Get live statistics and analysis of Matt Pocock's profile on X / Twitter

My skills repo has 160K stars, 7.5m downloads... ...and no tutorial. So, here it is. Watch me walk through the essential skills: - /grill-with-docs - /to-spec - /to-tickets - /implement - /code-review It's the whole flow, end-to-end. Enjoy:

Today's the day. My Beginner's TypeScript tutorial has dropped. And it's free for everyone. 🧵

This is an extremely good watch. The things that felt novel/interesting to me: 1. Lock down your agents Humans tend to like 'sharp knife' abstractions - that are powerful, but you can cut yourself if your use them wrong. Lauren says agents perform much better in extremely locked-down environments. Abstractions are designed so they can't screw up, and lint rules enforce it. They built a whole internal framework (Dune) to keep the agent on track. That helps optimise agents that don't have a large context window to work productively in your codebase. 2. Create verification infrastructure To trust the results of any agent, you either need to sit and watch it OR have it provide evidence of its improvement. This has always made sense to me, but Lauren really pushes it hard here: - Invest in custom CLI's that let the agent drive the app and measure its performance - Make the app "factory ready" from the get-go - i.e. deployable to an environment where the agent can mess about with it 3. Feature Maps Lauren's software factory (what she calls an 'outer loop') often requires the agent to break down vague bug reports from users and to turn those into potential fixes. To aid that, they built a 'feature map' of all the main features in their application, which describe exactly how the app is supposed to function. This has become essential for helping the agent navigate the codebase, and figure out quickly how things are supposed to work. It's maintained along with the codebase, and kept in sync via automations. This is the kind of documentation I usually warn against. It goes stale quickly and can confuse agents if it's not kept up to date. But Lauren's team are using it as critical navigation infrastructure, and it makes it possible for agents to explore faster and better - even on a large codebase. So it sounds like navigation docs like this are worth it if they enable new behavior. Banger talk - watch the whole thing on 2x.

mattpocock/skills v1.2 is out! We're now the 19th most-starred repo of all time. 13.5m downloads on skills​.sh. Thanks for your support! Here's what's new: - Docs: the community's biggest ask. Every skill documented, with explanations of the main flows + troubleshooting - Claude Plugin: install via Claude's official marketplace - Codex Support: full Codex support via agents/openai.yaml files Updated Skills: - /grilling now asks you questions in rounds, not one-by-one - /prototype now uses HTML instead of a TUI for building logic prototypes - easier to share and far richer - /writing-for-agents renamed from /writing-great-skills, use it for ANYTHING your agents read (AGENTS.md, system prompts, docs) New Skills: - /wizard: tired of provisioning infra? Get your agent to build you a TUI to walk you through it - /to-questionnaire: hit a grilling question you can't answer? Turn the session into a doc you can walk through on a call with a colleague - /wait-what: no idea what the model said? Refocus it in your domain language and simplify with ASD-STE100 Full changelog + docs below. Video soon!

If you don't know generics, I promise you'll understand them by the end of this thread. I like a challenge.

Lots of folks feeling FOMO about MCP. Here's the problem it solves:

Here's a fun trick you can do with template literals in TS!

Prompt of the day: /retro read my last 10 coding agent sessions and find ways to make my repo easier to navigate. Find where agents take too long to find relevant information, or rely on out-of-date docs. Improving navigability is such an underrated way to save tokens.

Devs who are feeling overwhelmed, take an hour out of your workday and do this: Setup 1. Get Anthropic Pro ($20), with a plan to upgrade to 5X Max later 2. Download Claude Code 3. Select Opus 4.5 (it's the default) Loop 1. Start plan mode 2. Plan a small feature 3. Once you're happy with the plan, auto-accept edits 4. Pause the LLM if you're not happy with the output 5. Clear context and repeat for the next feature Continue doing this until you get a feel for what the LLM can and can't do. It'll take 10-20 hours of practice.

/handoff might be my new favourite skill

🧵 The Ultimate TypeScript Thread 🧵 Here's everything I've learned from leading TS dev teams and working on XState's core team. My goal is to turn you into a TypeScript wizard. And yes, this thread is EVERGREEN - I'll add at least 3 more tips a week 🚀 Let's get started.

I poured my 10 years of teaching experience into a skill. It's called /teach, and it can teach you anything. Here's how it taught me to solve a Rubik's cube:

New in-progress skill: /loop-me Interviews you about your work and finds opportunities for delegating your day-to-day work to AI

Ultrawide, or dual monitor?

There's an anti-TypeScript post floating around with lots of the typical criticisms: - "Makes devs too slow" - "Only good for MASSIVE projects" - "Too much boilerplate" Let's bring a bit of positivity. What do you like about TS?

Folks who are running GLM 5.2, how are you doing it? What harness/provider are you using? Getting FOMO about an open weights model for the first time

I'm moving away from my local dev setup Makes zero sense to me now

Here's a fun trick you can do with template literals in TS!

Starting to wonder if the smartest way to reduce slop is just to produce less code Force code review to continually reduce code while ALSO keeping cyclomatic complexity low Less code means less code to maintain, fewer bugs

Folks using WSL* as their dev environment, what's your experience been like? I have a phat gaming PC that could churn up some dev tasks/video editing tasks but am nervous about the switch. * Windows Subsystem for Linux

I feel like we need a better name for '{}' in TS. People think it's an 'empty object', but it's not - it's really 'anything except null or undefined'. What should we call it?

What CLI's are folks using for managing multiple agents in the same terminal? I'm happy with Claude agents but it's not for everyone. Also keen to try herdr. What else?

The "should you read code" debate is dumb because the real decision isn't binary, it's a scale: 1. Reading every line of every diff 2. Scanning every diff, reviewing important lines 3. Ignoring diffs but understanding the 'why' of every PR 4. Spot checking PR's instead of reading every one 5. Ignoring PR's, but doing regular spot checks on the codebase 6. Ignoring the code, but spot checking agent traces to help improve the system 7. Ignoring both the code and the system, let models handle everything Where are you on the scale?

What are you guys using to let your agent spawn other agents? I.e. NOT subagents, but to open more tmux/herdr panes, or claude agents? I have a /claude-handoff skill which I use a LOT, and I'm debating making it into /spawn /spawn would detect what tool you use (tmux/cmux etc) and spawn agents to work on tasks when needed Perfect for /wayfinder

There are a class of AI Coding assets that IMO don't really belong checked into git: - PRD's - Research files - Decision maps - Implementation plans Folks who agree with me, what are you using instead?

Would you reject a decent-paying job offer if the company didn't use TypeScript, and wasn't interested in adopting it?

Knowledge work is SO much harder to automate with agents than code We underestimate how easy software development is for agents - Tons of high quality automated feedback loops (types, tests) - Well-organized free documentation, searchable on the web - Simple-to-use workspaces with version control (i.e. repositories) - Long history of systematising and delegating work (i.e. sprints, tickets, specs) Knowledge work has none of these advantages

What's the hardest UI element to build, and why? Bonus points if it reaches across the stack, like image uploaders or pagination.

I wish 'try' worked like this: