like, oh, this makes sense. Then it progressively discloses, meaning once it realizes it needs this skill, then it adds the rest of this, right? Versus if this was my agent.md file, imagine every single time and we can actually check how many tokens this is. Let me check. What was it? OpenAI token tokenizer. If I go to this. So this is 944 tokens. So if this was an agent.md file, every single time I have a chat, I'm adding 944 tokens. Tokens ain't cheap now. But if I just have the name and the description, it's just 53 tokens. And it's not even cheap. It's just like you're not trying to hit the limit quicker than you need to hit the limit. Because the model will get dumb as the context window closes, right? So if you have like a context window and I can draw this out, if this is your context window and like the optimal is you're between like there's always like maybe like 10% already filled with all the system prompt and all that stuff. You want to be between like. you know, fresh to like 70% because the closer you get to 99, 100%, like 99, 90, 80%, it starts to get done, right? And you could think of this like a human. Like imagine you throw a bunch of information again and again and again and again. And this is why like when I like was in school, like last minute studying never worked for me because like I didn't pay attention the entire year. Now I have to learn about polynomials and I have to do these graphs and there's this weird notation. it's impossible for me to catch up right and it's the same way with the agents you want to keep your context when you want to save your context because it saves you money but not only that it makes a more performant um agent so less is more less is more rely more on the model strengths and what the model needs is what's unique and special about you your workflow your business not general knowledge don't tell the model use react it knows to use react don't tell the model um you know things that like should already be known for the like, you know, tasks. Like, for example, like, let's say I'm doing a financial report and in the agents.md file, I say to denote money, use a dollar sign. It's going to use a dollar sign right now. If you have a specific currency, then you like, oh, use this currency. This is the you know, like for something that the agent won't do. always clearly breaking down things we uh i have to be real with you you weren't gonna come on the show today i wasn't and i'll be honest i i told greg and i'm just gonna be frank i'm like i don't have that banger you know something new drop in let's review it because if we gonna be honest there are not that many tools dropping nowadays like unfortunately the big dogs are running the show yeah um the clods and the the anthropics and the open ai especially when it comes to general purpose and and coding they sort of run the game so they're releasing updates and like all the stuff has already been covered so i was like greg i don't know if i have anything valuable and what did i say you're like the people you know you got to think about impact you got to think about what you know this could apply to someone's and you showed me like a testimony right like i sent a text to you yeah i'm gonna pull it up uh i sent a text to you of someone who saw a video that we did together and that video got him into coding now he's running a cake business and he's making $150,000 a year and growing and he said the Greg and Ross Mike episode in November last year is what got me into coding I've recommended to everyone asking how to start out and I just sent you that text and I said it's not about the numbers it's not about you know because you said in the text You don't see it sometimes, right? I need everything we do to get to 200K views minimum. And I'm just like, I hope this gets 200K views or more, so like and comment to juice those algorithms. But if it gets 2,000 and two people end up taking this information and changes their business, their productivity, how they think about things, and I think that's why... I think that's why you and myself have been put on this planet Earth is to inspire people to get their creative juices flowing. And so I thank you for coming on and taking time out of your day. And I appreciate the motivation. And yeah, I hope this helps somebody and I can't wait to be back with more. Absolutely. All right. Catch you later, dude.

I sit down with Ras Mic to break down how AI agents actually work and why most people are using them wrong. Ras Mic explains the mechanics of context windows, makes the case that agent md files are largely unnecessary, and shares his step-by-step methodology for building custom skills that make agents dramatically more productive. Whether you're coding with Claude Code or automating workflows with OpenClaw, this episode gives you the foundational knowledge to stop wasting tokens and start getting real results from your AI tools.

Timestamps
00:00 – Intro
00:42 – The Models Are Good Now
01:20 – How Context Windows Actually Work
04:55 – The Power of Skills
09:17 – How to create Skills
16:35 – Skill Maxxing
19:05 – What you need too build a project
20:40 – Recursively Building and Improving Skills
29:23 – Context Window Management and Token Efficiency
33:02 – Closing Thoughts

Key Points

* The models (Opus 4.6, GPT 5.4) are exceptionally good now — the differentiator is the context and harness you build around them.
* Agent md and claude md files get loaded into context on every single turn, burning tokens and degrading performance as the context window fills up. 95% of users can skip them entirely.
* Skills use progressive disclosure: only the name and description sit in context until the agent determines it needs the full file, saving thousands of tokens per conversation.
* The best way to create a skill is to walk through the workflow with the agent step by step, achieve a successful run, and then have the agent write the skill based on that real context.
* Recursively refine skills by feeding failures back into the agent and having it update the skill file so the same mistake is avoided going forward.
* Scale for productivity by starting with one agent and building up workflows before adding sub-agents — start simple, then expand.

Numbered Section Summaries

1. The Models Are Good — Context Is What Matters

Ras Mic opens by declaring that the current generation of models, Opus 4.6 and GPT 5.4, are exceptionally capable. The conversation is no longer about which model is "better" in a general sense. What matters now is the quality of context you feed them — that is what separates quality output from slop.

2. How Context Windows Work

Ras Mic walks through the anatomy of a context window: system prompt, agent.md files, skills, tools, the codebase, and the user conversation. All of these stack up as tokens, and the window has a hard limit (around 250,000 tokens). When you hit that limit, agents compact — and performance drops. Understanding this structure is the foundation for everything else in the episode.

3. Skills and Progressive Disclosure

Skills solve the token-bloat problem. A skill file contains a name, description, and the detailed instructions — but only the name and description are loaded into context. The agent reads the full file only when it determines the skill is relevant. This means a skill costs roughly 53 tokens per turn versus 944+ for an equivalent agent.md file.

4. Building Skills the Right Way

Ras Mic shares his methodology: identify a workflow, walk through it with the agent step by step, correct mistakes in real time, and only create the skill after you have completed a successful run. He illustrates this with his sponsor email screening agent — the first attempt returned all-positive results because the agent had no criteria for rejection.

5. Recursively Improving Skills

Even after a skill is created, the agent will still hit edge cases and fail. Ras Mic treats each failure as an opportunity: identify the error, have the agent fix it, then tell the agent to update the skill so the failure is documented. After five iterations of this loop on his YouTube analytics report generator, the agent now executes flawlessly across eight data sources in about ten minutes.

6. Scaling for Productivity Over Flash

Ras Mic started with a single agent handling everything — email, spreadsheets, research. Only after building reliable skills did he add sub-agents for marketing, business, and personal tasks. He argues that jumping straight to multi-agent architectures (or adopting tools like Paperclip without building foundational workflows first) optimizes for what looks cool rather than what is productive.

The #1 tool to find startup ideas/trends - https://www.ideabrowser.com/

LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/

The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/

FIND ME ON SOCIAL
X/Twitter: https://twitter.com/gregisenberg
Instagram: https://instagram.com/gregisenberg/
LinkedIn: https://www.linkedin.com/in/gisenberg/

FIND MIC ON SOCIAL
X/Twitter: https://x.com/Rasmic
Youtube: https://www.youtube.com/@rasmic