9 Claude Skills I Use Every Single Day

0:00There are over 500,000 Claude skills out there. GitHub is full of them, but most of them don't even work and some are just nicely formatted system prompts with a readme file. Very few are actually worth installing and you might think you don't need them. Models are already powerful enough, [screaming] right? Why add a skill file? But here's the thing, every model follows its own patterns and once you've seen it, you can't unsee it. That's why you need something to steer it. These skills are built by people in the trenches. You've got a meta engineer, a security researcher and they've repackaged what

0:33works for them so you can use it, too. From a skill that cut your token usage by 65% to one that creates motion graphics using natural language. I've tested hundreds of skills at this point and these nine are the ones I keep coming back to every single day. Thanks to HubSpot for sponsoring this video. We're starting with the absolute holy grail of Claude skills, the skill that arguably started this whole craze with over half a million installs of Claude's. I'm talking about the Caveman skill because why use many token when few token do trick? If you haven't heard about the Caveman skill before, then chances are that you are probably a

1:10Caveman yourself because this is unironically one of the most useful skills I've ever installed and probably the most entertaining as well. We all know Claude is a complete yapper. You ask for one simple request and you get three paragraphs of, "Great question. Let me walk you through my approach." That preamble is not [music] only annoying, but it costs you tokens and tokens equals money. What I love about Caveman is it drops all of it and just gives it to you straight. It's like having a spam filter for your inbox, but it also saves you tokens. The creator claims a 65% reduction in tokens saved, but I actually tested this myself and it

1:49was closer to about 35%. I'd rank Caveman higher, but everyone already knows about it, so I'll leave it at number nine. Next is a new skill that's been gaining attention from an up-and-coming developer. Millions of lines of code at Meta, Netflix, and now Cursor. The person who helped build and maintain the React compiler, that is who wrote number eight. Of course, I'm talking about Pista. [music] Pista is a set of skills from Potato with an E, and the one that everyone's going crazy about is potato mode. Her pitch is one of my favorite lines I've ever [music] read in a repo. I don't want to ship

2:26like a team of 20 slow artists. And then she says, "If you want to go fast, you first need to go deep." Which is the exact opposite of how everyone is currently using agents, by the way. The move right now is spin off eight parallel agents and pray. And you can do it. It technically works. It feels incredible for about 20 minutes until Sunday comes around and you're looking at 8,000 lines of code trying to figure out which one of your robot children broke your app. The insight in Pista is that the problem is not running

2:59parallel agents. The problem is trust. You cannot safely run 10 agents if you do not trust what the agent produces. Make one agent rigorous first, then run parallel agents. Once you have felt the difference, you cannot go back. Once you go deep, you can't go to sleep. And the cherry on top is the fact that these are the actual skills she uses every day at Cursor. She'll ship thousands of lines

3:27of code every single day. Okay, okay. Number eight was pretty solid, but if you thought that was good, wait till I tell you about rank seven. Hard coded API keys, security rules completely skipped, auto tokens sitting in local storage, and my personal favorite, letting the browser decide how much something costs. Do you know what that means? Someone opens dev tools, changes your $99 product to 1 cent, hits buy, and Stripe just processes it because your app basically asks the customer, "How much would you like to pay?" So, number seven is Vibe Security, built by Chris Rawrrock. I never know how to pronounce his name and the team at

4:07Alowa. If you've been anywhere near this side of YouTube, you probably already know Chris. I watch him all the time. This isn't just some generic prompt that says, "Check my app for security problems." It actually understands what your app is using. If you're using Supabase, it checks for Supabase specific security issues. If you're using Next.js, it checks for Next.js issues. And I think this skill is massively underrated. It has under 1,000 stars because the scary part about bad coding isn't that you intentionally wrote insecure code, the AI did. It confidently hardcoded your API key. It confidently skipped your security rules, [music] and you confidently clicked approve on it. So, use AI

4:49[music] to check AI. Run this on your app every time you make a big update. I ran it on a side project I'd already shipped 6 weeks earlier, and it found a few fatal [music] problems. All right, Vibe Security catches the vulnerabilities you did not know Claude wrote. But, there is another blind spot almost everyone has, and it is bigger than security. So, here's an uncomfortable truth I learned while researching for this video. Most of you are using maybe 10% of what Claude can actually do. You open the chat, you type, you close it. That is the whole workflow. Meanwhile, [music] Skills, Co-work, Code, and Design are

5:26just sitting there, untouched. And I get it. Anthropic ships new stuff faster than anyone can track. It is confusing. That's why I wanted to share this free guide called Claude at Work from HubSpot that maps the entire ecosystem. It has every product side by side, so you can see where each one fits. It even has the the model lineup with which model should I use breakdown, and three [music] real-world workflows showing you how to chain these tools together. This guide will show you exactly how the skills like the ones we're talking about in this video can fit into a daily workflow in a way that actually multiplies their

6:01capabilities. My favorite one is a workflow that takes a single video and turns it into a full week of content across platforms step-by-step with which Claude product to use at which stage. If you're someone who makes content that one workflow alone is worth the download. It takes one read and it will show you capabilities you did not know you had. [music] Check it out in the description. And thanks to HubSpot for sponsoring today's

6:26video. Right, back to the skills. Because number six is about fixing the deep Claude is genuinely the worst app. No AI slop. Built by Peter Yang, it kills 22 patterns of AI writing that have infected basically everything on the internet right now. You probably already know these. A lot of us have developed a physical reaction to them. It's not X, it's Y, the future isn't coming, it's already here, what nobody tells you is, and don't even get me started on the M dashes. Every single platform, LinkedIn, [music] Twitter, Substack, YouTube comments, they are everywhere. And here is the trap. When you use AI to fix AI writing,

7:08it polishes out the exact stuff that made it sound human. Your weird sentence lengths, your bad analogies, the joke that only lands if people know you. Those were the good bits. Most writing skills [music] sand them off and hand you back a nicer flavor of the same problem. This skill's actual trick is it removes the patterns without flattening your voice. And then, this is the part I genuinely love. It lists everything it changed so you can actually argue with it. All right, so as you can see I've made Claude write a short sales script about my app Ace and it is full of AI terminology. Here's the

7:46part that matters. It's not X, it's Y. Wow. So, we're going to go ahead and run the no AI slop skill. Let's see how it does. And boom, as you can see, we now have a script and Ace is a one-time payment. $150 for lifetime [music] access including every future update Ace ships, no recurring fee ever. That's a huge difference from here's the part that matters. Ace isn't a subscription, it's a one payment. Like, that's a way better improvement. And here you can see what actually changes. So, it's really easy

8:24to understand. Rewrote the offer line. And then if you want, you can argue in and be like, "Hey, I actually didn't want you to rewrite the offer line." That's really cool. That is the writing slop dealt with. Number five deals with the code slop problem. Coming in at number five, of course, I'm talking about Ponytail. And Ponytail makes your agents think like the laziest senior developer in the

8:48room. [music] He says nothing, he writes one line, and it works. You know the guy. Every team has one. You spend two days building an app, you show him, and he looks at it for eight seconds [music] and goes, "Why didn't you just do this?" This skill is the embodiment of that ponytailed individual. A perfect anti-slop skill for code volume. Because here's the thing a lot of people don't realize about AI coding. The problem is not that Ord writes bad code. It actually writes pretty good code if you know what you're doing. It just writes far too much of it. Ponytail claims to reduce the amount

9:23of code Ord writes by up to 94%. But from my own tests, it's closer to around 50%. And there's some pretty neat side effects, too, like tasks being about 20% cheaper and 27% faster. Everything is verifiable on the repo, but I recommend you try it for yourself. Ponytail is one idea executed perfectly. Write less code. Number four is the entire operating system, and I'm about to say something that might ruffle a few feathers. Remember superpowers? Everyone lost their minds over it. Every thread, every video, every this changes everything post, and honestly, it deserved it at the time. It was good, but this replaces it. I'm talking about

10:05Matt Pocock skills, and I'm not going to lie, it is the best base layer I have ever used. Because this is not a clever one-trick skill like caveman or ponytail, it is the foundation you put underneath everything else. Here is how I actually use it. And if you steal one thing from this video, steal this. I give my agent a link to the repo, kick off a long-running task, and tell it to

10:30use the skills where they make sense. That is the whole instruction. I do not micromanage which skill fires where, because the descriptions inside the skills are actually good enough. It just picks correctly. For example, inside Matt Pocock skills, there is a code review skill. I have Claude Fable orchestrate Sonic models to do the heavy execution work. It then uses the code review skill to make Sonic review its own output before it ever comes back to Fable, the orchestrator agent. The slot

10:59actually gets caught inside that loop. The same model that wrote it is now the same model that judges it. It never hits my eyeballs. I just get a finished product that's ready to test. All right, foundation, reviewer, security, editor, all the boring stuff is sorted, which means we can finally get to the fun stuff. All right, what if I told you every single piece of motion graphics in this video that you're watching was made using the skill hyperframes. And I'm going to say this straight up, but I think it's actually better than Remotion. Remotion's great, but I'm not trying to start a fight. HyperFrames just produces better outputs more of the

11:35time with less nag. So, if you make content, you already know the problem. Motion graphics are the single worst effort [music] to payoff ratio in the entire pipeline. A 4-second animation that makes one point clearly can eat an hour of your life in After Effects. Then you watch it back and go, "Actually, the easing is wrong." So, here's what I'm going to do. I'm going to describe an animation out loud right now, and we're going to see what comes back. And I'm going to link the HyperFrames skill and just say, "Create an animation of a really big crazy firework explosion in the night

12:14sky." And I'm just going to let this run. And let's see what it generates. And we're done. That took roughly 8 minutes. Let's have a look at the video. Look at Damn. That looks nice. Wow, I love how it explodes and shakes the sky. Well, there you go. In 8 minutes, we were able to create this sick ass motion graphic. Imagine trying to do that in After Effects. That would literally take you an entire day to get all the particles to look like that. HyperFrames makes cool animations, but coming in at number two, it turns Claude into an award-winning designer. All right, this one's actually cheating slightly, but

13:00coming in at number two, it's actually two skills. No. No. No, you can't do that. No. Hey, it's my video. I make the rules around here. But, I'm not going to lie, there are a lot of design skills out there. Genuinely, dozens at this point. And I'm going to say something that sounds harsh, but I mean [music] it. Most of them are like the same six prompts about white space wearing different hats. These two are the ones that survived on my machine. [music] And the reason they both survived is they are good at completely opposite things. Taste is the one shot king. If it's a blank page, no existing design

13:37language, you need something that looks intentional [music] on the first try. Taste just hands it to you. It is the I need a landing page in 20 minutes and I need it ASAP kind of skill. Impeccable is [music] the opposite. It's the analyst. It's not trying to be clever, it is trying to be right. Point out real app with 15 screens and it goes through them properly one by one. Maybe you've got inconsistent spacing, [music] you've got four different grays that should be one gray, that button that's

14:05like two pixels off on one screen only. Things you have absolutely looked directly [music] at and not seen. And the combination of these two is where it gets stupid. Taste for the first pass you have something with a point of view, Impeccable to grade it and grind out every inconsistency. One gives you the

14:23idea, the other gives you discipline. I've shipped things with this combination that people assumed I paid a designer for. Actually, no. Before number one, here are four skills that did not make the list but absolutely could have because I've seen comments about every single one of these and I would rather address them now than read about it in the comments for the next six months straight. First, Unlazy. This one genuinely hurt to cut out. It is an anti-laziness skill for agents built around something called the depth tree method. [music] Here's what it does. It splits a task into layers and gives every single leaf

14:59the full time budget of the whole task. So effort actually multiplies with depth instead of getting thinner. It's built on actual research into model laziness and premature completion. [music] That thing Coda's where it writes about 80% of the code and then types the rest follows the same pattern. I hate that. Unlazy fixes it. So if you do long energetic runs, this is on facing. Go

15:23get it. Next, you've got AI job search. Exactly [clears throat] what it sounds like. If you are job hunting right now, this is probably the most immediately valuable thing in this entire video, and it did not even make the list. Next, you've got agent reach. Give your agents access to gated parts of the internet.

15:40Use it responsibly though, please. With great power comes great responsibility. Fourth, you've got open design, and this one fixes a genuinely annoying big limitation. Claude design is one of my favorite creations from the Anthropic team, but you cannot extend it with skills. Open design lets you It's basically an open-sourced free Claude design alternative that lets you use skills like impeccable in taste to improve on your UI screens. And I want to reframe something real quick, because number one is not the flashiest skill on this list. Hyperframes makes pretty

16:14things. Play It To has better numbers. Number one is here for a different reason. It is probably the most versatile, most underrated, and biggest upgrade to your agent skill artillery today. Now, this skill was originally built to train AI models. The mechanism is brutally simple. Run hundreds of tiny experiments, keep what works, and then throw away what doesn't. Repeat, and that's it. That is the whole thing. Now, read that again, and tell me what part of it is actually about machine learning. Nothing. Nothing about that is specific to models. It is just the scientific method with the patient's problem removed, because the reason you and I do not run 100 experiments on

17:00anything in our lives is not that we do not believe in the method, it's that 100 experiments is 100 experiments. So, run 100 experiments to optimize your budget. Run 100 experiments on your calorie intake. [music] Run 100 experiments on your apps, UI. Run hundreds of experiments on your thumbnails. You are not limited by the skill, you are limited [music] by what we thought to point it at. All right, now a lot of people don't know this, but when I first built Ace, I actually ran the Auto Researcher skill on my app and it was able to create a lot of tiny little delight moments within my app. Like if

17:40we just click on any of these and we look at the whiteboard, even the loading screen, you can see like just being able to connect the models and stuff like that, it created a lot of tiny delight moments. Like literally hundreds of them and they stacked up on top of each other to the point where like I don't even know what is and what isn't done by the Auto Researcher skill

18:04anymore. Things like the line glowing when it's connected, the ability to change the things, the pill of the model picker here. Like how that menu looks. A lot of this was designed and implemented by the Auto Researcher skill. But we're not going to be doing that today. For today's example, I've actually got my gym workout and I've pasted it in. It's a 5-day upper lower split. All I'm going to say is use the Auto Researcher skill methodology because we're not using the skill because it's used to train AI agents, we're using the methodology of the skill to run 100 tiny experiments to improve my gym routine. I want to gain

18:46hypertrophy around the arms, look bulkier and toned. I'm 167 176 cm tall and I weigh 80 kg. I'm a 25 male. Now, I'm going to go ahead and send that prompt. And I'm doing this just to prove that you [music] can literally run this skill on anything and it will find the most optimal best solution. Just like when I ran it on my app and I focused it on finding, you know, animations and tiny little delight moments that would make a user want to stay on the app and have a more enjoyable experience. It's the exact same thing I'm doing with my workout routine. And I'm using Opus 5 on

19:26medium effort cuz you need to also consider that running 100 experiments isn't not cheap. So, I'm going to let this run and let's see how it does. Okay, so as you can see, it went ahead and ran 100 experiments. Five base diagnosis, five things wrong in it wrong in effect order. Direct arm volume is seven sets a week each.

19:49Priority range is 12 to 20. Five of seven triceps sets are push downs. No stretch position biceps work at all. So, yeah, pretty interesting. Let's have a look. And boom. If you compare it to the previous plan, you can see day one we've got barbell bench press, three sets, six to eight reps, lat pull down, incline bench,

20:16seated cable row. This all seems to look the same, okay? Except we they changed it to an overhead cable easy tricep extension. And then it also did incline dumbbell curls, okay? So, it's changed that slightly. Day two we've got lower, which is unchanged. And then day three, it's actually doing arm priority. So, it's changed this completely to a weighted dips bench, weighted chin ups, overhead press, chest supported. So, very arm heavy movements here. Lower is the same. Then upper, it's actually added a bit more of what we missed in

20:55day three. Super cool. And there you go. Everything else on this list makes you faster at something you were already doing. This one actually changes the size of the problem you're willing to attack and it costs nothing. It is just a text file. The habit, the secrets to all my favorite skills. I've left a link to all of them in the description. Leave

21:15a like on your way up.