back to you and then like help you with the next step. " Claude has really good documentation on hooks. Most people that have built hooks have done so with Claude. You can check their hook docs for specifics. Um the common use case, as I mentioned, is to play sound when the workflow finishes just so you can check...giving me all this information. First, it's going to do some research. Then it's going to actually write a script to run the claude code hook. All right. And it's now adding the hooks configuration with a little glass sound. I don't know if you guys heard that, but that's that. It just finished
Поиск по транскрипциям
pretty fine. It's like saving in a video game before you go fight a boss. Um and then you can actually run multiple tasks. Now Claude Code does multi- aent. So it'll actually spin up different agents for you. You have to go I'll make another video about this. You have to enable it in the settings
join you to build something? What are you talking about? Codeex is good enough. Codeex 5. 3 is amazing. Codeex 5. 3 is just as good as Claude code. And I'm not just saying that because it's cool to be hating on anthropic right now. I actually mean that. Codeex sucks to talk to. It's paranoid
complete and add it to a change log. Now, at first we do this man, just manually prompting, but then I show you how to create a custom claw code command or now called a skill with custom arguments to really streamline this process. So the point is not just to copy and have the same exact project that...follow along and build your own version of Dev Stash, but it's meant to be much bigger than that. Now my main tool in the course is claude code but I do make it clear that everything I'm going to show you can be done in cursor or you know wind surf or gemini just any agentic
have the Skill Creator plugin installed. So searching it over here, and then we can install it on this project level in our case. And then after restarting Claude Code, if I do /Skill Creator, I can see that I actually have two. And one of these is an older one that I installed a couple months ago. And that
From there, what we also want to do is make sure that we have persistent memory set up. This allows clawed code to remember every session before, right? And the reason for that is like if you set up a project and then you want to run a new one, well, it's going to be super annoying...which takes up more tokens, consumes your time, and makes you less productive. Now, if you want to install this, literally all you do is you just go into claude code terminal and you just say install this, right? I've got a full guide inside the air profit boardroom and from here you can install it. I've already
video to website skill. So, both of these skills are literally just markdown files. They're markdown files that I've worked on that tell Claude Code the best practices for creating these animated 3D websites. And you can get these skills for completely free by going to my free school community. The link for that is down...myclaude. Within that claude, I've got a skills folder. And then within that skills folder, here are my two skills I need you to use. And it should look something like this on the lefth hand side. Now, before you get too overwhelmed, if you've never used Cloud Code before, it's super simple. Right here, we have
going to write the code to clone in and actually move these items into the rec directory. And that means I should have them here locally. If I open up a new terminal here and I type ls ls-la, you can see I haveclaude. If we do a tree. claude l2, we can see that we have skills...important. Let this be your reminder if you don't have these agentics at the ready to help you build faster and faster. Definitely build this out. I know Claude Code has some, you know, build me a skill type of prompt. I highly recommend you build out your own so that you really understand how to do this better
network port over here. So that is HTTP proxy port. And then you want to make a proxy that looks kind of like this so you can get Claude Code to write you one. And you want to make sure that api. anthropic. com is allowed because that allows for the remote connection. Because
created a new folder called Excal diagram and then I just dumped in everything from the repo including the skill. md. This is the primary instruction set that guides claude code how to argue visually creating the JSON files for these Excal diagrams. And I know this is super meta, but I use the Excal diagram skill to create this
generated image gets generated with every meal that's shown. So there's a visual with every meal. I'm going to hit enter on that. And now Claude Code is going to go and start building out that new feature. Now what do you think we do from here? It builds out the new feature. We record ourselves using
also overridden some of these environment variables over here. So we can say, hi, who are you? And you can see that it says that's Claude Code, because that's baked into the system prompt. But anyways, we can give the instructions and the plan that we have from earlier, and then see how it performs in executing
brand new conversation, switch to plan mode by doing shift tab, and then describe what I want using Hyper Whisper, my voice to text tool, and then let Claude code explore the codebase. Often, it will ask me some clarifying questions as well, and then I review the plan. And if it was a really small feature, then I just
basically do is when I'm working on a brand new feature, so for example, I have a tasks folder in this project. The very initial plan that Claude Code comes up with is often kind of short. So it's like 150 lines, 200 lines and it may not cover all the edge cases that I actually care about
make professionallooking user interfaces. So, go down below, go to this tweet, pause now, grab these two commands, and then you're going to go into Claude Code, paste them right in here, hit enter on the first one, second one, and you'll have the design skill installed. Now, what you can do is you can say, "Redesign
instead of opening in the middle, it opens on the right hand side, and that's okay. Reason why is because I just haven't opened up my little claude code or terminal or aentic workflow instance. So sort of rearranges to look more similar to what you guys are used to. Now, typically what you actually have...have been known to cut corners wherever humanly possible for tokens saving reasons or for a variety of others. But the reality is we shouldn't just trust the code that comes out the very first time. What we need to do is we need to stress test it. And so you can think of the stress testing as basically
Claude code to include a Y whenever spins up a sub aent and I found that led to better results especially when you have multiple sub aents running in parallel in different parts of the codebase. So without a Y if you were adding a off related feature then cloud code would often just search how off works with
really like, which is this design systems. And what we're going to do is choose a design for our app and basically export it from V 0 to claude code really, really easily. So, I like this soft pop here. This soft pop looks nice. Let's open this up in the editor. I like the way these colors
Some other cool things here, we have memories. So we can actually upload our own context to the browser. So for instance, I am finishing up a claude code master class right now. I put the entire outline for the master class into this memory. Now as I'm working on this course, I can say hey find new modules
nuance here. Um, I'm not actually going to do this in the same thread that I launched and built the entire website. So, I'm going to use Claude Code for this instead of Gemini. And the reason why I'm doing it is cuz I don't want any context. I basically want the model to look...cloud code is going to go pass one discovery map the full architecture and then more or less tell me, you know, what's good, what's bad. And I'm doing this for a couple of reasons. Um, obviously I want no context as mentioned, but I also think that Claude is a lot more interpretable than Gemini right