The argument in one line.
Claude skills are markdown-based instruction templates that let you give Claude Code persistent domain expertise, enabling it to function as a specialized general-purpose agent for your specific workflows instead of a generic chatbot.
Read if. Skip if.
READ IF YOU ARE…
- You're a solopreneur or small business owner with no coding experience who wants to automate a specific workflow like social media posting or email drafting.
- A content creator or founder who's heard of AI agents but doesn't know where to start and wants a concrete, walkable example of building one.
- You have a specific repetitive task at work and want to see how Claude skills and code can handle it without hiring a developer or learning to code.
SKIP IF…
- You're already comfortable writing code or building AI agents — this teaches fundamentals and won't show you advanced patterns or optimization techniques.
- You need to deploy agents to production or integrate them into existing systems — this covers local proof-of-concept building only, not deployment infrastructure.
The full version, fast.
Claude Code is not just a coding agent � it is a general-purpose agent you can aim at any folder on your computer, and Anthropic's new Skills feature lets you give it reusable SOPs that fire automatically when relevant. A skill is nothing more than a markdown file inside a .claude/skills/ subfolder, with a name and a description that tells the agent when to use it; supporting references like annotated examples or API docs sit alongside it. The video walks through building a Twitter-posting agent by feeding Claude screenshots of your own tweets plus Typefully's API docs, producing drafts in your voice scheduled directly to the right account. Treat skills as the connective tissue between a general agent and your real workflows.
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 – 01:13
01 · Cold open
Bold assertion that Claude Code is the best, then introduces Claude skills as the most important thing to study right now.
01:13 – 02:48
02 · What is a coding agent?
Lovable demo: types make a landing page about pizza, explains sandbox VMs, positions Claude Code as the superior local equivalent.
02:48 – 05:14
03 · Claude Code on your computer
Replicates Lovable in an empty terminal folder. Generates neo-brutalism pizza page. Runs on localhost:8080.
05:14 – 07:32
04 · Claude as general agent
Switches to Obsidian notes folder. Types do what is in my queue -- Claude finds the right file unprompted and writes a research plan.
07:32 – 10:12
05 · Skills intro: folder structure
Opens Cursor, creates .claude/skills/summarize/SKILL.md. Explains the description field is the trigger for when Claude invokes the skill.
10:12 – 13:50
06 · X Post skill from annotations
Drags annotated Twitter screenshots in as references. Claude analyzes patterns and generates skill. Red text equals annotations not post content.
13:50 – 19:57
07 · Typefully API integration
Adds Typefully API key via key.txt. Claude extends the skill. Tests live -- drafts appear on Riley Brown and Vibe Coding Explained accounts.
19:57 – 24:55
08 · Fresh context test
Resets Claude context. Fresh prompt fires the xpost skill automatically (green dot). Generated posts include GitHub link unprompted.
24:55 – 27:20
09 · Conclusion + folder diagram
Visual diagram of .claude/skills/skill-1/SKILL.md. Teases Part 3 agent workspace. Links to Luma webinar.
Lines worth screenshotting.
- Claude Code is a general-purpose agent, not just a coding tool — running it in a folder of markdown notes turns it into a personal assistant with full context of your goals and tasks.
- A Claude Code skill is a markdown file with a front matter description that tells the agent when and how to use it — it is effectively a standard operating procedure the agent follows automatically.
- Lovable, Replit, and VibeCode are just coding agents running Claude or similar models inside a virtual machine — Claude Code running locally does the same thing without the SaaS wrapper.
- The Obsidian notes folder as an agent workspace is a practical architecture: the agent can read task queues, update progress notes, and create deliverables alongside the human's notes.
- Asking Claude to examine your workflow and identify which skills would be useful for you is the most efficient way to start a skill library — let the agent design the SOPs.
- A Twitter-posting skill that connects to Typefully via API is a complete agentic workflow: the agent drafts content from examples, formats it, and queues it for posting without human hand-offs.
- Annotated examples of successful tweets embedded in a skill file teach the agent voice, format, and style more efficiently than written instructions about those same properties.
- Claude built the API integration skill for Typefully itself after being shown the documentation — the developer only needed to provide the goal and the authentication credential.
- The skill file structure — description for routing, instructions for execution, tools for capability — is the same architecture whether the skill is for Twitter, email, or code review.
- Using Claude Code as a general agent reframes the tool from a coding assistant to an intelligent workspace that can manage tasks, draft content, and execute workflows across your entire business.
- The skill that proves the concept is the one that does something the agent would not do without explicit SOP guidance — posting to a specific API with a specific voice is that kind of task.
- Building a skill by showing Claude what you want as examples and asking it to write the SOP is faster and more accurate than writing the instructions yourself from scratch.
A Skill Is a Standard Operating Procedure That Claude Triggers Automatically When the Context Matches
Claude Code skills
Riley Brown's first-principles walkthrough shows that a Claude skill is just a markdown file with a description field that tells Claude when to activate it — and that the most powerful skills are built from annotated examples rather than written instructions.
03Claude Code on your computer
- An empty folder plus a natural language prompt produces a complete local application — no sandboxed VM, no cloud dependency, runs on localhost
- The local equivalent of browser-based coding tools gives the agent access to the full file system and system commands
04Claude as general agent
- Pointing Claude at an Obsidian notes folder and asking it to execute the queue demonstrates general agent capability without any code-specific context
- The agent finds the right file unprompted and builds a structured plan — general agent behavior requires no special configuration beyond being in the right folder
05Skills intro: folder structure
- .claude/skills/skill-name/SKILL.md is the folder structure — the description field is what Claude reads to decide when to activate
- The description should match the user's natural phrasing when they want the skill — write it from the user's perspective, not the developer's
06X Post skill from annotations
- Drag annotated screenshots of the target output into the session — Claude analyzes the patterns and generates the SKILL.md from examples rather than rules
- Red text annotations mark what is instructions versus what is example content — the annotation layer separates signal from sample
07Typefully API integration
- Adding an API key via key.txt and asking Claude to extend the skill turns a draft generator into a live posting pipeline
- The integration is built by Claude, not configured manually — describe what the API should do and let the agent write the integration
08Fresh context test
- Reset context, make a natural-language request — if the green activation dot appears, the skill's description field is working
- Automatic activation without naming the skill is the standard to build toward — it proves the description matches real user behavior
Terms worth knowing.
- Claude Code
- Anthropic's command-line AI agent that can autonomously read, write, and run code files — used here as a general-purpose agent beyond just software development.
- Claude skill
- A specially formatted Markdown file that gives Claude Code a set of instructions for performing a specific repeatable task, functioning like an SOP (standard operating procedure) for an AI agent.
- general agent
- An AI configured to perform a broad range of tasks — such as writing, posting, researching, or calling APIs — rather than being restricted to a single narrow use case like coding.
- skill.md file
- The Markdown file at the core of a Claude skill, containing the task instructions, examples, and rules that Claude reads when the skill is invoked.
- coding agent
- An AI that operates inside a sandboxed environment to generate code, build apps, and run commands autonomously based on natural-language instructions.
- vibe coding
- Building software by giving an AI loose natural-language descriptions rather than writing code manually — associated with tools like Lovable, Replit, and similar no-code AI builders.
- Typefully
- A Twitter/X scheduling and drafting platform with an API, used here as the destination for AI-generated tweet drafts the agent posts via programmatic API calls.
- Lovable
- A no-code AI web app builder that spins up a cloud sandbox, runs a coding agent, and generates a deployable web application from a plain-English prompt.
- annotated examples
- Real-world content samples (such as tweets) with notes explaining what makes each one effective — used here to teach a Claude skill by example rather than abstract rules.
- SOP (Standard Operating Procedure)
- A documented set of step-by-step instructions for completing a repeatable task — the analogy used here to explain what a Claude skill file does for an AI agent.
Things they pointed at.
Lines you could clip.
13:09
“All skills are, the way I think about them, they are just SOPs or standard operating procedures for agents.”
18:37
“I turned Claude into my personal marketing team. Social media copy on demand, email sequences in seconds, brand voice locked in permanently. Zero prompting every time.”
19:59
“Claude Code just became a general agent, not a chatbot -- an agent that does your workflows.”
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.
analogy
00:00You probably already know that ClaudeCode is by far the best coding agent in the world. It can create entire apps from a simple prompt, both front end and back end. It can blow your mind in terms of the design of that app.
00:13But what you might not know is you can actually use Claude as a general agent. And Anthropic released something really interesting a few weeks ago. They released what is called Claude skills, which is just a special type of markdown file which allows you to surround Claude code with relevant skills.
00:33So if you wished that you had an AI agent that had relevant skills, I believe that this is probably the most important thing that you could be studying right now. And so in this video, we're gonna talk about how to set up Claude skills.
00:46We're also gonna talk about how to use Claude code as a general agent, and we're gonna talk about how you need to set up your skill dot m d file and what folders, and I'm gonna show you how to just use AI to create these skills. Let's talk about building a general agent with relevant skills for your business, whether you're a content creator, business owner, aspiring entrepreneur.
01:06We're going to build an agent with relevant skills to you. And we're gonna use that agent. Let's dive in.
01:13Okay. So we're gonna start off by talking about what is a coding agent. You may have heard of Lovable, and this video is not about Lovable.
01:19We're not even gonna use Lovable. I just wanted to make a point real quick. So many people are talking about vibe coding.
01:25You can use tools like Lovable, Replit, VibeCode. These are coding agents that you can use to build apps.
01:31And whenever I go to Lovable and type in, uh, make a landing landing page about pizza.
01:41Right now, what it's doing is it's spinning up a sandbox, which is basically a virtual computer, and it's going to run an AI agent or an AI coding agent on the side.
01:53Now it's gonna generate a bunch of files within a directory or code base and those files are going to make an app.
02:02And so this is an AI coding agent at work building an app. Okay. So it's done.
02:08The lovable coding agent took my prompt, make a landing page about pizza. It generated all of the files. This coding agent decided what files it needed to generate.
02:18It generated them and then it probably reviewed those files and then it ran the program in a virtual computer somewhere so I can see it on my, uh, browser because this is within a web browser.
02:31And so this is an example of an agent made specifically for creating simple applications. A very narrow agent experience where it's made specifically for creating certain types of apps with certain stacks.
02:45And we could do this same thing on our computer. Right? We could do the same thing on our computer.
02:50If we were to go to finder, we can just go straight into our downloads. Right?
02:55We can go straight into our downloads and we could go new folder. We can go like this. We can say using Claude code.
03:04Right? So we don't even need any IDE or something like cursor or lovable. I can open a terminal window.
03:12I can open a new terminal at this folder and we can just run Claude. So now we're running Claude code in this empty folder called using Claude code which is an empty folder.
03:24And I can just say, please build a beautiful, amazing landing page for my pizza shop, Riley's Pizza Shop. Make it in the style of neo brutalism mixed with a friendly pizza energy.
03:39So just like Lovable, we can run this. And Claude Code in this empty folder is going to create the application right here.
03:47Okay. Check this out. It just generated an index dot HTML file and there we go.
03:53It created a file the same way that Lovable is creating all the different files and putting them in a folder in some virtual machine. It's just a virtual computer.
04:03We're doing this on our computer. It's doing the same exact thing Lovable is doing. And the point I wanna make here, you can just use these coding models on your computer and coding files, right, this is an HTML file and this is a CSS file.
04:19This is not the only type of file you can create with Claude Code. You can create any type of file.
04:26So it is done and if we just copy this link right here and we paste in localhost eighty eighty, we can run this on our computer. This is running locally on our computer where Lovable in Lovable's case, it just created a virtual machine and it ran it on that computer and it showed you what it created on the browser.
04:47Now we're running this fully on our computer and we didn't use any like software in between. We generated the code files with an AI coding agent on our computer.
04:57It used an AI model from Anthropic servers to create those files. So that's where it costs money. But we didn't use any other software other than getting Quad to generate all the files and we're running it on our MacBook Pro.
05:11And this is the website that it created. And you'll notice that in my opinion, I've tested every single one of these coding agents, just raw Claude code is the best in the world.
05:23So Replit and Lovable, they have their own coding agents. Claude code out of the box is better than all of them. And so what I want to explain now is how you can use this as a general agent.
05:36So this right here is Obsidian and this is just a basic notes app where every file instead of the files being an HTML file or a JavaScript file or a CSS file which ultimately created this application that we can use, instead of it being one of those types of files, these are all markdown files.
05:58So the way that I use general agents is I actually use Claude code at the same location as my notes.
06:07Like this is my agent workspace. This is kinda how I think about this. This is a note book and Riley Brown uses this as his personal note book so that he can be a better CMO and co founder of the Vibe Code app.
06:19And I basically state all of my goals. Why am I stating this? I I know my goals.
06:24Why am I writing this? Because I don't use this by myself. I use this with my general agent which is Claude Co.
06:31And what I can do here is I can actually click on this or I can right click on this and hit reveal in finder. So here we can see Riley content creation.
06:40That's basically what I called this file and you'll see here all of these different files here, um, like this is just a wrapper of these files that are showing up on my computer.
06:53Right? This is just in my computer and so the same way that I ran code in a new folder, I can run Claude code in this folder.
07:02So I can reveal this in Finder. What I'm gonna do is I'm gonna right click services, new terminal at folder.
07:10Alright. New terminal at folder. Now, you can see here that it is running.
07:14So we're in this folder right here, which is the same folder where all of this is located, and now we can run Claude. And so now we have Claude code running in the folder that has all of my notes and so I can use it with Claude code.
07:30So I could go into tasks, right, and and this is how I keep track of my tasks. I could go into queue, let's say these are both done, right, this is these are the things that I wanna do, and so in my queue, one thing that I do wanna do, and I can just drag this in here, one thing that I do wanna do is I want to explain Claude skills to my audience and make a video.
07:54Right? This is one thing I really wanna do. Um, I want to, um, share the file structure, um, with of Claude skills, and then I want to take my notebook and examine what Claude skills would be useful for me to create.
08:07And I'm I'm, uh, do this onto this page. Don't create or edit any other files. Just make a plan and do it.
08:14Okay. So we just created this markdown file of this thing that I wanna do. The cool thing is I can just ask Claude Code to do it.
08:20I can just say, do what's in my queue. Right? That's all I need to say.
08:25I can, yo, do what's in my queue. And because the first thing that this agent's gonna do is analyze the read file, it's going to see how it's organized.
08:33Right? It's gonna know that there's tasks, it's gonna know what the queue is, draft tasks, so it's just gonna know to check the queue and because Cloud Code is such a powerful agent and it's really good at looking through the code base, in this case, which is just a bunch of my notes, it's gonna find the right location.
08:51It's really smart. And it's gonna find this page and it's just gonna do what I want it to do. And we'll just wait for Cloud Code to do that.
08:57And you'll see here that we never said to look at this file. It doesn't know that I have this file open. It just found what's in my queue, and you can see here it's examining notebook for skill ideas.
09:09It found the right file, and now it's creating the relevant things. Allow it to edit this session. Boom.
09:14Look at that. So it just added all of this. It added all of this to this document.
09:23It told us what skills are. Right? And it told us that from the Anthropic skills repo, it it basically did research.
09:32It's found the Claude skills repo and now it is telling us that you can create within the Claude dot m d file, you can create a skill by creating a folder with the skill name and inside that folder, it needs to have a Claude dot or a skill dot m d file and then you can put optional, uh, resources within that folder.
09:56So you can even put assets, references, etcetera. And I'll get to that in just a second.
10:00The point I wanted to make is the same way Lovable was a coding specific example of using an agent, this is a notes specific example for using an agent.
10:12So I promise you, we are we're working our way up to creating Claude's skills. I just wanted to illustrate the point. I wanted to talk about what a domain specific agent was like the lovable agent that can create apps.
10:23Then I showed you a note taking example where you can use Claude code as a general agent. Now we're gonna use it in a wide open world within Cursor. And we can do literally whatever we want.
10:36I like to use Cursor because it's just the best in my opinion for quickly using Claude code and it's ironic because I use we can just say Claude code skills.
10:48So what we're gonna be creating Claude skills in this project, I'll just name it that. And now it is opening up this directory in an IDE. So Claude cursor is just an IDE like Versus Code where you can view all the files.
11:06And so the way that I vibe code is I'm just gonna come in here and the first thing that I'm gonna do is hit command j. We're gonna open up the terminal and we're gonna type Claude. Then we're gonna press this right here to open up the side panel.
11:18And so now we have Claude code on the left or on the right controlling this directory which is Claude code skills. And what we're gonna do here is I'm gonna say please take a look at this direct or at this repo, and I'm gonna paste this GitHub, uh, to the Anthropic skills right here.
11:41Please create one simple skill in the right format so that you will use this skill when you need to.
11:53Okay. So right now it's creating an example skill. What it's going to do is it's going to create a dot claud file.
12:01It's going to create a dot claud file. As you can see here, it's created this dot Claude file.
12:07It's also going to create a skills folder as you'll see in just a second. Okay. There you go.
12:13It created a folder called dot Claude, and then it created a skills folder within that, and then it has other folders beneath it.
12:23So it created this summarized folder with a Skill MD. That's all you need to create a skill. You just need to put in the dot claud folder because Claude code knows to look in the dot claud folder for certain things like sub agents and now skills.
12:35We're not talking about sub agents in this video, we're just talking about skills. So we created the skills folder. And within this folder, right, we see this skill dot m d.
12:44And every single skill dot m d file should be formatted with the name and description. Right?
12:50It should have a name and description. You can see here that this one that I've created is called brand voice, which is skill number one, and then there is a name and description.
13:02And so the name is just a human friendly title. It can be anything. But the crucial part is this description because it tells Claude Code when to use this skill.
13:11And so we're reaching a point where you can get agents to do things with a simple markdown file. But what you need to do is you need to make sure that you format it correctly so Claude Code knows when to follow your instructions. Because basically, all skills are, the way that I think about them is they are just SOPs or standard operating procedures, SOPs for agents.
13:36And so, right, these are instructions on what to do in certain scenarios. And if you put a high quality description, it'll know what instruction manual or SOP to use when it needs to do a specific task.
13:50And so I don't really wanna use this summarize skill. I actually wanna create a skill that's much more relevant to me.
13:57Okay. So I just wanna show you what I've been doing. I've been annotating.
14:01I've been annotating my Twitter posts because I can give these to Claude. I can put these in Claude's skills so the agent knows how I post. And so I can say, short video attached to this photo.
14:16This is a Twitter account that I run, by the way, that helps me grow VibeCode. And I can say, senior Vibe Coder is rage bait and works.
14:30Uh, don't do this often. Right? And I just put this directly on the image and it helps me kind of annotate my images here.
14:38And I'm just gonna hit I'm just gonna exit out. Let's save. And we can save all these.
14:44And so what we can do here is we can just take all of these files. We can drag them in here. And what I'm gonna do is I'm just going to put a new skill here.
14:53And what we could do is we could just drag these images in here. Now we're gonna go to Cloud Code. I want you to replace this, uh, summarize skill.
15:03And because this is a folder, right, I can just type at summarize. Right? I can say replace this summarize skill, this skill.
15:14The whole summarize skill should be replaced with a Twitter post x post skill.
15:21This skill should allow the agent to create tweets in my style and use the images that are in the at new in the new skill here folder as a reference. So please create that skill now.
15:37So we're basically going to tell Claude Code to analyze these images. It's gonna look for patterns in how I speak. And actually, one thing I can mention, I just hit the backspace.
15:48Just know the red text in these images are annotations.
15:55So that's not part of the post. These are my annotations to you on why I did certain things. So take that into consideration when constructing this skill.
16:02Right? So I annotated why I did what I did. So this gives some extra context to Claude code, and it's going to packages it package it as a skill.
16:09And so in theory, whenever I ask for a Twitter post to Claude code in the future, uh, within this repo, it should be able to do it in my style because I've given it relevant context. Okay.
16:20So there you go. It created this skill dot m d file, and all it did was analyze all of those images. It converted them into these, uh, markdown formats, and it converted it into a skill.
16:34What it didn't do is I didn't specify this. Uh, that was just a temporary folder. Please remove that folder, but add those images into that skill folder references because this doesn't need to be here.
16:47This can just go into the skill and right?
16:50So right now we have two skills. We're gonna add another skill in just a second. So we have one skill and every skill needs a claw dot m d file.
16:58So it just created this, and now it has these references that it can use right here. What we can do if we want, references to posts, and we can select all of these and we can just like move them in here.
17:14So we have references and then the skill dot m d file. You need this skill dot m d file.
17:20Right? And so what we can do, I want you to create a markdown file in the root.
17:29And when I say in the root, I mean, right, there's the the folder that we opened up originally, is Claude code skills.
17:38This is the root folder. So it should put it below the dot claud folder.
17:42The dot claud folder is also in the root. The skills folder is in the dot claud folder, thus not in the root. Just wanted to be clear.
17:49Uh, in the root and come up with 10 ideas ideas for the Twitter copy based on my last video where I explained Claude skills.
18:08Should match. And then I can, uh, give it that GitHub repo link. I mentioned skills and explained why it's important for general use cases for like marketing and as general agent.
18:30Okay. So let's say I made this video because I'm making this video right now. What I would probably do is feed in the transcript of this video and then it would generate 10 options.
18:38So it would have more context of the video we're creating. But since I'm making the video right now, I can't give it the transcript. Um, but that's okay.
18:45It's going to create a markdown file in the root and it's going to use this skill. Okay. So it is done.
18:52Okay. You'll see that when you see this green dot and it shows x post right here, when you see this green dot and it has x post, that means it's using that skill.
19:03Right? It is using the x post skill and we're gonna allow it to create these files and boom, Twitter ideas.
19:13So here we go. Cloud Code just became a general agent, not a chatbot, an agent that does your workflows. Anthropic just released skills, reusable prompt templates, invoke with slash commands, marketing teams.
19:27Okay. So this is really good. Oh my.
19:29This shouldn't be possible. I turned Claude into my personal marketing team. Social media copy on demand, email sequences in seconds, brand voice locked in permanently.
19:40Zero prompting every time. How? Claude skills.
19:44One markdown file, infinite workflows. This is very good. So it wrote this in my voice using this skill.
19:53But it gets much cooler than this. So if we were to go to, um, let's go to Arc.
20:01So we're gonna go to typefully.com. And in Typefully, we can go to settings and we could go to API and we can hit new API key.
20:15And so this is going to be test key for me, create API key.
20:22I'm gonna delete after this video and then what I'm gonna do is I'm gonna click on this docs and this explains exactly how to use this API key. So what I'm trying to do here is I don't want it to just come up with ideas, I want them to draft them in this tool where I can post directly to social media.
20:39So in theory, I could have an agent come up with tweets and automatically draft them within Typefuly because that's what you can do here on this platform.
20:50Right? We could have it directly post this as a, um, a draft here.
20:56Right? It can schedule a new draft. And so that's exactly what I'm gonna tell it.
21:00So I want you to add to our x post skill.
21:07I'm using the software Typefuly, and I want you to instead of basically, of putting these in a document, I want you to actually directly schedule these as a draft on Typefuly. And so I am going to give it these docs to the API. Here are the docs to read.
21:19Here is my API key. It is in a text file. Right?
21:23So I don't want to expose it. What I'm gonna do is I'm just gonna go I'm gonna go key dot t x t.
21:30I'm gonna paste my key right here. So I pasted my key in this file, and I can just go at key dot t x t.
21:37It is here. Please add to the skill using Claude's skills, and I'm going to mention this link right here.
21:45Please make this skill such that it schedules it as a draft to this Typefulli account.
21:57It should not post or schedule. Okay.
22:01Now we're gonna wait for the skill called XPost to be, uh, messed with.
22:08Okay. So it is done. And here we can see that your accounts available is Riley Brown, Vybe Code, Vybe Code explained.
22:17Okay. So this works. Maybe.
22:19Maybe. Uh, please test this by drafting one of the items in the list that we generated in and then we can just go Claude skills Twitter ideas.
22:38Okay. Okay. It looks like it is done if we come back here.
22:42Okay. It created this. Right?
22:45It created this on Vibe Coding Explained. Okay. Now on the Riley Brown account, draft a post that says, hi, this is a test.
22:59Okay. So it's done. If we go back to ARC, we go to Riley.
23:05Here we go. We see, hi, this is a test. This was thirty four seconds ago.
23:10So that's pretty cool. We can have it draft post.
23:14I'm gonna just reset the context here. So we're opening up a new Claude instance to reset it.
23:22Right? We're resetting it, uh, so that there's no context in here and I'm gonna say, I just you created a Typefuly video that explains how I created a Clog Code skill in order to post on all my Twitter accounts via Typefuly.
23:40I want you to draft up three x posts and draft them on Typefuly on the Vibe Coding Explained account. Oops.
23:48I misspelled it. Typefuly is the app.
23:55Okay. So we interrupted it, but it was using the expo skill. It should go back to using the expo skill.
24:01Okay. Do I wanna proceed? Yes.
24:04Okay. So the drafts were created. Oh.
24:08It has a link associated with it? Wait. What happens if we just go to this link?
24:13Wow. Skills repo. It even included that repo.
24:17No way. You can build custom skills for Claude code, automate repetitive workflows, create one click commands, share skills across projects, zero coding required. Just dropped a full walk through how to do this.
24:29Wow. Okay. So it created these posts using the Typefly or the XPost skill.
24:37And in this skill dot m d file, it has access to this code. Right?
24:43You can it has this code that I can that the Claude code can use to post this on social media. And what I need to do now is I need to delete my API key because I probably exposed it.
24:55Alright. So there you go. We just created a general agent and we gave it a skill.
25:00And you know what? I think that's enough for you to get started. I don't wanna like go crazy and create, like, an agent swarm or an agent with a ton of different skills.
25:10But we just created a we used Claude within cursor to create an agent, and then we just created one simple skill. And this is enough for you to get started because as you saw, I just gave it the link which I'll put in the description to the Claude code skills.
25:25So Claude code can make your skills for you. And remember, you just create a you know, you have the root folder.
25:31Right? And then within your project, just have a dot claud folder, then you have another folder, uh, which is your skills folder.
25:42And then within that, you just have the skill name. So this is just skill, uh, skill dash one folder.
25:50And then in here, you have a, uh, a skill dot m d file. And within that file, it will have a name and description.
26:01And Cloud Code will do that for you. Just make sure that when you create these skills, right, because you can create many of these. You can create skill one, which we did, um, and we didn't create more than one skill.
26:12Right? You can create as many skills as you want. I wouldn't go overboard, but if you wanna create a general purpose agent and use Claude Code, this is how you can do it and you can create a bunch of different skills.
26:24And so in the description down below this video, you'll find a link to a webinar. I'm just gonna do like a big livestream where we're gonna create a really cool agent interface with a ton of different skills.
26:36We're gonna do it live. It's gonna be like three to four hours long. And so if you wanna sign up for that, that's in the description.
26:42It's gonna be sick. But, uh, yeah, this is just part two of my general agent series. I made part one on Obsidian and I'm just gonna continue this because I'm becoming much more interested in creating agents with skills.
26:57And in the future, we're gonna mix agent skills with also apps.
27:02We're gonna create a little interface where we can alternate between using an app that we create and the agent and we can create things that both me and the agent can use. It's gonna be like an agent interface or an agent workspace.
27:14And that's what we're gonna talk about in the next video. Uh, so thank you guys for watching. Peace.
The Hook
The bait, then the rug-pull.
The promise is buried in the second sentence: not more coding tricks, but a different category of use. Riley Brown opens with a flattering claim his audience already believes, then pivots to the thing they do not know yet -- that Claude Code can run as a general-purpose agent with persistent, reusable skills.
Named ideas worth stealing.
13:09concept
Skills as SOPs
Skills are standard operating procedures for agents. The description field is the trigger that tells Claude when to invoke the skill. High-quality description = reliable invocation.
Steal forFraming any repeatable workflow Joe does as a skill he builds once and reuses forever
00:00model
Progressive revelation ladder
- Lovable (familiar)
- Terminal + local Claude Code
- Notes-based general agent
- Cursor + skills (the unlock)
Teach the familiar before the unfamiliar. Each rung lands the next one. By the time skills appear the audience is already sold.
Steal forAny tutorial video Joe makes about tools his audience has not tried yet
13:56model
Annotated examples to skill loop
- Collect real examples
- Annotate them (why you made each choice)
- Dump into references folder
- Ask Claude to extract the skill
- Claude writes the SOP
You do not write skills manually. You give Claude annotated examples and it writes the skill for you. The annotation is the instruction.
Steal forBuilding any brand-voice, posting-style, or workflow skill for JoeFlow morning batch, Rewriter templates, or Chef prompts
How they asked for the click.
VERBAL ASK
25:56link
“In the description down below this video, you will find a link to a webinar -- a big livestream where we are gonna create a really cool agent interface with a ton of different skills.”
Soft close, no hard sell. Points to Luma event. Reasonable for a free educational video.
MENTIONED ON CAMERA
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
OTHER LINKSAlso linked in the description.
Visual structure at a glance.
