How to build Claude Skills Better than 99% of People

With AI agents on cloud code, co-work and codeex becoming more powerful by the day. Building good skills will be one of

day. Building good skills will be one of the most important things to get good at in 2026. Building agent skills allows

in 2026. Building agent skills allows anyone to automate any workflow by simply prompting it and can even become self-improving. And good skills will

self-improving. And good skills will likely become monetizable soon. So, in

this video, I'll show you why you need to learn skill engineering, show you what skills actually are and when to use them, and a simple framework to build better skills than 99% of people. Now

this guide should help you whether you work with cloud code, co-work, openai, google as they all have integrated uh skills by now. Now before we dive into what skills are and how to build them effectively, let me quickly explain why

learning skills is a big deal. Now we're

all seeing that these AI agents are getting really powerful. But no matter how good they get, they still need that specific those specific guard rails, context and SOPs around all the unique ways you and a business do things and

use software. Now we've tried to solve

use software. Now we've tried to solve this before. Of course, we have projects

this before. Of course, we have projects and custom GPTs where you set a system prompt and add context files. But

generally, the problem with these is they're isolated. You're hopping between

they're isolated. You're hopping between different windows. They don't really

different windows. They don't really self-improve and can't handle a lot of context. On the other side, of course,

context. On the other side, of course, we have NAND and automation platforms that hardcode the guardrails and make the system deterministic. And for fully deterministic non-human in the loop workflows, these are still great. But

most day-to-day work isn't actually deterministic. Uh the processes aren't

deterministic. Uh the processes aren't always clear-cut. Uh it's context

always clear-cut. Uh it's context dependent. It requires judgment. And

dependent. It requires judgment. And

that's why human in the loop is often really important to get good outputs from AI. And skills sit in the middle.

from AI. And skills sit in the middle.

They're essentially instructions for an AI agent on how to do a specific process. They can self-improve. They

process. They can self-improve. They

have human in the loop. But unlike a project or custom GPT, thousands of skills can be accessed by the same agent. And the game changer is that they

agent. And the game changer is that they can be created and updated by simply prompting. And that means anyone can

prompting. And that means anyone can start automating their tasks and workflows through a single interface on cloud code, co-work. They're also

sharable across your business. So one

person's process and domain expertise can instantly be used by the entire team which of course has huge implications for onboarding consistency and how a company operates and if thousands of these specific capabilities can be given

to one very capable general agent it seems likely uh that AI agents will slowly become the single interface for doing work. Now, of course, we are very

doing work. Now, of course, we are very early with this, but I predict that building the skill infrastructure for these agents to do specific tasks well will not only allow you and your company to become far more productive, it will

also become monetizable. Sort of like a new software layer. But just like with software engineering, prompt engineering, and AI automation engineering, you need to actually get good at it. Even though anyone can create skills through prompts, the same

skill can produce completely different outputs depending on how you build them.

For example, this is an infographic that I got out of an infographic skill that I quickly created. And this is the output

quickly created. And this is the output of the same input of an infographic skill I put a lot more effort in. As you

can see, it's a lot clearer and a lot more aligned to my brand. I'll show you a full demo of the infographic scale later in this video. Also, if you want access to that infographic scale and all of the other skills me and my team are building out, you can also check out my

AI accelerator where we uh list them all for you to download or customize. Now,

before showing you how to build these types of skills, it's good to understand what skills actually are. And simply

put, agent skills are folders of instructions, scripts, and resources that agents can use to do things more accurately and efficiently. And at the core, we have the skill.md file. You can

basically see this as an instruction on how to do a process. Think of it like a system prompt, a cloud project, or a custom GPT. But besides that process

custom GPT. But besides that process instruction, we can have additional instructions on how and when to use knowledge files, how and when to use tools, how and when to spin up sub aents

and how and when to use code executions.

So the skill MD you can basically see as the SOP. Now that skill MD is just the

the SOP. Now that skill MD is just the core. What makes skills more powerful

core. What makes skills more powerful are those additional reference files or the context we add. Now what kind of reference files can we have? Now

firstly, we can build really simple skills with no reference files at all.

It's just a skill MD or a process instruction. For example, we have an

instruction. For example, we have an sales account research skill here from Enthropic which has no additional reference files, just the skill MD here.

And the skill MD, as you can see, includes an execution flow, right? Step

one, parse request, step two, web search, right? Step three, enrichment,

search, right? Step three, enrichment, and step four CRM check. But commonly

when we build our skills, we want to add some reference files to provide the skill with more information. Firstly, we

can have text files. For example, common ones you might want to include are example outputs, style guides, context around your ICP, uh your background, etc. For example, in my newsletter writer skill, you can see I have

multiple reference files here to give the skill more context on my background, what we do, my ICP and voice personality. Another common one to use

personality. Another common one to use is an MCP instructions file, which basically lays out to the agent how to use a specific tool efficiently in this specific skill process. for example, the way you navigate or use your CRM for

this specific task. Now, don't worry.

Your agent can build these MCP documents. Now, a second type of

documents. Now, a second type of reference file we can have in there are assets or non-ext files like images, presentations, videos, or even uh binary, for example, to give it good

output examples of a presentation layout that you want. And then lastly, reference files can even include code scripts, Python or JS functions that can take actions like doing API calls in a

software or executing functions. For

example, my infographic scale, we have a script to do an API call to the nano banana Google API call. So you can see that these skills can be very simple or can become quite complex and can look a

lot more like a software except skills of course are software for AI agents.

But how are we able to give one AI agent access to thousands of these skills, feed it all of these documents without overloading it with context? Now this is done through a process called progressive disclosure. Now it sounds

progressive disclosure. Now it sounds complicated, but it's not. Basically,

when we create or upload a new skill and give it to our AI agent in cloud co-work or code, only the metadata, which is the description and the name are stored in the agent memory. In my infographic

skill, this is the name and this is the description. And this is how your agent

description. And this is how your agent knows when to trigger or use a specific skill. And then only when the skill is

skill. And then only when the skill is triggered, the skill MD or the process will be loaded into the context window of the agent to understand how to execute on this specific process. And

only when the skill instructs to use a reference file, it loads the reference file into the context window. And

because of this progressive disclosure of context, we can give one agent access to thousands of potential skills. Now, I

see a lot of confusion between plugins and skills too. So, let me explain it very quickly. Plugins are essentially

very quickly. Plugins are essentially packaged or bundled sets of skills, commands, agents, and connectors. And

this basically means and does three things. First, it adds a layer of

things. First, it adds a layer of complexity on top of skills because plugins can include multiple skills. It

can include commands which serve as workflow triggers that can trigger multiple skills in sequence to automate more complex tasks. It can have specialized agent teams and a preset set

of connectors. So, we can add a lot more

of connectors. So, we can add a lot more functionality to these plugins. Second,

through plugins, these bundled packages can easily be shared and divided between company departments. Sales teams can get

company departments. Sales teams can get a sales plugin. Marketing teams can get a marketing plugin each with the connectors and skills that each department needs. And thirdly, these

department needs. And thirdly, these plugins are also becoming uh versionable uh skills too by the way, which means they can be updated at any time across any account that uses them. And because

of these characteristics, plugins start to look a lot more like software of course or SAS. And I predict that SAS will start to launch their own plugins with their specific functionalities.

Now, if you want to learn more about plugins, I recently did a video on it.

So, I'll make sure to link it in the description below, too. But skills are really the key aspect even inside of these plugins. And even though we have

these plugins. And even though we have plugins, we can still directly build, trigger, and access skills even without these plugins. Now, skills and plugins

these plugins. Now, skills and plugins are relevant for any industry, business, department, and any niche workflow. And

we're seeing three layers of skills and plugins appear. uh we have the general

plugins appear. uh we have the general plugins and skills uh for example the ones built by Entropic or OpenAI um but we're already seeing marketplaces of skills like Skills MP Smithy um where

people are building and potentially selling them and potentially SAS businesses will start creating their own plugins now as these will have to be general purpose skills in order to be relevant to multiple industries and

businesses companies will want to build their own ones based on their unique processes or customize some of these general skills but even within a company it makes sense for different employees and different people to customize skills

to their specific way of working and their specific workflows. For example,

an entropic or third party, let's say sales outreach skill can be useful, but a company probably wants to customize and improve it by adding uh the company brand tone, the ICP and the business context. And one uh sales rep's

context. And one uh sales rep's copywriting style will be different than anothers. So, they can even start

anothers. So, they can even start customizing uh those skills for their specific copyrightiting style. for

example. Of course, if you as an individual start to get good at it and you have specific domain expertise and build a skill out of it, you can potentially monetize it by providing it to the general public. So, how do we actually build these skills ourselves?

Now, we can first of all customize entropics or the third party provider skills. There are multiple of these

skills. There are multiple of these marketplaces now, but the real unlock is really building them yourself because every person and every company has their specific ways of working and their specific expertise. Now, there are two

specific expertise. Now, there are two main ways to build your own. First way

is you do a task once manually with an AI agent and then ask it to save it as a skill. And the second way is to instruct

skill. And the second way is to instruct it on how to build the skill right away.

For example, here I downloaded a third party provider meta ad scale from one of the marketplaces, imported it and used it here in my own account. And then I asked it to use this skill combined with

my specific knowledge sources to create a new skill that helps me create ads.

And then it created a new skill which I can add to my library. Customizing

Entropics built-in plugins and skills is also very easy. You can just go to skills, click on edit and customize with claude or even the plugins by just clicking here on customize. And here I created my own skill by just prompting

it and giving it some reference files.

Now whatever the method, applying some best practices is important. So let me start by saying that building good skills is kind of like an art. It's the

art of putting your domain expertise of a process into something productizable and usable for an agent. The more I do this, the more similarities I see between skill engineering and software engineering, but it's sort of like

software engineering for an AI agent. uh

but you have to think about UX right when to add in human in the loop you have to think about context engineering right which balance of context uh produces the best outcomes you're adding features removing things handling edge

cases etc the beautiful thing with skills is you can easily update them with prompt so skills are never finished and what I've learned is the more you use them the better they get I've probably updated and iterated on my infographic skill around five times to

get to the outcome that I get now now the first step is the step that most people skip but what makes the biggest impact uh before prompting to build or customize a scale, you really do want to take a step back and think about the

ideal step-by-step process to get to a good outcome. You want to think about uh

good outcome. You want to think about uh what knowledge sources or additional information you can give your AI agent in this skill to do a better job. Now,

generally, some context or reference files that I recommend you have, especially if you're going to use these skills more for marketing or sales related uh skills, is what we do.

basically a description of your business or description of your ICP of your voice personality if you're using this for uh LinkedIn etc. newsletter strategy in this case I have this also for my

YouTube for my LinkedIn etc and also writing framework these are some of the documents that I reuse across different skills too so I highly recommend this now if you don't have these reference files yet you can do it together with cloud for example here I asked it I want

to create a YouTube strategy document that I can later give when I'm building skills for research ideation scripting etc and then I basically ask it to ask me some questions about my YouTube strategy and through the planning mode

as you can see here ask questions etc you'll get more and more context text and at the end here you can see club generated a YouTube strategy document for me which I can then reuse in multiple uh YouTube skills that I create

and once you have a few of these building skills will get a lot more efficient. Now once you have that of

efficient. Now once you have that of course you want to think about which tools or software the agent needs in order to uh do this task and then if possible you always want to prepare good output examples and this is generally

the thing that impacts performance the most. Now once you have that sort of

most. Now once you have that sort of clear we move to the building which of course in this case is prompting. Now I

just go through a framework that I like to use which is not hard science but I think can help you uh to think about what to include to get to a good first outcome uh of your skill. Now first you want to define the name of the skill and

how the skill should be triggered. So in

this case the name of the skill should be infographic generator and should be triggered anytime a user mentions he wants to generate or create an infographic. And this is what the agent

infographic. And this is what the agent uses to write the meta description. Then

just like with prompting you want to define the goal or objective for the skill. Uh it can be quite short because

skill. Uh it can be quite short because we dive a lot deeper into the process later. Now, in this case, an infographic

later. Now, in this case, an infographic skill that creates quality infographics according to my brand style for LinkedIn and newsletters. Then, we want to give

and newsletters. Then, we want to give Claude context on connectors, APIs or MCPS that it needs uh to use in this scale. Now, if there's a specific table,

scale. Now, if there's a specific table, maybe a page or a process it should take in that software for this uh skill, you can also describe that here. And then

you want to lay out the process uh step by step. This is one of the most

by step. This is one of the most important things and it's good to actually spend some time on it. Now a

good way to think about what to include in each step is what does it need to do?

First of all, when do you want a human in the loop? What kind of human in the loop do you want? With the dynamic QA boxes of cloud, we can now choose between check boxes, open field, single

select, etc. Which kind of becomes like UX design. And for what additional

UX design. And for what additional context should be used to do this task better? If it's very short, you can add

better? If it's very short, you can add it in the prompt. But if you have a specific file it needs to read, you want to specify that for each of the step.

Even if you don't have the reference file yet, you can just paste the context here in the prompt and ask it to create the reference file for that skill with that context. Generally, you want to try

that context. Generally, you want to try to keep the skill MD very clean and focused on the process. Any additional

information should be in the reference files. That's how your skill is going to

files. That's how your skill is going to perform a lot better. And lastly, you want to think about what you expect as an output for each of the steps. So

something that I like to do and has made a big impact on my productivity is when you have human in the loop steps ask cloth to always give you multiple variations or options which you can choose from instead of just one-off

outputs. So I usually say something like

outputs. So I usually say something like that. It should give me five different

that. It should give me five different ways an infographic could visualize this idea or concept. And then lastly you want to think about rules for this skill. Here you can basically predict

skill. Here you can basically predict what could possibly go wrong when executing this skill and write it down as a rule. Now, this is also the section that you will continuously update when improving the skill. Two tips here in

the rule section is first of all to double down on instructing it to use the knowledge files as obligatory steps in the process when needed. Otherwise, I I notice it tends to skip over some. And

second, I usually double down on the multiple variations with human in the loop. And lastly, a really good thing to

loop. And lastly, a really good thing to include is progressive updates.

Basically, instruct the skill to be automatically updated and improved when using the skill so it becomes self-learning. For example, every time I

self-learning. For example, every time I define a clear thing not to do anymore in this scale, update the rule section.

And what can be very powerful too is instruct in the process that if a user approved the final outcome to save that as a good example so it learns and builds more data around what good looks

like automatically. Now let me show you

like automatically. Now let me show you a quick demo of how my infographic works so you get a better idea of what you can get out of this. So I'm in this case I'm using the code tab here because uh with API calls it can be a little bit easier.

Uh, so I can just trigger it with the slash command. And this is already an

slash command. And this is already an updated version from this initial prompt that I gave it. First, it asked me what content should I turn into an infographic. So I'll just paste in a

infographic. So I'll just paste in a part of my video where I talk about what skills are. A later update I made from

skills are. A later update I made from this first prompt is to ask it first for which platform it is to understand which format it has to generate it in. So in

this case, LinkedIn and as you can see, it uses these QA boxes because I instructed it to do that. And then what type of visual should it be?

Infographic. Then I later adjusted it and iterated on it to get a checkbox out. So I can actually start generating

out. So I can actually start generating multiple variations. But here it

multiple variations. But here it suggests me what we should visualize.

This case I'll go with anatomy of a skill. And then it suggests me ways to

skill. And then it suggests me ways to visualize that concept. I can choose what makes most sense and generate those. I'll just do all of them.

those. I'll just do all of them.

Now again the first time I launched this prompt, it wasn't this good yet. I had

to iterate three or four times, adding extra rules, etc. So became an iterative process. And it's really about that the

process. And it's really about that the more you use it the better it becomes.

But these are quite powerful and really follow my uh brands down and guidelines.

And you can see I added this box at the end. If I click keep all finalize, it

end. If I click keep all finalize, it will save it as the good output uh examples. So it gets trained on what

examples. So it gets trained on what good look looks like. Now it is important uh how you instruct the model to change things. Then an easy rule of thumb you can keep in mind on improving and updating is if it doesn't follow the

process correctly, ask it to make changes to the skill MD. The key in the skill MD is that it doesn't get polluted with a lot of additional information. It

should mostly focus on the core process.

Now, if you need additional information, you want to ask it to add a reference file. Now, if it does something wrong,

file. Now, if it does something wrong, not just for this specific task, but you never want it to do, for example, I had this with my infographic. I never want the black background because the shadows are not visible. Then you can ask it to

add a rule or update the knowledge file.

Now, if it struggles to use one of your softwares, MCPs or tools, you can first guide it manually to do the specific action necessary and then ask it to create an MCP reference doc on how to do

the task in the software. And you can see that my first version is completely different from my last version. Now,

lastly, once your skill is performing well and you maybe want to share it on a marketplace or maybe to a team member, the easiest way is to ask Claude to give you a zip file for that skill. You can

then just share that and someone else can go into the settings, the capabilities and upload the zip file.

You can also deploy a skill through GitHub. I'll put a link in the

GitHub. I'll put a link in the description below on how to do that.

Now, if you have multiple of these skills, you maybe want to combine uh different skills, maybe commands, adding agents, specific connectors. You can

bundle them into a plug-in, which again can be done by just telling Claw to build you a plug-in. It will ask you for all the skills, etc. that you want to include and then you can add it to your library and if you want to share it

again you can do it through a zip file or by uploading it to github and if you're a business and you have multiple plugins across multiple departments you can create an entire plug-in marketplace

which is a bundle of all your plugins now you'd have to create this together with cloth code and upload it to GitHub in order to get a link again released a full guide which I'll uh share in the link in the description below now if you

want access to all of the skills plugins uh me and my team are building out including in graphic one. You can also check out my AI uh accelerator, my AI community where we list them all. We

also do weekly AI workshops where we dive a lot deeper into these types of tools. We have blueprints on how to

tools. We have blueprints on how to start your business, how to find your first client. So, if that's potentially

first client. So, if that's potentially interesting to you, uh you can check it out in the link in the description.

Thank you so much for watching and if you want to learn more about cloth co-work uh you can check out the video here above.