Episode Categories:
Resources:
Join the discussion on LinkedIn: Got something to say? Let us know on LinkedIn and network with other AI leaders
Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Connect with Jordan Wilson: LinkedIn Profile
Start Here Series in our Inner Circle Community: Join for free access
ChatGPT Skills: Unlocking Modular Workflows for Scalable Business Impact
The latest episode of Everyday AI offers a hands-on deep dive into ChatGPT Skills—a new feature inside OpenAI’s ecosystem designed specifically for business enterprise, EDU, and team plans. This article explores the tangible benefits and practical applications for business leaders seeking ROI-driven, scalable AI adoption. Rather than generalizing, it breaks down exact workflows, technical approach, and key unlocks presented in the episode.
AI Job Reductions: Quantifying Current Reality
In the first months of 2026 alone, U.S. companies reported over 40,000 planned job eliminations attributed to AI. This adds to an existing 45,000-plus AI-related job cuts already recorded in 2026, according to Section research. Major tech firms including Meta, Block, and Oracle are publicly associating tens of thousands of headcount reductions with “AI efficiencies.” Meta, for instance, cited more than 15,000 roles targeted for elimination, while Block cut 4,000 jobs and Oracle is moving towards 30,000 reductions.
However, recent Harvard Business Review data shows that 60% of hiring managers referencing AI as the cause for layoffs actually do not replace these roles or augment them with AI—a strong indicator that AI explanations are often leveraged as a narrative device for broader cost reductions. Public companies frequently experience positive market responses for these AI-cited cuts: when Block announced its 40% workforce reduction and attributed it to AI, the company’s stock climbed 22%.
ChatGPT Skills: Modular, Scalable Workflows for Business Efficiency
ChatGPT Skills are not simply another AI add-on. They represent reusable, customizable workflows that encode Standard Operating Procedures (SOPs), templates, and domain knowledge directly into ChatGPT. Unlike one-off prompts, skills enable consistent execution of business procedures—packaging repeatable tasks, workflows, scripts, and company knowledge into modular, executable formats.
Instead of needing to repeatedly re-explain processes, users can upload instructions (even using natural language), connect files, and build bundles that are accessed whenever required. Skills draw from the agent skills open standard, ensuring compatibility across platforms like OpenAI and Anthropic Claude.
ChatGPT Skills vs. Custom GPTs and Projects: Specific Technical Advantages
While custom GPTs allow for creating tailored chatbot experiences, they lack the depth and cross-workflow chaining enabled by skills. ChatGPT Skills describe entire tasks, allowing business users to chain together multiple agentic steps and interact with connected apps.
Projects within ChatGPT enabled file-sharing and instruction organization. Skills supersede this by allowing simultaneous use within GPTs, covering projects’ features while adding depth, modularity, and execution consistency. The ability to use multiple skills for complex, multi-step workflows positions skills as a utility layer above custom GPTs and projects.
Enterprise-Ready AI Features: Business Integration and Team Collaboration
Skills are currently available for business, enterprise, and EDU workspace accounts, not for individual users. This rollout is positioned for team-wide use: skills can be shared across organizations, acting as reusable SOP, templates, and copy-and-paste mechanisms. They incorporate connected company apps, enabling advanced business processes—such as live spreadsheet integrations, analytics reporting, and automating executive briefings.
Skills can be uploaded, created via chat (including using a “skill creator” tool), or constructed via an editor. For technical teams, existing skills can be imported from Anthropic Claude, further reducing ramp-up time and enhancing cross-platform flexibility.
Real-World Use Cases: Precision Applications for Everyday Business Workflows
Specific examples from the episode highlight direct business value:
Automated Executive Briefings: Skills integrate updates from connected company apps, auto-triggering perfectly formatted morning updates without manual intervention.
Budget vs. Actuals Explainer: By connecting live spreadsheet data, skills automate variance explanations, bypassing manual review and improving financial transparency.
Marketing Performance Summaries: Combine analytics across multiple platforms for repeatable, insight-driven weekly reports.
Contract Review Summaries: Encode legal review SOPs to empower team members to quickly understand agreements—even with limited legal expertise.
Automated Operations Reporting: Pull operational KPIs for standardized, uninterrupted reporting, ensuring no section is skipped.
Leaders can analyze their ChatGPT chat histories, identify repeated processes ripe for automation, and convert those into scalable skills. This not only streamlines workflow but ensures higher quality output, reduces human error, and increases measurable business value.
Practical Implementation: Step-by-Step Workflow to Deploy ChatGPT Skills
Key takeaways include:
Audit for Skills Creation: Review existing ChatGPT conversations, especially those with extensive refinement, and reverse-engineer them into skills for repeatable use.
Leverage ChatGPT Memory: Upload brand, workflow, and preferences files. Ask ChatGPT to analyze workstyle and suggest skills that will save time or enhance output.
Iterative Testing: Build skills through the skill creator tool, test outputs, and incrementally refine processes based on business needs.
Cross-Platform Flexibility: Download skills from Anthropic Claude and upload directly to ChatGPT, ensuring open standard compatibility and migration flexibility.
Leaders are advised to focus on high-impact, repeated tasks and to maintain skill libraries as they would traditional templates or SOPs, sharing these across their teams for maximum ROI and adoption.
Closing Thoughts: Business Value Beyond Adoption Metrics
ChatGPT Skills are designed to shift employee usage from basic tasks (meeting summaries, simple prompts) to transformative, workflow-driven business impact. By tracking adoption and business value, companies can prove ROI to stakeholders, enhance operational excellence, and move beyond underutilized AI investments.
Business leaders seeking specific, actionable AI upgrades should prioritize skills as modular, organization-wide assets—unlocking consistent, scalable, and high-quality business processes in the ChatGPT ecosystem.
For more detailed AI implementation insights and emerging features, follow Everyday AI and visit youreverydayai.com for daily updates and practical business guides.
Topics Covered in This Episode:
- ChatGPT Skills Feature Introduction & Overview
- Reusable Workflows for Business Procedures
- ChatGPT Skills vs. Custom GPTs & Projects
- Team Access: Enterprise, Business, EDU Plans
- Anthropic vs. OpenAI Skills Compatibility
- How to Build and Deploy ChatGPT Skills
- Skill Sharing and Collaboration for Teams
- Best Use Cases for ChatGPT Skills
- Practical Setup and Implementation Walkthrough
- Editing, Importing, and Managing ChatGPT Skills
Episode Transcript
Jordan Wilson [00:00:18]:
Buying AI tools is the easy part. Getting your employees to actually use them for anything meaningful, that's where most companies fall apart. Section's own research shows over 90% of employees only use AI for basic tasks. That's not ROI. Section coaches every employee on real role specific use cases, tracks who's driving AI impact, and it gives you the data to prove it's working. For more, check out Section at sectionai.com. Imagine your day to day business life if you didn't have things like templates, SOPs, or even copy and paste. Well, maybe you've been using ChatGPT without the equivalent of those things.
Jordan Wilson [00:01:03]:
Yes. We've had for a long time inside of ChatGPT very helpful features like custom GPTs and projects. But I still think that there was a certain level of modularity and scalability that we were maybe missing. And OpenAI may have just changed that with their recently new feature that they released, which is chat GPT skills. So on today's show, that's exactly what we're gonna be diving into to show you how to use them and some of the best use cases. So here's the big picture. ChatGPT skills are essentially reusable workflows that teach ChatGPT how to follow very specific business procedures consistently that you upload, and you can do them in natural language. So they essentially package repeatable tasks, your company's domain knowledge, and executable scripts into a more modular format.
Jordan Wilson [00:02:05]:
So in the same way, like, you might have very strict and, refined and defined templates and SOPs at your company, the same thing is now available with chat g p t skills. And if you're hearing this skills thing and you're like, wait. Hasn't this been around for a long time? Yes. Technically, Anthropic created and popularized skills back in the 2025. And now OpenAI has finally adopted them inside of chat g b t. So previously, skills were available on the developer side if you were using them in the API or inside codex like I was, but now they are available inside of chat g b t. Downside is even if you're on a paid $20 a month, plus plan or a free plan or the $200 a month pro plan, you're not gonna find skills there. So there's the caveat.
Jordan Wilson [00:03:03]:
Right now, these are being rolled out and maybe even positioned as teamwork skills. Right? Because they're only available if you are on the business enterprise team or EDU plans. So on today's show, here's exactly what you're gonna learn if you stick around for the next twenty some minutes. You're gonna learn exactly how to build and deploy your first chat GPT skill live because it is putting AI to work on Wednesdays, our weekly segment where we go hands on, and we're gonna be doing this live. Then you're gonna be able to explain the differences between regular custom GPTs and these new skill workflows. And at the end, I'm gonna share with you some example and, I think, really good use cases of skills. And along the way, I'm actually gonna give you what I think is the one cheat code, the best way to actually start using skills today and not really just following the leader and doing what everyone else is doing. That sound good? You ready to maybe start implementing, you know, templates and SOPs and essentially copy and paste into you or your company's workflow? It's exactly what we're gonna be unwrapping today.
Jordan Wilson [00:04:15]:
And, apparently, you all wanted this. Right? So if you are listening on the podcast and you're like, man, this guy is always covering these, you know, random things. Well, I asked you what you wanted to hear. Right? So on Wednesdays, like I said, we always go hands on, doing some live demos on a newer update model release feature and, you know, I put it up for a vote. And overwhelmingly, our audience said, let's go and learn skills. Alright. Well, let's learn together. And if you're new here, welcome to Everyday AI.
Jordan Wilson [00:04:44]:
My name is Jordan Wilson. And if you don't know any of this, we do this every single day, not just Wednesdays. It's a daily unedited, unscripted, livestream podcast, and free daily newsletter helping everyday business leaders like you and me keep up with the nonstop breakneck developments of AI. I tell you what's noteworthy, what matters, and you take that information as your cheap code to grow your company and career. So it starts here, but make sure you go to our website at youreverydayai.com. We're gonna be recapping the highlights from today's show as well as giving you all of the other AI need news that you need to know to stay ahead. Alright. So chat g p t skills.
Jordan Wilson [00:05:22]:
I think this is a big shift into maybe how teams are ultimately using ChatGPT. I kinda think of it as the, you know, kind of a line in the sand. There's the old ChatGPT that was more of, a friendly assistant that it's a chatbot. Now today's version of ChatGPT, it's a it's a full AI operating system. Right? Because we've gone from just simple prompts to then it got a little bit more scalable. Right? And you didn't just you know, with prompts, it's essentially one time instructions that live and die there. And then we, over time, got things like memory and chat history, which helped, and then we got custom GBTs. You know, now almost two years ago, which allowed you to create a custom version of chat GBT.
Jordan Wilson [00:06:05]:
And then we got projects. Right? A way to better organize your chats, but also, share files and instructions across those chats. And now I think skills are a bigger step in that same direction. So I do think skills kind of build off of some of the momentum that custom GBTs and projects and memory helped create. And I really do think it's the one thing that encapsulates, all of those things together, which we'll unpack a little bit more. But this is essentially skills are reusable workflows that your company can package together, you know, your SOPs templates ready to go. So a skill essentially just tells ChatGPT how to execute a highly specific workflow the same over and over without you, the human, needing to reexplain and course correct each and every time. So here's what's new.
Jordan Wilson [00:06:58]:
So like I said, they launched right now in beta just for Teams. So, the enterprise plan, business plan, and e d u workspace plans. They are powered and made possible by the new g b d five four model. That's the technical backbone. And, eventually, we've been told that you'll be able to convert those custom GPTs, into skills. It's not available yet, but it does seem like that's gonna be rolling out to enterprise plans. But it's very easy to create these, but, you know, from existing GPTs projects because it's super simple, and I'm gonna show you how to do all of that. And the cool thing is, like I talked about, skills really build off of everything else that you already have because skills can use apps.
Jordan Wilson [00:07:43]:
You can use skills in GPTs at the same time, and skills essentially cover the basic functionality and then some that you would get inside of projects. So now that you know how skills are kind of implemented in chat g p t, let's maybe hit rewind and be like, what the heck are skills? So skills, they're just reusable workflows. Think of it as SOPs, your company's standardized playbook that teach AI agents exactly what they need to do each and every time a user invokes those skills. From a visual standpoint, they're folder bundles. Right? Each skill is a folder with a, you know, skills dot markdown, file containing core instructions. So you might look at skills and be like, oh, that seems technical, not for me, but you don't have to write them by hand. Right? ChatGPT will write your skills for you conversationally. And there is something called the progressive disclosure.
Jordan Wilson [00:08:40]:
So the, at first, the AI just reads the skills name and descriptions, and then it fully loads those all the instructions and the executable, actions and files only when the skill is triggered. So from a visual perspective, think of it like this. And this will maybe help even our podcast audience better understand. Right? I I am gonna be sharing some visuals. And, yes, on Wednesdays, maybe those are the shows that you should go home or at the office. Go to our website, youreverydayai.com. We always have the video version up. You can watch that for free, but I'm gonna do my best to describe visually what this looks like.
Jordan Wilson [00:09:17]:
But skills, in the same way, if you've ever downloaded a program on your computer, right, and you unzip it, you unpack it, and there's usually multiple files in there. And those files essentially tell the computer how to run a program, and there's multiple different files. Right? So that's essentially what a skill is. It is a kind of a parent folder with, you know, different markdown files, different references, assets. So these are all things that you can customize in natural language. ChatGPT can do it for you. You can upload files, do all of these different things. So literally think of it.
Jordan Wilson [00:09:52]:
You probably have a similar setup like this maybe in your organization where it has all the different templates. Maybe there's an instructions file that says how you use the templates, you know, brand guidelines, all of those things. Those are the exact, you know, kind of the exact backbone that skills, kind of can do for the front end AI. So, essentially, it uses the agent skills open standard. So, I'm gonna get into how these are reusable, both bringing different skills inside of CheggiPT skills and how you can ultimately do the same thing and use them elsewhere. But how you use them, well, CheggiPT will automatically recognize relevant skills based on their name, or you can also explicitly activate a desired workflow by mentioning its name. Right? So it's not the same as a GPT where you go and find the GPT, Or if you're in a normal chat, you can click the at button and start typing and then find your GPT and click it. Right? It will sometimes know or infer that you want to use a skill or you can call it out by name and use the skill that way.
Jordan Wilson [00:10:59]:
So like I said, Anthropic made this happen. Right? And you're probably if maybe you're wondering, well, what's the difference between Anthropic skills and GEDT skills? Well, the good thing is they can be used interchangeably, right, which is a huge benefit for people that are maybe using both in their day to day work, or maybe you're trying to transition from one to the other. But, essentially, Anthropic created and popularized, this skills format, and now it's widely used across the AI landscape. And OpenAI essentially just adopted the same open standard after Claude's success. So some of the differences, you know, skills have only been out in ChattopiTE for a week and a half, and they've been out for, you know, now, like, five and a half, almost six months, I believe, inside Anthropic. So when Anthropic rolled out skills, they were a little rusty. Right? But that's what happens when you are literally blazing the trail. Right now, Anthropic skills are much better.
Jordan Wilson [00:11:54]:
But I will say, OpenAI skills to start with, really, really good. And for me, I actually prefer the UI, the user interface, and user experience of creating and editing skills inside of chat g b t versus Claude. It's, to me, a little easier even though, you know, I do think anthropic skills implementation is a little bit more mature, and maybe a little bit better in terms of very difficult workflows right now. I do think ChatGPTs are a little bit easier to use and easier to modify and just simpler to understand, period. So now let's talk about the differences between a skill versus a custom GPT or a project. So custom GPTs are great. Don't get me wrong. But they lack a lot of the depth and breadth that you get in a skill.
Jordan Wilson [00:12:50]:
Well, mainly because you can use a skill while you're still using a GPT. But think of it like this way. I like to think of skills as describing an entire task in its entirety. Right? Where I think custom GPTs maybe help get you closer to a goal, but they're not necessarily at least by default, really meant to chain all of these agentic skill sets together one after another, where that's exactly what skills are. Right? Like a very think of the most detailed, you know, SOP that you've seen at your company. Think of skills that way. Right? Where it can interact with other apps. That's the great thing.
Jordan Wilson [00:13:29]:
Skills can interact with different apps. You can use them at the same time as you're using GPTs, and then you do get the same features and functionalities that you get within projects. So by default, I do think skills are, instantly better, more useful, and hold more utility than GPTs and projects. Although there is a lot of crossover, I think, ultimately, skills might be the, kind of feature or function that takes off the fastest and goes the furthest. And you can also use multiple skills to combine automatically to complete a complex and multi step project more effectively. Alright. Let's get in and get our hands dirty. We're going live.
Jordan Wilson [00:14:10]:
But first, I gotta take a drink. Quick word from our partners. Here's a harsh truth. Your company is probably spending thousands or millions of dollars on AI tools they're being massively underutilized. Half of companies have AI tools, but only 12% use them for business value. Most employees are still just using AI to summarize meeting notes. If you're the one responsible for AI adoption at your company, you need Section. Section is a platform that helps you manage AI transformation across your entire organization.
Jordan Wilson [00:14:43]:
It coaches employees on real use cases, tracks who's using AI for business impact, and shows you exactly where AI is and isn't creating value. The result? You go from rolling out tools to driving measurable AI value. Your employees move from meeting summaries to solving actual business problems, and you can prove the ROI. Stop guessing if your AI investment is working. Check out section at sectionai.com. That's sectionai.com. Alright. Let's get our hands dirty, shall we? Alright.
Jordan Wilson [00:15:22]:
So here is the part of putting AI to work on Wednesdays where sometimes things can go wrong. So we'll see if they do or not. Alright. Ready? Here's my little secret on what you should be doing. So I'm gonna get this started, and then we're gonna come back to it, as we go, and I'll tell you exactly what's going on. Alright. So I just hit enter because, yeah, I like to do these things live. Sometimes they work well, sometimes they don't.
Jordan Wilson [00:15:51]:
So if you want to find skills, remember, you do have to be on a business plan. So business enterprise, EDU, etcetera. Essentially, a team plan. This is not available yet for individuals. I hope they do make it. So in the bottom left hand corner, you're gonna click your icon, and then you're you should see a skills, section, which kinda looks like the icon is kinda like a little brick. So from there, I've been cleaning up my skills. You know, I had a lot of them that I was demoing around, but then you're gonna have a new skills section, which might look and function a little bit similarly as the GPT section.
Jordan Wilson [00:16:26]:
So you're gonna have ones that are installed. So for you, by default, you're only gonna have the skill creator, which is OpenAI's skill that yeah. It's kinda meta. It's a skill that helps you create skills. Alright. And like I said, there's skill repositories. Right? You can download skills, all those things, you know, in other places and then upload them. So you have your installed, skills, ones created by you, and then skills that you can share across your team.
Jordan Wilson [00:16:55]:
That's the big unlock here. Right? I'm just showing off an individual use case here, but imagine sharing these across your team in the same way that you can share, you know, GPTs, sharing skills. You know, again, think of it, SOPs, templates, copy and paste, time savings, share that across your organization is the big unlock. And then in the upper right hand corner, you can click new skills. So you can create a skill with a chat. So you can do that conversationally. You can do it even without using the skill creator, skill, although that would be used inside of a chat. I know that's confusing.
Jordan Wilson [00:17:32]:
So there's technically four different ways. You could do a chat naturally without using the skill creator. You could do a skill using the skill creator. That's number two. You can just create with the editor from scratch, so not in the chat interface, a little more technical. Right. And then you can edit them as well, or you can upload them from your computer. Alright.
Jordan Wilson [00:17:51]:
So that's the four different ways that you can create or import skills. Now let me take you to the little cheat code here because I think the natural human tendency is to go find the most popular skill and use it for yourself. Not always a good idea. Don't always go out looking, you you know, don't be a, solution looking for a problem. Instead, use something very powerful inside of ChatGPT, and that's its ability, to tap into its memory, how you use ChatGPT, your chat history, and then I would ask it some questions. So I'm gonna show you exactly how I'm going to, well, reset this up. I already had it set up, and I deleted it so, you know, could, not show too many things on my screen here. But I essentially have two working files that I use across all different large language models.
Jordan Wilson [00:18:46]:
There are two markdown files, which is essentially just a text file. Right? It's about everyday AI and then about me, my preferences, how I work, all of that good stuff, my brand voice. All of that is in these two files. I keep them updated constantly so that I can, at any point, you know, use them. They're in my Google Drive so I can connect dynamically, etcetera. So I said, based on the attached files, please carefully go through my day to day workflow, understand what Chatt GPT skills is capable of, and briefly suggest the 10 most helpful skills I should implement and how they'll save me time. You could also just say, hey. Based on, you know, your memories about me and my chat history, same thing.
Jordan Wilson [00:19:26]:
Because chat g v t AI systems are so good at knowing things about your own personal work style that you might not even know about yourself. So I say when you're trying to figure out what skills to start with, see where you're going wrong or what you're constantly using chat GBD for or what your ultimate, you know, deliverable or artifact is, because then you can kind of reverse the process and start with what you actually need, not just what others are doing. Alright. So I'm going down here, and we're gonna pick one. So there's the daily AI. Right? I'm not gonna read all 10, but it gave me the daily AI research brief builder, the Jordan hot take extractor. Excuse me. Got a cough.
Jordan Wilson [00:20:11]:
Oh, fantastic. I've been sick since November, more or less. If I sound nasally, yeah, I've just been sick for months. Alright. Jordan hot take extractor, I kinda like that one. Alright. There's a lot of other ones. I'm just gonna use this one, and I'm gonna say, let's build number two.
Jordan Wilson [00:20:30]:
Alright. So give me 10 suggestions. All I have to do is say, let's build number two. It's probably gonna go through and come up with some clarifying questions, which is good. Alright. So it's asking input. What will I usually give it? I'm gonna say podcast transcript. Alright? Then I'm gonna say the output.
Jordan Wilson [00:20:49]:
What should the output produce every time? So I'm gonna say it's saying five to 10 Jordan style hot takes, three episode angle titles, five. I'm just gonna say all of those. Alright? And then three, where should I pull the context from? Should this skill work only from the pasted uploaded text or also search your connected? So I'm gonna say, only from the pasted, uploaded text. Alright. So simple enough here. I'm using the skill creator. And, again, you can look at the bottom in the prompt input box. It's highlighted the skill creator.
Jordan Wilson [00:21:29]:
But even if you just say, help me turn this into a skill. So, you know, one thing aside from going through this process that I'm showing you right now, another great example is go look at a recent chat that you had with chat g b t. There was a lot of back and forth, but you finally got something just the way you wanted. Hopefully, you went through the prime prompt polish and refine queue. Right? Because then you got a much better output. So all of our people in our inner circle probably went through and did that. Here's a harsh truth. Your company is probably spending thousands or millions of dollars on AI tools that are being massively underutilized.
Jordan Wilson [00:22:15]:
Half of companies have AI tools, but only 12% use them for business value. Most employees are still just using AI to summarize meeting notes. If you're the one responsible for AI adoption at your company, you need Section. Section is a platform that helps you manage AI transformation across your entire organization. It coaches employees on real use cases, tracks who's using AI for business impact, and shows you exactly where AI is and isn't creating value. The result? You go from rolling out tools to driving measurable AI value. Your employees move from meeting summaries to solving actual business problems, and you can prove the ROI. Stop guessing if your AI investment is working.
Jordan Wilson [00:22:59]:
Check out section at sectionai.com. That's sectionai.com. Oh, excuse me again. There we go. Yeah. I keep muting my mic. So much it's it's unedited, unscripted y'all. This is it's real.
Jordan Wilson [00:23:21]:
Alright? So go through that chat that you went through, and you finally got a great output, and then just reverse engineer it and say, I wanna turn this into a skill. Outline every single correction, mistake, pivot, everything we went through and turn this into a skill. Right? So at any point, you can just click the backslash button and then start typing skills and then go to the skill creator. Alright. So this is probably gonna take a couple of minutes to build. Alright? I'm not just gonna, keep blabbing on. So again, instead, I'm gonna pivot here a little bit and go into my Claude account. So the great thing, this uses the agent skills open standard.
Jordan Wilson [00:24:09]:
So what that means is, well, skills kind of work anywhere. Right? So, you know, you gotta tip your cap to anthropic between, you you know, MCP, the model context protocol, agent skills, a lot of things that they've kind of innovated and have helped make the AI community at large better. So I now am in my Claude account. So if you wanna know where this is, it's they just moved it kind of recently. So it's on the left hand side. You go to customize skills, and then you can choose your different skills there. So in the upper right hand corner, I selected AI researcher. Alright? And I'm gonna download it.
Jordan Wilson [00:24:47]:
So you can click the three little dots in the upper right hand corner, go into download. So now I'm going to go back into, Chat GPT in the skills section. Okay? And I'm just gonna click new skill. I'm gonna say upload from my computer, and then I'm gonna go ahead and upload that one from Claude that I just did. And within a second or two, it says skill uploaded. Pretty pretty simple. Right? So now, I'm gonna go ahead. There it is, AI searcher.
Jordan Wilson [00:25:18]:
So, at any point, you can click on a skill, even the OpenAI skill, and you can see exactly how it's set up. You can read it. Right. So for the skill creator as an example, here's the skill markdown file. Here's the references folder with the different, files that are in there, the scripts, the different Python scripts, the license text. So like I said, in the same way, you know, if you do any coding, right, obviously, you probably understand this. But even if you don't, if you've ever downloaded a program in your computer, and there's all these different files and folders and license text, right, it's kinda like that. You are literally taking and bundling up your company's knowledge, your files, you know, different things, different access points, and putting them all into a, essentially, an executable skill folder that then OpenAI, Anthropic, and others can use.
Jordan Wilson [00:26:10]:
Alright. So on this skill section, there is a nice little shortcut. You can hover over any of these skills, and then you get the option to edit them. But you can also click the little chat icon, and that'll just start a new skill right away. So I'm not even gonna do anything here. I'm just gonna say I'm gonna say give me 10. I'm gonna say give me the top 10. Alright? That's all I'm saying.
Jordan Wilson [00:26:33]:
So, again, not having to go through, you know, refine all of those things. It's gonna go through. Alright. So when I was trying this earlier, it it actually did a little bit better job. I think it was because I was in the extended, the extended thinking. I'm gonna try this again. Alright. I'm gonna say, alright.
Jordan Wilson [00:26:56]:
Load my skill up there, and I'm just gonna say top 10 stories. And we'll see if it comes back with clarifying questions. There we go. So now it's using the skill. So I don't have to go in and tell it the different things that I want. So, you know, let's just take a quick look at this skill that I have. So this skill, I can go in and edit it. So the AI searcher skill okay.
Jordan Wilson [00:27:28]:
Interesting. So yeah. Sometimes things don't work well. So even though the skill is working, I can't go in and edit it for some reason. That's interesting. So I'm gonna go into the skill creator. Or now I'm gonna go into my weekly triage and edit it. Alright.
Jordan Wilson [00:27:43]:
So this is a different one, that I created. So in this instance, I have it. The description is it triages the user's upcoming week by reading Gmail and Google Calendar, identifying important meetings and commitment driven driving emails, doing lightweight Internet research to fill context gaps, and producing a one page weekly plan plus a scored backlog and recommended time blocks. So, in this instance, I can go through and just change these things very simply. Right? It's a Word doc. I can go in if something's not working. I can just edit it live from here. Right? And the good thing, like I said, with skills, they can access files and folders.
Jordan Wilson [00:28:25]:
Right? Over here in the files, I can upload different files and then have it reference those things. I can go and change anything that I want to right there in the skill editor. So it's very easy to manage and edit these skills. Alright. There we go. And just like that, it gave me my 10 stories. So it went through the AI researcher skill, which if I look at the Claude skill here, right, it searches for and presents the latest AI news from the past twenty four hours focusing on large language model updates, Gen AI breakthroughs, developments from AI companies like OpenAI, Anthropic, Google, Meta, Microsoft, Apple, Nvidia, Amazon, Salesforce, Adobe, IBM, etcetera. Right? So I didn't have to go through and describe.
Jordan Wilson [00:29:12]:
Right? It's a lot more than that. I didn't have to go through and describe all these things, what I wanted. I just invoked that skill, and I said top 10 stories. And it knew all those things because I had technically, via Claude, I had already taught it, and I had gone through and made corrections and made updates and said, here's how we want the format. I want the format very simple, very easy, with a heading, with a date, what happened, why it matters. That's it. Right? So it went through, and it did all that for me. And this new, AI searcher skill went through, worked correctly.
Jordan Wilson [00:29:44]:
Right? I'm looking through yeah. It got it got everything. It got all of the, most recent stories from the last day, so it did a great job. Alright. Now let's see if my skill is done. So, to go back and remind you before we got slightly sidetracked, that's what AI at work on Wednesdays. Yeah. We just do things live.
Jordan Wilson [00:30:05]:
We bounce around. We try to explain what's going on. Alright. So remember, I uploaded, and I recommend you do this. I uploaded these files about me or just say based on my chat history, suggest 10 different things. The one that I liked was kind of the Jordan hot takes extractor. Say the truth, I actually use this a lot in Claude, and I'll probably start using it a lot in chatty bitty. A lot of times, I'll have, you know, longer podcast episodes, and I'm like, wait.
Jordan Wilson [00:30:32]:
I thought I had a pretty good take in there, but I completely forgot what I said sometimes. Right? This thing's unedited, unscripted. Yeah. Sometimes I have notes, to help keep me on track a little bit, but I'm like, man, I had a great point about a b c. And now someone's asking me, how do I find this? Right? So I can run this automatically and just put them all into a file or folder, and then I can more easily find them. So it went through, it created this skill. Right? I gave it some feedback, and then I go to the bottom, and there we go. It says the Jordan hot take extractor.
Jordan Wilson [00:31:04]:
Right. So right now, it's a draft. I can click on it, and then I can click install. So very easy. One click install. Like I said, you don't have to know anything about markdown. You don't have to know anything about YAML, about Python. Nothing.
Jordan Wilson [00:31:19]:
If you can go in and talk to chat g b t and approve some things and iterate, have a conversation, if you can be creative and strategic, you can start using skills in minutes. Alright. Then I'm gonna go ahead and try in chat. So here's what I'm gonna do. I'm not even gonna give it any instructions. Right? That's the whole point. I'm gonna go in on my, my podcast episode here, from the other day. I'm just gonna copy and paste this entire transcript.
Jordan Wilson [00:31:45]:
Let's see how it how it works here. See what model. I'll do standard thinking. That's fine. Alright. So literally nothing. I said nothing. I didn't have to click anything aside from once the skill is active.
Jordan Wilson [00:32:02]:
That's it. Again, think of the benefit of using standard operating procedures, templates, the concept of copy and paste. Right? So now all these things that I might normally do in my day to day workflow, I can turn all of them into individual skills. I think, the two biggest and best pieces of advice here, as we wrap up our live demo portion, and then I'm gonna tell you, I think what our five great, skill examples. Two big things. Number one, go find those long conversations that you had with Chatt GPT where you had to do a lot of refining, a lot of back and forth, but you ultimately got the end deliverable exactly how you wanted it or needed it. Go back and turn that into a skill. Take your time in doing it, right, and then iterate, use it once or twice, look at the chain of thought, update it.
Jordan Wilson [00:32:52]:
Secondly, do exactly what I just showed you. Right? Say, hey. Based on my chat history, based on my memories, or just upload files about yourself based on all this, recommend 10 different skills that could end up saving me time or help me produce, something more valuable to my clients, my potential, you know, customers, etcetera. So, we'll see if this one works now that I talked it up. There we go. Alright. So I pasted this long transcript, and, it said right here, it said it used the Jordan hot take extractor skill. Alright.
Jordan Wilson [00:33:24]:
I can go in and view that, edit it, download it. Right? Because now I can take this elsewhere if I wanted to, but it did a good job. So I've got my core stance here. It got my ranked hot takes. You know, one of them was most AI layoffs are PR. My second, hot take there was Wall Street rewards AI layoffs. Absolutely. Right? So a good way to kind of get my opinions or my hot takes, straight out, and then it got three additional episode angles.
Jordan Wilson [00:33:52]:
So I wanted to do follow-up episodes and then quotable lines. Alright. Hey. This is that's not bad. AI tools are the easy part. Getting people to use them for real work, that's where companies fail. I agree with that. It's because I said it.
Jordan Wilson [00:34:06]:
Alright. So there you go. Now you know the easiest way to go in and start using skills immediately. So let me quickly share, three or no, five that I think could be helpful. Alright. So one automated executive briefings. So pulling in updates from connect connected company apps. Remember, you can pull in information from multiple different apps, and then, you know, auto triggering that to perfectly format your morning update without needing to manually select a GPT or go into a project and, you know, connect a bunch of documents.
Jordan Wilson [00:34:41]:
Number two, budget versus actuals explainer. So pulling live data from connected spreadsheets to explain any variances in budgets. Right? So, again, versus saying uploading two documents, going through explaining, here's what I want you to do. Turn it into a skill. Third, marketing performance summaries. So drafting a weekly performance digest with insights and recommended actions, and this allows you to combine multiple analytics apps into one flawless, repeatable reporting workflow. Next, here's a great one. Contract review summaries.
Jordan Wilson [00:35:12]:
Let's be honest. Not everyone has the same skill sets. Right? That's why I think the example of templates are great. Because think of like a PowerPoint template. Not everyone is a good designer. But if you are a good designer, you can give someone the ability to design something that looks fairly good. Right? So in this example, a contract review summary, if your company has a strict process when it comes to legal review and you have all the documents, you have the examples, you have the SOPs, well, turn that into a skill because then you at least give people, the, ability to quickly understand maybe a contract or a service agreement or to be able to know where you can start to redline something without having to have all those skills. And then last but not least, automated operations reporting.
Jordan Wilson [00:35:59]:
So that, you know, pulling in operational KPIs from sheets, draft a weekly operations update, and that can kind of function as a strict SOP, ensuring that no section of the mandatory report is ever skipped or forgotten. So, again, think. What do your people do over and over and over? And maybe there's some GPTs that work great that you should probably turn into skills. Maybe there's GPTs that lacked a little bit, that failed, because it didn't have a certain feature or functionality that you now have within, skills or projects. Right? Maybe there's something in projects, but you're like, ah, it's a little too limited. It didn't work really how we needed it to. So now I think you have a new tool, and sometimes it's not always the big release. Right? It's not always going from, you know, GPT to five to GBD 5.5 that's gonna move the needle.
Jordan Wilson [00:36:55]:
Sometimes it is these, quote, unquote, smaller features that maybe you didn't even know about, right, that can really help your company or your department turn a corner and work smarter, work more efficiently, and hopefully, even create more valuable outcomes, that can really push your company forward. Alright. Was this one helpful, y'all? Putting AI to work on Wednesday. So, yeah, maybe you tune in once a week. We did change things up a little bit FYI, and I'll just explain that here quickly. So Mondays, we bring you the AI news that matters. On Wednesdays, we usually go deep with one new feature, or if there is a big model release, we'll do that. And then on Fridays, we're kinda starting this new thing called feature Fridays because what I realized, it's very tough to choose that one thing to focus on on Wednesdays.
Jordan Wilson [00:37:42]:
And a lot of the most useful, updates really just become a literal one second bullet point in our Monday podcast. So, that's kind of the lineup. And then Tuesday, Thursday is right. We'll rotate the shows. Been doing a lot of the start here series and some guest interviews here and there as well. So I hope this was helpful. If so, tell someone about it. Tell someone on your team, and you're like, yo.
Jordan Wilson [00:38:04]:
We need to start using these skills. I just broke down the easiest and the simplest way for you to start using these today. Give giving you and your company, the right information on how to start using skills as reusable templates today. So when you're done listening this and sharing this with your friends, please, if you're listening on the podcast, please make sure to subscribe, then go to youreverydayai.com. Sign up for that free daily newsletter. Thanks for tuning in. We'll see you back tomorrow and every day for more everyday AI. Thanks y'all.
Jordan Wilson [00:38:42]:
If you're leading AI at your company and your employees are barely scratching the surface of what AI can actually do, you need a better plan. Section coaches employees on real role specific use cases, tracks adoption across your entire organization, and helps you prove the ROI to your CEO, your board, or whoever's asking. That's the job. Section helps you do it. Check out more on Section at sectionai.com.