Matt Pocock Built the Skills Repo Every AI Coder Is Using

0:00This one skill pack will make your coding agent so much smarter and get all your output to be much better. That's why it's one of the all-time most popular projects on GitHub with over 200,000 stars. Serious developers swear by it, but so do new builders like me. You're about to meet the creator, Matt Pocock, and he's going to teach us how to get the most out of it. Let's get into it. Presented by Zapier, the AI automation company. All right, Matt, what are we looking at here? What is

0:24this? So, I have just done something interesting with this application, which I have This is the application that I use in my work repo. And before it was an entirely local application, but I have bumped it up so that part of it is sitting in the cloud. And what I've not done is I've not done a security review on it. So, what I'm keen to do is I'm just going to prompt Claude Code. This is Opus 5, medium effort, Claude Max subscription. And I'm just going to say, "I just deployed a large

0:55application, blah blah blah blah blah." And it's going to do its security review, right? Now, this is okay, but what I really prefer doing, and what I think you're going to get better results from, is aligning on what you actually want to get from the AI before you commit to something. If you think about the process here, it's kind of like we are doing something with the agent, usually implementing some code or conducting a review or something like that. And then we're going to review it at the end or review it at some point. And so, there's

1:25a kind of plan, implement, review setup. Now, most people don't spend enough time on the pre-alignment phase, right? On the aligning before you do the thing. And so, what I much prefer to do is if I open up a new tab here, I'll run Claude again, and this time I'm just going to prepend it with Grill Me here, which is kind of my most popular skill. It's the

1:48skill that does this alignment for you. And what it's doing is it's going to invoke the grilling skill, and then we're going to actually chat about the things that it's going to do, the things that it's going to focus on and find before it goes and does the review. So, I'm keen to kind of sort of see the two different approaches here. This I mean, these are non-deterministic, right? Like so, who knows what's going to happen,

2:08but that's the main idea. Now, I have a hard time using a skill like this before I get started because I almost need to see not almost, I need to see a version of the finished product, to touch it, to feel it, to then have some opinions about where I want it to go. When it's just an idea, it's too hard for me to think it through. And so, both the eagerness of just getting started keeps me from going through a set of questions and planning with Claude, and the need to feel it keeps me from doing it. What do you say about

2:38that? So, what you're describing there is the fidelity of the thing that you're talking about, right? And when you're working on anything, this is like this is an old idea. This is from Shape Up. This is Ryan Singer's great book about designing, planning stuff. And what he talks about in Shape Up is that people often feel like they're operating on or they want to operate at a higher fidelity than they need to. So, actually when you're first starting out, it's often really good to operate at a really

3:06low fidelity. In other words, just text. And then maybe from text you can work up to, let's say, diagrams or breadboarding or various techniques. And from there maybe then you can go to prototypes. But what everyone seems to be doing or the default mode regions is to just go to a massively high fidelity immediately and just say, "Okay, I'm going to produce the entire feature for you, and then we'll review the whole thing." But then, because you've produced the whole thing, review becomes really expensive, right? Because you're having to review the whole thing. Maybe there are bugs you didn't expect. Maybe it's just not done the thing that you

3:39wanted it to do before. Whereas if you were to spend 5 minutes just aligning low fidelity first, and then you actually understand what you're building together, then you can ship something really, really really You know, it's still the cost isn't really an issue for me because, you know, you have the subscription. It's I have the $200 a month plan, not that big a deal. Where it does end up biting me is there is something that I hadn't thought of that is a problem. Like I have a tool that will analyze YouTube videos related to AI and then tell me who's got more more than their average views. And then I

4:14realize a month later, oh, I didn't think through that it has to daily keep track of what their regular view counts is to know when something is an outlier. And if I would have spent some time thinking about it, I would have caught that. But boy, I just rushed to build so fast. Exactly. And that means that something very simple, something very quick, a little quick check at the start would have been able to catch that, right? And I don't always think that you need to operate at low fidelity. Sometimes you need a prototype before you're building the thing. And what I'm often talking about here is building really complex

4:47apps, apps that are supposed to go into production. These are the apps that I spent my career building. And before you build anything real, you have to align. You have to figure out where you're going. Okay. Uh let me know when the questions come up. I want to see what Grill me looks like with this new form. Totally. So, let's see. So, on the first one here, it basically just went and this is the one where we ran it without Grill me. And so, it just produced a security audit, right? So, it's done a very general security audit and it's go okay, Vercel credentials in the public

5:19history, that's not good. Um I actually looked at this and it is actually fine, so we're okay. Uh drizzle it are on the deployed path, low practical risk, blah blah blah blah blah. Now, this is very general. It's okay. It's going to probably give me some decent advice. But what if we actually talked about it first, just did a very small amount of conversation? So, this is what Grill me looks like. So, you essentially just have a bunch of questions where this little um red check mark here, this is the question, who is the adversary? And then you have a little recommendation from Grill me on what it

5:54thinks you should choose. So, which of these do you actually want to defend against? Anonymous person on the internet who finds the resell URL, etc. What is the asset? Blah, blah, blah, blah, blah. What is in scope? What is the deliverable? So, it's just a little tiny set of questions, which I will then read through and dictate out my answer to. And so, it's asking these questions in sensible batches. It's going to ask rounds of these questions. So, when I submit an answer here, it's then going to find the next round of questions and ask them to me, too. So, Before you go into it, here's my

6:25challenge for how to respond to something like this. I don't I don't know. Do I say, "Well, for your first question." and then repeat the question and then give the answer? Or do I copy and paste the whole thing in and then write underneath it? Yeah. What I would say is, "For Q1, yeah, I accept your recommendation. For Q2, the worst thing that can occur is probably data loss and probably database abuse. I want to make sure I'm not getting DDoS'd. For Q3, I think apps remote is the only thing that's in

6:54scope." You get the idea. So, that's why they're labeled with the numbers. It's so you can just reply to the number very quickly. Okay. What's the difference while you send that out and we're going to get the next batch of questions? Do you want to uh Now, I guess you didn't want to an-

7:07answer any more of the questions. What's the difference between this and just saying, "Claude, ask me some questions before we get started. Force me to think about this well." I mean, it's a really small skill. That's the thing about Grill me is it's very, very small. It really is just a case of uh you know, you aren't like quiz me relentlessly about these things, use this certain format, ask them in rounds, and there's really not much to it. So,

7:31anyone could have written this skill. This is not a special sauce. Makes it very easy to audit, very easy to bring into your organization. It's a teeny, teeny little thing. And so, yeah, of course, you can just do your own thing, but I noticed that whenever I want to encode a process and do it again and again and again, I think that a skill is a really nice place for that. And Grill me, you know, you just modify yourself, you figure out exactly what you want to do

7:56with it, and then you're good to go. Okay. I do want to see what that skill looks like in a moment, but keep going with this. I'm curious what the what the result will be. So, let's see. So, it's asked a bunch more questions here. It's asking about rate limits, right? So, the whole first answer was just like, okay, here is your security audit, but now it's actually thinking a bit outside the box. It's extending the scope a little bit. I don't have any rate limiting today. So, I probably need

8:22to add maybe the Versel firewall rules. Our health is on authenticated, so I probably need to figure that out as well. Last use at right, so some various stuff here. So, this is really going into depth. It's sort of become like begun the security audit already, but now I am involved in it, and so it's kind of trying to align to where I need to go. I think what most people underestimate when they start new work is that they have an internal kind of hierarchy of values, right? A set of things that they want to be done. And a set of priorities that sort of they hold that the agent

9:00just doesn't understand. In other words, there's a communication gap between you and the agent. And that's always going to be there, right? Because we as the user, like the AI can't anticipate that hierarchy of values. So, it has to figure them out, and this I found is the best way. Would you Would you open up the skill and just show me how it works? And then what This is part of a collection of skills, and it has so many other things like how you you personally learn, how you get your agent to communicate with you more clearly. I think there's also how you write, which is in here. It's

9:37basically your your set of personal skills. I'd like to see what's in it. This is So, where is the skill itself? I see this is the exact file that I'm that I'm looking at on GitHub. It is just this, a relentless interview to sharpen a plan or design? Yeah. So, there's a there's a little more to it than this. This is the grill me skill. And one important idea about skills is that you can have skills that the model can invoke or that the user can invoke. And this one, this skill is actually invisible to the model by default. But, the skill grilling is really where the

10:10meat is. So, let me pull out grilling just here. And grilling is a little bit longer. It just says, "Interview the user relentlessly until you reach a shared understanding. Map this as a design tree. Every decision branches into the decisions that hang off it. You work the tree in rounds, and the frontier is every decision whose prerequisites are already settled." These, by the way, these bolded terms here are what I like to call leading words. They're words inside the skill that are designed to essentially trigger the agent's reasoning traces, and it's encouraging the agent to think in these terms, leading the agent to do its thing, sort

10:46of like Lightfoot. And so, essentially, that's that's the skill. It's just 22 lines long. It's grown a little bit since it it was fair bit smaller, actually. And it's just little things like finding facts is your job, never the user's. When a frontier question needs a fact from the environment, dispatch a sub agent to find it. Don't block the user. So, this is this is all the skill is, and it's just one utility just for

11:08creating this grilling style interview. And by the way, as someone who personally creates and lives off of skills all day long, anything that I do more than once, actually more than multiple times, I have a skill created for it. And I never did one of the things that you just showed, which is have a skill that

11:25basically just invokes another skill. Why would I do that? So, it's It's of constraint that I have, which is that I have two grilling skills. One of which is grill me, and one of which is in my engineering directory, and it's grill with docs, which essentially just has run a grilling session using the domain modeling skill. So, it's a little layer on top of grill me. So, it's just it's a

11:48little bit of code sharing, basically. There's nothing actually in the skill spec that describes how you should share code between skills, and so this is my kind of hacky attempt at it. Okay, I got it. Um I have my own little hacky attempt. I created an orchestrator, which then pulls the different skills that it needs in. Okay, I get it. You basically you're saying, "Look, I have one format for grilling, but there're two different ways to grill. One is ask questions, and the other is use these documents to get the information you need." Okay, so back to

12:15what we were doing before. Um do we have a response yet from the version that it's still asking more questions? Yeah, yeah, yeah. I haven't answered these questions yet, and I could do. We could just sort of keep running through, but I think we kind of know where it's going. We're going to end up with a document kind of like the first one, but just way more detailed, way more

12:34tailored to what we actually want. Okay. All right. So, the discipline here is first of all to just have this on my system by giving the GitHub link over to Claude or Codex and saying, "Now, I want you to to start using this." And then the discipline is before I start a session to say grill me about this thing I'm starting to launch. That's one

12:54thing. By the way, if you're listening to this and you're building software that you want to bake in something like HubSpot, Slack, Jira, Gmail, or over 9,000 other apps, if you use Zapier SDK, you can do it easily, and you can have the controls that you need over it. Go to zapier.com/sdk and check it out. Okay, um why don't we look at some of the other skills and

13:15just talk to me about why they're there. What's the What's the wait what? That's a new one that I saw you publish. So, if we look here, this is my um documentation site for the skills. Um we should be, there we go. Uh, I've 214,000 GitHub stars, ridiculous. Um, I want to talk first just about this main flow, basically, cuz you talked about like the discipline. And this main flow, like going from the grill with docs skill to the to spec skill to the to ticket skill to the implement skill to the code review skill, that's essentially a software development life cycle there, right? And when we're talking about

13:48skills, you can encode these processes that last more than one session. It's very, very cool. And so the all of these, these are all of the skills in the repo. Wait, can you go back for a moment just repeat what you just said? I want to understand, I'm not a developer, but I build tools now all the time for myself and my team. There is a what? A product life cycle that you said? And then you also said that they will start off on

14:11their own? Tell me tell me both those things. The way these work is that a lot of skills repos and skill setups, they try to give the model they try to make the model really powerful and try to make the harness really powerful. So, for instance, superpowers, which is a very, very, um, popular, um, set of skills. They're designed to give the model superpowers,

14:34not necessarily the user superpowers. And so, mine, they take a little bit more learning, a little bit more understanding, but once you've learned essentially these five skills, you can build, uh, anything of any size. Like it really is a very powerful setup. And you've got grill with docs, which is essentially grill me with a little bit of, um,

14:55little bit of an extra layer on top. What's that extra layer? What are the docs that I would use instead of the questions? Great question. So, it's it does it's essentially, um, the same thing as grilling. You have a, um, a grill me session where you're answering questions, but it does two things. It's first of all creates a glossary of the thing you're building, which sounds incredibly dull. Why why would you do that? But when you realize that, okay, the glossary, if I name everything consistently throughout the application and I name all of the folders like that, I name all of the concepts that I have and I I find the

15:30right language for what I'm building, the thing about agents is that they thrive off consistent language. And so, if you say, "Okay, change uh this uh let's say two sentences of long blah blah blah blah blah blah blah." The way that ghost lessons materialize into um ghost sections into blah blah blah blah blah. Very complicated. Whereas, if you just say, "Make a modification to the materialization cascade." Right? A term that you've agreed on with the agent, it knows exactly where to look because the functions are named properly, the folders are named properly, and everything is aligned. So, actually aligning with the agent, creating those

16:03glossaries is so important. I see. So, grill with docs, the difference is the output is the docs that that have the understanding that we've gotten from the grilling session, and then that helps make the rest of the process better, but I've also got a doc of how I work of what I I got it. Okay, so that's the first step. What's the

16:22next in in the rest of the process? So, the and there's a there's another thing in grill with docs, too, which is it creates architectural decision records, which help explain the non-obvious stuff about the code, which if you've done any coding that you'll you'll know how important those are. And so, it's essentially just layering on good software concepts onto the grill me

16:43skill. Once you've had that conversation, you can then you've then got a decision you need to make. You can either, if you think that you've got enough juice left in your session, if you've got enough context window left to work with, then you can just implement it, right? You just jump to the implement skill, which just does a very simple uh set up. It's just implement the code, create a commit, and then review it. So, do an automated

17:08review on it. Okay. Or, if it's like a massive feature that you're building, if you know, "Okay, there's no way I'm I'm to squeeze this into the good bit of my context window. Then you need to schedule that over multiple context windows. And for that, you need two things. You need a spec. And that specification is going to be essentially a huge document that

17:31describes what you're building. And that description of what you're building means that you can then review it afterwards. And it also means you can pass that into every session that comes afterwards to say this is what we're building. And then the tickets is we are building this slice of the spec. I see. So what that means is you essentially describe your destination. Okay, we're building this huge feature. And then ticket one fits [snorts] in one context window, you're going to build that bit. Ticket two fits in another context window, go back, build that bit. So that's the whole theory. And then you implement

18:06each ticket and you review at the end. Can I also use I've never I never even thought to use the ticket skills, but now I understand it. Can I also then use it to break up the project so that multiple agents or multiple tabs in my cloud code can do I can. That's what I do. So start by grilling, then create a spec. Now we know exactly what the finished product looks like. Break it up into parts, assign them to different agents or different like basically tabs within the window. I've got everything ready. Now Now the implementation puts it all together because it's all the features have been built and now we

18:38need to connect them all. Got it. You got it. And the cool thing about it is is like the cool thing is that you can actually just schedule this with a process, right? Once you've created the tickets, you can then create a workflow, which you don't even have to monitor, that just builds the thing, right? I've had specs that have like 30 tickets, and I have a setup in GitHub actions where it just basically churns through. Just says, "Okay, implement this thing, clear the context, implement the next thing, clear the context." And that can run overnight, right? I don't need to be there to monitor it. And I

19:10wake up in the morning, I review it, and I see what's what's been done. So, yeah, that's the idea. You know, that creates a PR for you, does human review, you get the idea. I'm still a bit of an amateur on this. I'm sitting a Claude code, for example. How do I tell it, schedule it, and parse this out, and then wait for the context

19:28window, and clear it out? You need a layer on top of the harness, basically. You think there's like the model itself, and then the harness, and the model and harness together form the agent. You need a layer on top that's going to say, right, do this, uh tell the agent to do this, and then clear the agent's context

19:47window. Do this, clear the agent's context window. And because like you think of a set of tickets, that's just a loop, right? You just have to just loop over that, and that can be deterministic. It doesn't have to be an agent. And so, I've built something for that called Sandcastle, which is pretty good. Uh there's also things like the AI SDK, which allow you to build these things in TypeScript, but you can you can think of even like Claude workflows, for instance. The workflow uh set up in Claude, where it you essentially just schedule a bunch of sub-agents using a

20:18script, that's exactly the same thing. So, you can think of that as kind of like an orchestrator over your agents. Okay, I see Sandcastle. It's another one of It's on GitHub, another one of your projects. I can just go there and get it, and it's the orchestrator I might use. Exactly. You get the idea. Okay, I see that. How about if we take it away from Now that I understand the way that you build and that you think about and lead the creation of something, why don't we go to a more personal stuff? Writing. What type of writing are you able to get the agent to

20:49do with your skill? Well, so this is this is actually a skill that I've um recently taken out of the repo. So, I don't I don't actually I didn't end up using it that much. I can talk about a different skill, which is sort of similar. Um Oh, actually no. Um no, okay, I'm

21:08thinking of the wrong thing actually. If you ask your question again, I think we can hit it around that. Basically, I Oh, I see. You've got writing for agents in here, but the writing that is like the output writing you don't have in here anymore, right? No. Well, I it might be like writing beats or something, but it's it's not very that's an in progress skill. I'm not sure it's it's quite ready for prime

21:29time. All right. What's a what's a non-development skill then that I could look at here and get an understanding of the way that you personally work? These are for engineers, basically. This this skill set. And the stuff that isn't for engineers, it's also sort of for engineers. But, the I tell you what. I I have a skill that I would love to talk about, which is a sort of new skill. I think what everyone is doing, what you're certainly doing a lot of, is writing skills, right? And writing instructions for agents, writing prompts for agents. And this writing for agents skill is essentially everything that I've learned about writing skills in a

22:04skill to help Okay. Um essentially allows you to Okay. Um essentially allows you to take all of the crap and all of the crud out of agent writing. Usually, when you get an agent to write something, it's just going to be full of a specific type of garbage. And that specific garbage is no-ops. So, if I search in here, I'm

22:27pretty sure I've got these. Um there's a specific uh mistake I see all the time with people creating skills, which is that they will write things inside the skill that do nothing to change the actual outputs of the skill or the behavior of the agent reading that skill. And I call these no-ops. This is sort of programming term. You can remove it and

22:51nothing will change. Okay. And if you look at skills that you've written or look at popular skills even that um that go viral, you can probably go through that and delete about half of it and not much about the output will change. It I definitely have that. I know it confuses my agent and largely the more I use the skill, the more of this junk gets built in, but I don't know what's junk and what's not. And when I say to somebody I'll have to go and read it, they laugh at me and it's true. I can't go and read the whole skill. I'm just saying to it at the end of each run,

23:22what could we do to improve next time? It gives me some suggestions. I say, okay, implement these but not those. It implements it and then I just trust that it's there and the very next time when something wacky comes out, I can't audit it cuz it's so much text. And I bet a lot of it is junk because frankly, even when it writes for me, it's junk. So,

23:39that's what this is about. 100%. That's exactly the thing that I'm trying to kill because what you need is you just need essentially a little pass over the top. Uh where is it? skill.md And this does a whole bunch of stuff in here. This is certainly one of my longer skills because it surfaces a lot of um

23:57important ideas. The main one that it's got in here is pruning, right? Keep each meaning in the skill to a single source of truth. And if you have duplication, the same meaning in more than one place, that costs you maintenance and tokens. So, you check every line for relevance. Does it still bear on what the document does? And you hunt no-ops sentence by sentence. An instruction the model already obeys by default pays loads of saying nothing. That's That's an awkward sentence actually. I don't like that

24:24one. [snorts] This is why reading the skills is actually blooming important because I That's That's a nasty little sentence. I think Opus wrote that. But, what you get the idea is like things like be thorough. Right? Be thorough. What does that mean? You know, people will often say, you know, it's almost like saying don't make mistakes or something. It's just It's That's a no-op, right? That's not going to do

24:44anything to change the agent's output. And so, this is definitely something that I think you should run on your own skills just to have a check and see if you can remove some stuff. So, like once a month, take all the skills that I've written and say, run it against this and and see what you can remove. Do I just trust it to make these decisions or do I

25:02need to see it? I mean, you can you can read the diff, right? Read the before and after and see what it's done and see if you agree with it. Um it will often really cull skills down into um smaller sections. It's pretty opinionated, you know, it contains all of my opinions. And also, if you have this on your system, this is a model and vote skill. It's says use when creating or editing skills or modifying agents.md or code.md. So, this will get invoked by your agent when it's making those crucial edits, which is

25:29very very handy. Okay. So, it's an automatic one that I can just set and then keep using. All right, I think that makes sense. Why don't we just close it out real quick with a conversation about um the one that you used to teach you to teach yourself? Yeah. Yeah, teach is great. I had a bit of a boring day um cuz I was traveling. And this is one that I actually wrote by hand. I didn't get an agent to do anything to this. I'm very passionate about teaching. Before I was a Before I

25:58was a dev, I was actually a voice coach. So, I taught people how to um speak and how to sing and like I did that for about 6 years. I had so much one-to-one teaching. And so, between that and between now teaching devs for about 4 years, I've got about 10 years of teaching experience. And I wanted to encode that into a skill just for fun and see what

26:17would happen. And this has been a blast because it's you're essentially just create a new folder on your system. And then teach, you can run it in that folder and say teach me something. And the usual thing you get with agents is that you know, it's it's good for that conversation, maybe it remembers, but it doesn't necessarily remember the next time you invoke it. Whereas teach, what it does is it creates a stateful workspace where it saves information about you. It understands how you're

26:46developing. It keeps learning records. So, it's just like a sort of teacher that you have sessions with. And then it creates these lessons in HTML which try to teach you skills or concepts depending on what you're doing. And it taught me how to So, what has it taught me? It's taught me how to uh get my son eating better foods uh who's about 2 and 1/2, so that's a bit of a challenge. And taught me how to solve a Rubik's Cube. It's been teaching me how to do better like folk harmonies as well. Like I've been using it for all

27:18sorts of stuff. And it's absolute joy to use. It's great fun. What does it know what it's teaching you? Is it researching it on its own? I know that it keeps up with what you've done, so it remembers for next time to keep you developing. [snorts] Yeah, it basically on its first run you say you interview you about what you want to learn and what your mission is, what the reason is you're you're learning. And then it goes out and finds primary source resources to pull in and teach itself essentially. I found it's really good actually for academic stuff because a lot of like those resources

27:52are in PDFs which are publicly available, and so it goes pulls in those PDFs, scans the stuff, and really understands it very deeply. And so yeah, it's working from primary source information, but of course it's an LLM, right? And so you should never really trust an LLM, and so it does push you to go and read those primary sources as far as I know. There we go. Each lesson should recommend a primary source for

28:13the user to read or watch. All right. This is fantastic. I think that this is it seemed to me like you were a little surprised by how popular this got. You then inspired a few other people to start putting their skills on. I actually even noticed uh one or two people who you interviewed then started putting their skills on and they were excited. I think the most exciting thing about seeing your skill online was seeing how you work and think about your own personal skills help me think about mine. And now that I've dug in a little deeper I've I've picked up some more understanding. And I I think this is

28:46really exciting. I interviewed this guy Mads who had lost his job, who went to get a job himself, and he used Claude to do it, and he wrote all these skills for himself. He said, "You know what? I'm just going to put them online." And as a result of that, it became the most popular skill for the week, and he didn't even know it. He just said, "You know what? I'll put it on GitHub." And he saw our show, and or someone saw our

29:05show and told him, and he was shocked. And I said, "Do you know how many people you're helping just by saying this is the stuff that's working for you, you're passing to others? Matt, you've done the same thing. You're inspiring me to do more of it." I'm now finally getting started, and I I I'd love to see more of what our audience is creating. They literally are now emailing me every day what they're what they're creating. When I get permission, I will show it on our weekly show, and I will say to you, Matt, you've been featured on our show several times because I go through every

29:29week the top 10 GitHub repos of the week. If you're watching us and you hadn't seen the show right yet, I've got one where you can see, just like I learned from Matt about his skill and his repo. Every week I learn about the top 10, and I've got one for you right here that you can learn along

29:42with me. See you there.