Anthropic Just Changed How We Build Skills Forever (screen record)

[00:00:00]Anthropic's just dropped one of the most interesting features that I've ever seen for Claude. And this might completely change the way that we use it. This feature is a new way to build out Claude's skills. So, instead of needing to write skills, we can now have Claude record our screen, watch what we're doing, and we could physically talk through the process of what we're wanting Claude to automate, and then it's going to analyze that and turn that into a skill. So, in this video, I'm going to break down exactly how it works. I'm going to test it out so you could see it in action. And then we're going to break down whether or not this is a game-changing feature like most people are going to be talking about.

[00:00:33]And I will say my answer is probably going to surprise you. So, without further ado, let's dive right into this video. All right, so without wasting any time, let's dive in and begin testing this out. So, first of all, this is only available inside of Claude Co-work. And if you want to use Claude Co-work, make sure to download the desktop app. There will be a link in the description to do so. And now, where we're going to see this is if we come over to this plus button here. Once we toggle on Co-work, then we will now see this little button here that says record a skill. If I click on this, what it's going to do now is it's going to give me this prompt here. Right here, it says record a skill. Your screen, clicks, typing, and voice are recorded, then sent to Claude and turned into a repeatable skill.

[00:01:14]Don't type passwords or secrets or display sensitive information or private conversations while recording. And this brings up a really good point, and that is security, which is something I'm going to talk about later on in this video and give you my honest thoughts on. Next up, we have two other buttons.

[00:01:27]We have a start recording button, and then we have our microphone. Because we're able to literally talk through while we're doing something on our screen as if we're teaching an employee how to do a specific task or process.

[00:01:38]Let's test this out now. So, I'm just going to click on record. Next up, you could see it pulled up this little icon here. And now it's actually recording my physical screen. So, let's go and explain a task. All right, so what I am trying to do is I want to automate basically copy and pasting given YouTube comments and adding it to this YouTube comment tracker spreadsheet. From here, I basically wanted to decide whether or not it's worthy of creating a video and order to give me YouTube video ideas based on the comments that I'm getting from my subscribers. So, let's come here and I'm just going to physically show on my screen how to do this task. Because before, if we were to create this skill, then I would have to like explain to a T which buttons to click on, where on the screen to click, etc. for it to understand how to navigate through YouTube Studio, which is what I'm having it go through. And that could be a bit of a headache and that's kind of where the browser use and computer use capabilities of things like Claude and Claude Co-work kind of fall short. So, hopefully this fixes it. Anyways, I'm just going to come here. So, Claude, what I want you to do is I want you to take all these comments that I get for only my long-form YouTube videos and I want you to paste in the comments. From here, I want you to for all of these make sure that you are wrapping the text that way, you know, it shows the full comment there. And then for each of these, I want you to analyze based on the video, you know, is this worthy of a video idea? And for this one, for example, what's the cost of the entire project? That's probably not worthy. So, I want you to go through and reason based on what you know about my YouTube videos and the ones that perform well in order to decide whether it's worthy of making a video about. And again, I want you to only go through my like long-form YouTube videos. Don't go through shorts.

[00:03:18]What I would do is I'd come here and select just my videos for content type and then copy all these. So, for example, would be good to get a side-by-side Co-work versus um ChatGPT work competition. Just open up the spreadsheet, paste that in. Again, you want to make sure that it's always wrapping the text. And then this one, in my opinion, is actually worthy of a video idea. So, this is the process. I just want you to go through, copy all these comments, and then basically decide whether or not this is worthy of a video idea. This one I would say isn't. All right. So, now I'm just going to click on done and you could see it is actually processing the 73 steps that it saw through the video. And this is my first time actually testing this out, so I'm really interested to see how capable and how spot on this actually is. I'm interested to see the logic behind how it's able to break all of this down. So, looks like it took screenshots throughout this entire workflow, and I believe it took about 76 screenshots or something like that. And then it's also transcribing the entire recording of the video right here. This is the full transcription. Okay, so now it took maybe like 2 minutes here, and then it came up with this. So, it went through, watched the recording, and turned it into a skill. Here's what it does in plain terms. Then I'm going to read through very briefly this skill.md file that it created here that I could then save as a skill. So, first of all, it says it grabs the comments, opens YouTube Studio, sets the filters like I did because I explained that in my voice over, and then logs them into the spreadsheet, pastes them into column A.

[00:04:43]You can see it's pretty descriptive of exactly like where exactly we're pasting this information, what buttons to click on, etc. Then it makes a call, picks whether or not it is good for a YouTube video, and then it also noticed, and I never mentioned this, that it never touches the comments. So, it doesn't reply, like, or delete these comments, which is cool that it was able to figure that out itself, which I guess is kind of self-explanatory. And then now we could actually save this skill here.

[00:05:07]But, actually let me go ahead and save that. Now, here we go. Let's quickly just go through the actual skill.md file that it wrote so we could see basically how detailed it is, which is obviously going to be really important to recreate that workflow. So, it breaks down what exactly this is. Turns viewer comments into a video idea pipeline. It breaks down the specific tools that it's going to use, which it's using the Cloud and Chrome MCP tool. It breaks down step-by-step how to do this. Breaks down how to log them into the tracker. It even shows a visual of what the columns look like. And then here is a pretty detailed breakdown on what justifies a video idea and when it should select either yes or no. And then breaks down the report back here as well as some specific edge cases. So, this is a pretty detailed skill in the file.

[00:05:49]Obviously, we could update this over time. All right, so now that we saw it in action, let's break down my actual thoughts on this, if I think it's capable, when I think we should use this, if we should even be using it, and other alternatives that might be better than using the record skill feature that they just released. First of all, what I think after testing this out is I think that the majority of the time that we'll be using this skill record feature is for different things that don't have specific connectors inside of Claude. If you don't know what a connector is, this is how it's able to work across our different applications like Slack and Gmail, Google Drive, etc. It's an MCP server that it's using in order to navigate throughout those applications.

[00:06:26]I do think that that's going to be more reliable than having to walk through and try to basically explain how to do different tasks throughout these applications while screen recording.

[00:06:34]But, where I do find this very valuable is when we need to do things that require browser use capabilities. If you don't know what browser use, this is basically the function that allows Claude to go and actually use our browser or our computer to do things like fill out forms, click on buttons, navigate different websites, etc. So, more of the manual work that you actually do on your computer aside from using a connector. And a perfect example of that is what I showed you inside of the YouTube app. There is no way to connect Claude to YouTube, so I have to instruct it manually in order to go and copy those comments and paste them into Google Sheets for me. And I think it's much more valuable in order to screen record what it is you're doing and literally talk to Claude in real time about how to perform this task, rather than just sending off a prompt to Claude using browser use and expecting it to know exactly where to click on things on your computer. So, to summarize that, if there's a task you want to do that has a connector, I would consider using that first. If it doesn't have a connector, you can then record and walk through a skill using the browser use capabilities. Now, if there is an app that you can't connect to inside of Claude, I highly recommend to use something called the Zapier MCP. If you don't know what this is, Zapier is a platform that connects to 9,000 plus different applications and it's really easy to plug Claude directly into all those apps. It includes a majority of the apps that you use on a day-to-day basis. Now, in order to give you an example, this is an MCP server inside of Zapier that I created and there's a bunch of different apps that I can use that I can't connect to inside of Claude. So, for example, School and Beehiiv are different tools that I use every single day to help grow my business, but there's no way to connect those inside the Claude app. Well, with the Zapier MCP, I'm able to perform actions across both of those different applications and I personally would prefer to use this as opposed to using this new record skill feature from Anthropic and hoping that the browser user able to figure out how to do those tasks. If you guys do want to try out Zapier MCP, there is a link in the description for you to test it out. Now, I do want to say I really do think this is a step in the right direction. I personally know friends of mine in the AI space that have Meta glasses that are literally recording what they're doing on their computer all day long in order to help them optimize their workflows and come up with ideas for what Claude can help them automate. And I think this is a step in the direction for us to be able to like record our screen, walk through as if we're talking to an employee on how to do a specific task, especially ones that are a little bit more intricate and require a little bit more attention to detail instead of us needing to go and just like type in a prompt and hoping Claude can understand what we're trying to accomplish. Now, the question you probably have is is this safe based on privacy? And if you are worried about privacy, then maybe don't use this. You might not want Claude to see what it is you're doing on your computer and have access to all this information. But, if you do want to test it out, just make sure not to show like any banking information or anything that's confidential you don't want Claude to have access to. Other than that, I personally have no problem testing this out for myself if I'm not showing any confidential information.

[00:09:23]Anyways, guys, I hope you got some value. If you guys want more videos like this, subscribe to the channel. I cover all things AI for non-techies and have countless videos on how to use Claude Co-work. With that being said, thanks for staying till the end. I'll see you in the next video.