WEBVTT 00:00:00.080 --> 00:00:04.400 So most people use Clawd in the most basic way that you can imagine. 00:00:04.400 --> 00:00:08.400 They open up a chat, they type in a prompt, they get an answer, 00:00:08.560 --> 00:00:21.595 and then what do they do? They repeat it. And that's basically it. They never actually go deeper, but Claude is actually capable of so much more than that, and most people have no idea. 00:00:21.755 --> 00:00:33.560 With Claude skills, you can catch bugs before you even see them. You can keep your sessions clean for hours and you can make Claude behave exactly the way that you needed to for a specific situation. 00:00:33.720 --> 00:00:42.335 And the best part is it gets smarter every time you use it. There are now thousands of Claude skills and I have tested more than 250 00:00:42.335 --> 00:00:46.895 of them. Most are broken, outdated, or just system plumps 00:00:46.895 --> 00:01:08.950 with a fancy name. But buried inside that mess are nine skills that represent a completely different way of using Claude. So I'm splitting them into three categories for today's video. Essential Claude skills that you can use right now, Claude code skills for building, and also one co work pattern that ties everything 00:01:08.950 --> 00:01:33.390 together. This is gonna be a fun one. Don't forget to check out the three score community down in the description below. But right now, let's get into it. So we are starting off with category number one and that is the essential Claude skills. So these work in Claude desktop. There's no terminal, no code needed. Just upload a zip file through customize and you are set. So let's get into skill number one and that is skill creator. 00:01:33.870 --> 00:01:43.355 This is our first skill and it's basically something that sounds pretty funny, but it actually solves most of your problems. This is one that is built for beginners. But ironically, 00:01:43.435 --> 00:01:47.595 it's one of the most overlooked skills that you will find anywhere. 00:01:47.675 --> 00:02:04.100 Not because it's hard to find, I mean, it's actually pre installed, but most people just never think to actually use it first. So you don't need to download anything, just open up Claude desktop and then go to any tab in Claude and then just type in this prompt. I want to create a skill using slash 00:02:04.180 --> 00:02:05.540 skill dash creator. 00:02:05.925 --> 00:02:21.040 Just type that in. And here's the problem that most people actually run into. They have a workflow that they just repeat about three, four, five times a week. I mean, it's the same instructions, the same format, the same corrections, and every time they start a new chat, 00:02:21.200 --> 00:02:45.845 they explain it all over again from scratch. Skill Creator actually lets you turn that into a reusable skill in just a few minutes. You describe what you want the skill to do, and then Claude actually interviews you with a few questions just to basically, like, nail down all of the details, and then it builds the full skill dot m d file for you, and there's no markdown editing. It's just a pure conversation. 00:02:46.450 --> 00:03:11.195 But here's the part that nobody actually shows. After it builds the skill, it automatically generates test cases with the skill active and also without the skill. So you can actually see the output side by side. So if the skill doesn't actually improve the result, then you know before you ever even commit to using it. That step is the difference between a skill that works and a skill that you think works. 00:03:11.355 --> 00:03:17.770 I mean, most people skip it, so I'm telling you don't. Now we get on to the second skill and that is prompt master. 00:03:17.770 --> 00:03:27.290 So this one is on GitHub. All you have to do is basically just go and search for prompt master by n dash I dash d dash h dash I dash n 00:03:27.615 --> 00:03:29.855 dash j dash s. 00:03:30.015 --> 00:03:50.560 And then what you do is you download the repo as a zip file, and then you go over to Claude, you open up the sidebar, and then you click customize and then skills, and then upload a skill, and you are done. So here's the problem. Now most people plant Claude with messy brain dumps. It's always long. It's unstructured, 00:03:50.560 --> 00:03:53.200 and it's basically just full of vague instructions. 00:03:53.280 --> 00:03:55.920 And for simple tasks, that is fine, 00:03:56.080 --> 00:03:57.680 but for anything that's complex, 00:03:58.035 --> 00:04:02.755 the the output quality drops pretty fast and it's noticeable. 00:04:02.835 --> 00:04:04.355 So prompt master 00:04:04.355 --> 00:04:20.190 actually takes whatever you throw at it and it turns it into a structured optimized prompt according to the best practices. It detects which AI tool the prompt is for, it extracts your intent across nine dimensions, and it asks a maximum of three clarifying questions 00:04:20.270 --> 00:04:28.430 if something critical is missing from all of this, and it delivers one clean prompt that you can simply just copy and you can use. 00:04:29.175 --> 00:04:33.095 It works with over 30 tools Claude, ChatGPT, 00:04:33.095 --> 00:04:40.455 Cursor, Midjourney, Stable Diffusion, you name it, all of it is there. But the real power is using it inside Claude itself. 00:04:40.855 --> 00:04:50.900 You write your messy brain dump, you add, use the prompt master skill on this one and then Claude actually rewrites it before processing. One extra step but 00:04:51.060 --> 00:04:52.100 dramatically 00:04:52.100 --> 00:05:08.775 better outputs. Now here's a quick pro tip, you can actually add this to your general instructions inside Claude desktop settings so it auto enhances on every complex prompt. You never have to think about it ever again. Now that takes us perfectly into skill number three and that is the fact checker. 00:05:08.855 --> 00:05:31.235 So multiple versions of this exist. The easiest one is to grab from Daymaid's Claw Code Skills repo on GitHub and all you do is just download, zip, upload through, customize, and then it's basically the same process that we discussed before. The AI generates confident sounding text. So sometimes it is wrong and if you're putting a name on it like a LinkedIn post, a script, or a client deliverable, 00:05:31.395 --> 00:05:51.380 then wrong is basically a huge problem. So this skill runs a systematic fact verification pass on every or any text that you give it. So it reads every factual claim and it cross references against external sources using web search and it gives you a report like what's confirmed, what's unverifiable, 00:05:51.380 --> 00:05:52.180 and what 00:05:52.655 --> 00:05:54.815 what's flat out false. 00:05:54.895 --> 00:06:14.740 So I use some three things, anything AI generated that goes out publicly, so my own video outlines before I film and other people's content when I want to check if what they are claiming holds up. Now here's another pro tip for you, Once you have it installed, just add a step to your writing skills that runs the fact checker automatically before giving you the final output. 00:06:15.140 --> 00:06:28.365 You stop the problem before it even reaches you. Now we go on to skill number four and that is the humanizer. Grab this from Blader's humanizer repo on GitHub, download it as a zip and upload through customize and takes about thirty seconds, 00:06:28.685 --> 00:06:31.805 and this one is pretty straightforward. 00:06:32.045 --> 00:06:33.325 It removes 00:06:33.325 --> 00:06:52.375 the signs of AI generated writing from any text that you give it, and you should be running this on anything AI generated that other people are going to read over. It's based on the Wikipedia's comprehensive signs of AI writing guide and it detects 25 specific patterns, inflated symbolism, 00:06:52.535 --> 00:06:53.575 promotional 00:06:53.575 --> 00:06:54.375 language, 00:06:54.775 --> 00:06:56.535 m dash overuse, 00:06:56.535 --> 00:07:02.695 and I know you know what I'm talking about, and also the rule of three AI vocabulary words like leverage 00:07:02.695 --> 00:07:04.390 and streamline, 00:07:04.550 --> 00:07:06.150 all those vague attributions 00:07:06.150 --> 00:07:07.670 and the filler phrases, 00:07:07.910 --> 00:07:12.550 all of those things that make the AI text feel like an AI text. 00:07:13.110 --> 00:07:18.070 But here's what makes this one better than just telling Claude to make it sound more human. 00:07:18.735 --> 00:07:20.575 If you give it a sample 00:07:20.655 --> 00:07:26.495 of your own writing, then it actually analyzes your sentence rhythm, your word choices, your quirks, 00:07:26.575 --> 00:07:36.350 and then applies those to the rewrite instead of producing generic clean output. I run this on LinkedIn posts, client emails, onboarding docs, community guides, 00:07:36.670 --> 00:07:43.390 anything that goes out with my name on it. And if you use writing skills like LinkedIn writer 00:07:43.470 --> 00:07:44.990 or a newsletter skill, 00:07:45.405 --> 00:07:53.325 add a humanizer as a final step so that it runs automatically before you see the output. That's only gonna give you the best results. 00:07:53.645 --> 00:08:01.110 Now we are moving on to category number two and that is the Claude code skills. So those four work in any Claude chat. 00:08:01.510 --> 00:08:12.870 But if you use Claude code, then the next four skills operate at a completely different level. For skill number five, I have a powerful combo of playwright and superpowers. 00:08:13.275 --> 00:08:21.275 This combines two skills. Playwright is an official Anthropic skill, so you can find it in the Anthropic skills repo on GitHub, 00:08:21.435 --> 00:08:24.155 and Superpowers is from Obera's 00:08:24.155 --> 00:08:31.700 GitHub repo. So you can install both through the plug in marketplace in the code tab, and you'll need Playwright installed 00:08:31.700 --> 00:08:34.020 on your machine. Super important. 00:08:34.260 --> 00:08:36.580 Everyone shows Claude writing code, 00:08:37.060 --> 00:08:47.715 but nobody actually shows Claude testing the code that it actually just allowed. Claude bolds you a web app, and it looks right, but did it test the sign up flow? 00:08:48.035 --> 00:08:52.500 Does the button work on mobile? You don't know. By default, 00:08:52.660 --> 00:08:54.980 you are the q and a department. 00:08:55.140 --> 00:09:08.505 Playwright handles the testing side. Once active, Claude navigates your local app like a real user. It clicks through flows, it fills out forms, it captures screenshots at every step, and it reports back exactly what broke. 00:09:08.665 --> 00:09:13.785 But superpowers takes it even further. It forces Claude to plan before it codes, 00:09:14.025 --> 00:09:22.990 write tests before it ships, and it even reviews its own work before you ever see it. So instead of Claude building something 00:09:23.710 --> 00:09:25.790 and testing it after, 00:09:26.030 --> 00:09:53.400 it's building with quality gates baked into every step. Now the moment that actually sold me on this was that Claude built a simple app. It planned the architecture first, it wrote tests alongside the code, and then it then played right to verify everything end to end. And it found a button that was technically there but visually hidden on screens under 400 pixels wide. That's the kind of bug that reaches your users if nobody 00:09:53.400 --> 00:09:54.600 catches it first. 00:09:54.920 --> 00:09:58.840 Now we have to go to skill number six and that is Septum 00:09:58.840 --> 00:10:00.040 Agents Pack. 00:10:00.440 --> 00:10:09.575 So this is going to take you to the next level. Most people using Claude Co do everything with one agent in one context window. By default, 00:10:09.735 --> 00:10:11.975 you are the QA department. 00:10:11.975 --> 00:10:16.615 That's like hiding one person to be your architect, your lawyer, your CFO, your marketer, 00:10:16.930 --> 00:10:18.690 and your QA tester 00:10:18.930 --> 00:10:20.210 all at once. 00:10:20.850 --> 00:10:28.610 This skill drops a full name team in your project in just a single move. 10 specialized sub agents 00:10:28.945 --> 00:10:34.225 each with a name and a role. Atlas handles the planning, Luca handles the architecture, 00:10:34.225 --> 00:10:51.020 Canon handles the brand, Amber handles the marketing, and Telly handles the finance, Nova handles the design, Ward handles the legal side, and Meta handles the customer experience. And then on top of that Juno handles the research, PIP handles the coordination, 00:10:51.180 --> 00:10:53.500 so you genuinely have an entire team. 00:10:53.660 --> 00:10:56.140 In practice, you are building a new feature. 00:10:56.835 --> 00:11:09.235 You ask Claude to use Atlas to plan it out and then Ward to check for the legal issues and then Tally to estimate the costs. That's three perspectives. That's three areas of expertise 00:11:09.620 --> 00:11:11.620 in just one project. 00:11:11.620 --> 00:11:21.140 You never have to re explain context before each agent reads from the same project files. Now the original Septum Agents pack costs about $49, 00:11:21.140 --> 00:11:34.955 but I built my own free version that does the exact same thing, and you can actually grab it in the free school community. The link is down in the description below. Now for skill number seven, and that is the view, and this has to be one of the most underrated skills. 00:11:35.035 --> 00:11:47.280 Claude writes code, but it doesn't really view its own work unless you tell it to. You type in slash review after any bold and then Clawd actually checks for bugs, edges, cases, 00:11:47.680 --> 00:11:52.880 security issues, and design problems all for you. The stuff a careful 00:11:52.880 --> 00:12:08.845 human reviewer would catch and you can actually use it as your last step before merging anything. So it runs locally, it costs nothing extra, and it catches things that Claude missed the first time around. But did you know that you can actually do a security review directly 00:12:08.845 --> 00:12:16.040 in code? All you have to do is just type in slash security dash review and you can see a review of the pending changes 00:12:16.120 --> 00:12:21.720 on your current branch. Now let's discuss skill number eight and that is context and compact. 00:12:21.800 --> 00:12:35.855 Now every tool under Claude dumps raw data into your context window. So after about thirty minutes of real work, half your window is noise and when it fills up, then Claude auto compacts and it forgets what it was doing. 00:12:36.095 --> 00:12:54.075 So slash context shows you what's eating your window up right now and slash compact lets you compress it on your own terms instead of letting Claude decide randomly. So the habit that you're going for here is you wanna run context every twenty minutes and then when you hit 60, 00:12:54.075 --> 00:12:58.315 you run compact with a focus like compact focus on auth module 00:12:58.315 --> 00:13:18.250 and then your sessions run longer and then Claude stops forgetting and you stop wasting prompts at explaining things that you really don't need to. So that was category number two and that was basically just the code skills. Now we are getting into category number three, and that is the co work pattern. Okay. And let's start off with skill number nine, and that is self improving skills. 00:13:18.890 --> 00:13:22.330 So we are wrapping up our list, and we have 00:13:22.895 --> 00:13:25.935 our final learning dot m d pattern. 00:13:26.095 --> 00:13:34.735 So this is the one that I tell you to implement today because it's so important and that's basically if you only if you only had to take away one thing from this video. 00:13:35.600 --> 00:14:18.330 Now there's no install needed. This is just a pattern that you apply to any skill that you already have and you just create a file called learnings dot m d alongside your existing skill file and then you add in one line to your skill that says before running the learnings dot m d. And here's why. You build a skill and it works okay, but it makes the same mistakes every time. You correct it and then the next run and it's just the same mistakes. The learnings dot MD pattern fixes this for you. So after every run, Claude logs what worked, what didn't, and what you corrected. They did specific scope to that skill. So the next time the skill runs, it divides those notes first and the skill actually compounds. 00:14:18.635 --> 00:14:27.355 So I run a writing skill on day one, and then the output is decent but generic. You corrected and then the intro was too long, the headlines 00:14:27.755 --> 00:14:29.195 needs a number, 00:14:29.435 --> 00:14:31.275 the client hates passive voice, 00:14:31.790 --> 00:14:35.470 those corrections go into learnings.md. 00:14:35.790 --> 00:14:37.310 And by then five, 00:14:37.630 --> 00:14:39.710 the skill has internalized 00:14:39.710 --> 00:14:45.645 all of that. The learnings file from one of my content skills says something like headlines 00:14:45.645 --> 00:14:46.765 with numbers 00:14:46.765 --> 00:14:48.445 consistently outperformed, 00:14:48.605 --> 00:14:55.325 intro paragraphs over 80 words flagged as too long by client, avoid the word leverage. 00:14:55.405 --> 00:14:58.445 Client has specifically rejected this three times. 00:14:59.060 --> 00:15:00.420 And that's not a prompt. 00:15:00.740 --> 00:15:02.420 That's institutional 00:15:02.420 --> 00:15:03.300 memory. 00:15:03.780 --> 00:15:11.380 That single change turns any static skill into a system that learns your preferences 00:15:11.155 --> 00:15:12.355 over time. 00:15:12.755 --> 00:15:16.675 And here's the thing that nobody says out loud about Claude skills. 00:15:16.915 --> 00:15:21.475 Installing a skill does not make you better at using Claude. 00:15:21.555 --> 00:15:27.280 A skill is just a tool. A tool that you never improve is just clutter. 00:15:27.440 --> 00:15:34.800 The one pattern that separates every skill on this list from everything else that you've installed is the learnings file. 00:15:35.280 --> 00:15:38.240 Not because it's the most impressive skill, 00:15:38.735 --> 00:15:57.020 but because it's the only one that gets better the more you use it. Every correction that you make, every preference that you log, every mistake that Claude repeats and you catch, that all goes in and it compounds over time. Now that's the difference between a calculator 00:15:57.180 --> 00:15:59.420 and a full on computer. 00:15:59.735 --> 00:16:10.775 So that is all nine skills and every install link is all down in the description below in the free school community. Go and check it out and I will catch you on the next one.