
Matt Pocock (@mattpocockuk) X analytics
@mattpocockuk
I teach devs for a living. Author of Total TypeScript and AI Hero. Ex-@vercel. Used to be a voice coach.
@mattpocockuk has 397.1K followers, a median of 109.4K views per post and a 1.59% engagement rate.
Based on 30 recent original posts (high confidence). Updated November 21, 2026.
At a glance
Key stats
- Followers
- 397.1K397,065 followers on November 21, 2026+5.7K in 7 days+21.3K in 30 days
- Median views per post
- 109.4K
- Average views per post
- 127K
- Engagement rate (by views)
- 1.59%
- Original posts per week
- 13.6
- Average engagements per post
- 2,018
Engagement grade
Strong
This is above the baseline for accounts with 100K-1M followers.
Profile score
84/100
- Profile completeness100
- Audience shape100
- Engagement25
- Consistency100
- Positioning clarity94
Monetization
Estimated X creator earnings
$837–$2,093 in the last 30 days
From 8.4M views on @mattpocockuk's original posts in the last 30 days.
Rewards eligibility: likely
Rough estimate. X publishes no payout rate, so this assumes about $100–250 per 1M original-post impressions, based on real creator payouts. Payouts vary with how many of your viewers have Premium.
Free report
How does your account compare with @mattpocockuk?
Get the same report for your own account by email: engagement grade, median views, best times to post and estimated earnings.
Growth
Follower growth
+5.7K followers in the last 7 days. +21.3K in the last 30 days. Tracked by Xholic since October 4, 2026.
| Date | Followers | Change |
|---|---|---|
| Nov 21, 2026 | 397,065 | +1,256 |
| Nov 19, 2026 | 395,809 | +2,163 |
| Nov 18, 2026 | 393,646 | +1,627 |
| Nov 16, 2026 | 392,019 | +669 |
| Nov 14, 2026 | 391,350 | +653 |
| Nov 13, 2026 | 390,697 | +2,286 |
| Nov 11, 2026 | 388,411 | +791 |
Timing
Best times to post
When @mattpocockuk's recent posts performed best (UTC).
- #1 slot
8:12 PM
Monday · UTC
- #2 slot
8:18 PM
Tuesday · UTC
- #3 slot
8:34 PM
Wednesday · UTC
What worked
Top recent posts
- 01

@mattpocockuk ·
It's been nearly 6 months since I posted a 'watch me work' deep dive on my skills. Since then, they've become the most-starred skills repo in the world. So, here's 70 minutes of me building a 21,000-line PR, especially focusing on: - DDD with /grill-with-docs - Improving your codebase with /retro - How to do human review effectively Enjoy!
Watch video- 114Replies
- 307Reposts
- 5KLikes
- 329.5KViews
4.8x average engagementHas a videoLong post (over 200 characters)Posted Wed 16:00 UTC - 02

@mattpocockuk ·
A lot of folks ask me "how do you work with agents in multiple repos at once?" I have a very simple solution - the Home Repo I have a single repo (the home) where all of my skills, steering files, wiki etc live. I run my agent in the home repo, and then inside AGENTS.md I have pointers to the other repos: ``` For skills, clone mattpocock/skills to ~/repos/skills. For Sandcastle, clone mattpocock/sandcastle to ~/repos/sandcastle ``` This is extremely simple and incredibly effective. The home repo lets you: 1. Put all your steering files and tooling in one place 2. Have a single spot to run all your agents in 3. Make sweeping changes over multiple repos Talked about this in the course yesterday and folks are loving it (see below). I'm sure you will too. Enjoy!

- 313Replies
- 204Reposts
- 3.5KLikes
- 288.5KViews
2.9x average engagementHas an imageLong post (over 200 characters)Posted Tue 21:00 UTC - 03

@mattpocockuk ·
Prompt of the day (a long one): Take a look at every code comment in <my codebase | this section of the code>. Categorise each comment as: - Tautology: simply repeats what is already visible from the code - Excuse: many comments allow the agent to get away with a hacky implementation, which then gets propagated through the code - Stale: references code or implementation information that is no longer relevant - Decision Record: documents an important, non-obvious decision about the code For each comment, take this action: - Tautology/Stale: delete the comment - Excuse: delete the comment and file an issue to fix the hacky implementation - Decision Record: move it into an ADR Once this is done: - Create a lint rule banning comments for <my codebase | this section of the code> - Take a ratchet approach, assuming not all comments will be deleted this PR - Create a /delete-comment skill in this repository so we can repeat this process later - Estimate for me how many lines of code we'll shed by deleting all comments --- I'm sold - comments considered harmful
- 129Replies
- 101Reposts
- 2.7KLikes
- 161.7KViews
2.6x average engagementText onlyLong post (over 200 characters)Posted Fri 15:00 UTC - 04

@mattpocockuk ·
A brief history of AI Coding since Nov 2025: Nov 2025: Opus 4.5 releases, OpenClaw gets built Dec 2025: community agrees that models get good enough to handle 95% of coding tasks Jan 2026: Ralph loops get popular, early efforts on loops/orchestration Feb: Everyone feels knackered, too much strategic decision-making, fears around cognitive debt begin Mar: Skills explosion as community converges around easy-to-share processes (superpowers already ahead of the game here) Apr: most SOTA devs haven't written a line of code in months May: "The unreasonable effectiveness of HTML" - more interest in richer review surfaces Jun: "Loop Engineering" wins vaguepost of the year, signals more hype around process Jul: Every talk in every conference becomes "here is my software factory" Aug: Opus 5 speaks incomprehensibly, interest in ASD-STE100 peaks Sep: Grok Bot gets popular, more interest in long-running "manager" threads which retain context and delegate work Oct: The promised speed gains haven't materialised, "dark factory" feels a long way off still Nov: No-slop manifesto releases, reading the code still appears essential TL;DR: no-one is writing code anymore, and we are still figuring out what that means
- 294Replies
- 416Reposts
- 5.2KLikes
- 282.3KViews
1.9x average engagementText onlyLong post (over 200 characters)Posted Mon 11:00 UTC - 05

@mattpocockuk ·
As expected, the thing that is blowing people's minds most in my course is not the agentic stuff. It's the DDD stuff - domain-driven design. Building a ubiquitous language, using it with the agent, and refactoring the code to use it. Just bonkers how good it is
- 217Replies
- 126Reposts
- 3.3KLikes
- 266.3KViews
1.7x average engagementText onlyLong post (over 200 characters)Posted Wed 13:00 UTC - 06

@mattpocockuk ·
.@poteto's talk at AIE Code is excellent. If I had to pick one still from that felt genuinely original, it would be this one: "nuance tends to lead to slop" To increase quality, design API's and automated checks that remove the nuance from agents' decisions. - Ban useEffect - Ban 99% of explanatory comments (they just lead to workarounds) - Create API's that hide complexity from agents Full talk below.

- 130Replies
- 123Reposts
- 2.9KLikes
- 173.7KViews
1.7x average engagementHas an imageLong post (over 200 characters)Posted Mon 13:00 UTC
Latest
Recent posts by Matt Pocock
The latest 30 original posts from @mattpocockuk, newest first, as of November 21, 2026. Replies and reposts aren't included.

@mattpocockuk ·
Cooking my first skill for non-devs It's called /vector, and it guides you on how to delegate AI for any task. Six simple steps, and you'll have a workflow that is easy to use, easy to trust, and gets better over time I'm planning on releasing frameworks and docs around it so you can run your own VECTOR sessions at your company: - Find workflows that AI could help with - Give agents the right context - Reorder the workflow - Identify ways it can improve over time (via memory) Releasing soon. Would you use this?

- 102Replies
- 32Reposts
- 1.4KLikes
- 49KViews

@mattpocockuk ·
Prompt of the day (a long one): Take a look at every code comment in <my codebase | this section of the code>. Categorise each comment as: - Tautology: simply repeats what is already visible from the code - Excuse: many comments allow the agent to get away with a hacky implementation, which then gets propagated through the code - Stale: references code or implementation information that is no longer relevant - Decision Record: documents an important, non-obvious decision about the code For each comment, take this action: - Tautology/Stale: delete the comment - Excuse: delete the comment and file an issue to fix the hacky implementation - Decision Record: move it into an ADR Once this is done: - Create a lint rule banning comments for <my codebase | this section of the code> - Take a ratchet approach, assuming not all comments will be deleted this PR - Create a /delete-comment skill in this repository so we can repeat this process later - Estimate for me how many lines of code…
- 129Replies
- 101Reposts
- 2.7KLikes
- 161.7KViews

@mattpocockuk ·
Reading back through the AI Coding Crash Course, it is insane how much of it can be directly ported to non-coding work Giving me some ideas...
- 91Replies
- 7Reposts
- 419Likes
- 52.7KViews

@mattpocockuk ·
It's been nearly 6 months since I posted a 'watch me work' deep dive on my skills. Since then, they've become the most-starred skills repo in the world. So, here's 70 minutes of me building a 21,000-line PR, especially focusing on: - DDD with /grill-with-docs - Improving your codebase with /retro - How to do human review effectively Enjoy!
Watch video- 114Replies
- 307Reposts
- 5KLikes
- 329.5KViews

@mattpocockuk ·
Who is writing the best stuff/making the best videos about using AI for non-coding tasks? That field is full of noise, I need signal
- 117Replies
- 18Reposts
- 1.3KLikes
- 122.3KViews

@mattpocockuk ·
Today's experiment: If too much choice is bad for agents, what if you could create an EXTREMELY constrained version of the tools you like? I.e. the agent is allowed to use React, but all state must be in Zustand/useReducer? Strip out all the nuance, create a black hole of success, all through incredibly harsh lint rules. Thinking of calling it /constrain
- 189Replies
- 20Reposts
- 818Likes
- 71KViews

@mattpocockuk ·
Prompt of the day: Let's assess the XState v6 beta. 1. Research what it does and the problem it solves. 2. Find the gnarliest problem in our application that it might assist with 3. Create a proof-of-concept implementation in a draft PR 4. Fully verify the results 5. Grade it on: 5a. How much nuance there is in the API (more is worse, agents perform better with fewer choices) 5b. How typesafe it is 5c. How easy-to-test it is 5d. How much cyclomatic complexity it introduces 5e. The quality of docs provided 5f. What changes to deployment will be needed 6. Give me your overall recommendation Drop in a technology you're interested in, and see if it's any good
- 75Replies
- 30Reposts
- 902Likes
- 68.4KViews

@mattpocockuk ·
Starting in a couple of hours! I'll be interviewing @badlogicgames and @mitsuhiko about the current software engineering meta Maybe we need to slow the f*** down Starting 4:20PM UTC https://t.co/58Sazr19FV
- 26Replies
- 13Reposts
- 330Likes
- 42.2KViews

@mattpocockuk ·
.@poteto's talk at AIE Code is excellent. If I had to pick one still from that felt genuinely original, it would be this one: "nuance tends to lead to slop" To increase quality, design API's and automated checks that remove the nuance from agents' decisions. - Ban useEffect - Ban 99% of explanatory comments (they just lead to workarounds) - Create API's that hide complexity from agents Full talk below.

- 130Replies
- 123Reposts
- 2.9KLikes
- 173.7KViews

@mattpocockuk ·
A brief history of AI Coding since Nov 2025: Nov 2025: Opus 4.5 releases, OpenClaw gets built Dec 2025: community agrees that models get good enough to handle 95% of coding tasks Jan 2026: Ralph loops get popular, early efforts on loops/orchestration Feb: Everyone feels knackered, too much strategic decision-making, fears around cognitive debt begin Mar: Skills explosion as community converges around easy-to-share processes (superpowers already ahead of the game here) Apr: most SOTA devs haven't written a line of code in months May: "The unreasonable effectiveness of HTML" - more interest in richer review surfaces Jun: "Loop Engineering" wins vaguepost of the year, signals more hype around process Jul: Every talk in every conference becomes "here is my software factory" Aug: Opus 5 speaks incomprehensibly, interest in ASD-STE100 peaks Sep: Grok Bot gets popular, more interest in long-running "manager" threads which retain context and delegate work Oct: The promised speed gains…
- 294Replies
- 416Reposts
- 5.2KLikes
- 282.3KViews
Show all 30Show fewer

@mattpocockuk ·
Tired of walls of markdown? Try an /animatic. I'm working on two skills: - /setup-animatic, that chooses the tooling and sets it up on your machine (or a remote machine) - /animatic, that creates a video ready for upload I've been using them for a while. Here's a preview:
Watch video- 157Replies
- 69Reposts
- 2.1KLikes
- 134.5KViews

@mattpocockuk ·
My dream is for every important PR to be accompanied by a video that shows folks how it works Working on an /animatic skill for this
- 338Replies
- 84Reposts
- 3.6KLikes
- 224.4KViews

@mattpocockuk ·
Hit 200K in January Hit 300K in August Will hit 400K in 2 weeks' time Thanks for a crazy year on X, folks. Glad you're enjoying it!
- 52Replies
- 8Reposts
- 1.1KLikes
- 97.5KViews

@mattpocockuk ·
Working with agents across multiple repos is a pain Where do you put the skills? The steering files? The tooling? Let me propose a solution I've been using for months (that I thought was too boring and obvious to post) It's a pattern called the Home Repo. Enjoy:
Watch video- 196Replies
- 116Reposts
- 2KLikes
- 197KViews

@mattpocockuk ·
Published a proper article on the Home Repo pattern - the simple solution to running agents across multiple repos. Contains a prompt you can run on your org's repos to help you set it up for yourself. Enjoy your new home https://t.co/Y2HIzu3d0z
- 84Replies
- 101Reposts
- 1.4KLikes
- 73.6KViews

@mattpocockuk ·
I just told my agent "treat me like a tool call" So degrading
- 179Replies
- 56Reposts
- 2KLikes
- 128.9KViews

@mattpocockuk ·
One odd quirk of AI is that if you can describe your business processes in clear, consistent language... ...you've already half-built all the software you need to automate the process DDD has never been more powerful
- 76Replies
- 33Reposts
- 744Likes
- 93.8KViews

@mattpocockuk ·
Super excited to be doing another one of my live interviews This time, with two legends in the space: @mitsuhiko and @badlogicgames You'll learn how the creators of Pi think code should be written in the AI age Monday, 4:20PM UTC https://t.co/58Sazr0BQn
- 31Replies
- 28Reposts
- 485Likes
- 60.4KViews

@mattpocockuk ·
As expected, the thing that is blowing people's minds most in my course is not the agentic stuff. It's the DDD stuff - domain-driven design. Building a ubiquitous language, using it with the agent, and refactoring the code to use it. Just bonkers how good it is
- 217Replies
- 126Reposts
- 3.3KLikes
- 266.3KViews

@mattpocockuk ·
A lot of folks ask me "how do you work with agents in multiple repos at once?" I have a very simple solution - the Home Repo I have a single repo (the home) where all of my skills, steering files, wiki etc live. I run my agent in the home repo, and then inside AGENTS.md I have pointers to the other repos: ``` For skills, clone mattpocock/skills to ~/repos/skills. For Sandcastle, clone mattpocock/sandcastle to ~/repos/sandcastle ``` This is extremely simple and incredibly effective. The home repo lets you: 1. Put all your steering files and tooling in one place 2. Have a single spot to run all your agents in 3. Make sweeping changes over multiple repos Talked about this in the course yesterday and folks are loving it (see below). I'm sure you will too. Enjoy!

- 313Replies
- 204Reposts
- 3.5KLikes
- 288.5KViews

@mattpocockuk ·
Playing around with a different UI for grilling A shared 'decision ticket' board, where your team can talk through decisions before implementation Why leave all the alignment until review - get it done early

- 80Replies
- 9Reposts
- 475Likes
- 45KViews

@mattpocockuk ·
Agents make Goodhart's Law a LOT worse: "When a measure becomes a target, it ceases to be a good measure." Agents are incredibly good at gaming metrics. So any organisation that says "we track your number of PR's" is fucked. Measuring productivity was already impossible. Now it might be actively harmful.
- 136Replies
- 38Reposts
- 584Likes
- 46.8KViews

@mattpocockuk ·
Agree, with a modification: "wtf is this crap, no, not like this. not ever again. new lint rule"
- 29Replies
- 24Reposts
- 679Likes
- 60.2KViews

@mattpocockuk ·
One tip to improve your grilling Instead of talking about the 'what', try explaining more of the 'why'. BAD: "I want to build an analytics panel for admins with graphs and filters" GOOD: "Admins can't currently see an overview of the important data in the app" If you start by explaining your proposed solution, the agent will stick to it. It'll assume all the important stuff is settled, and just grill you on implementation. But if you describe the problem, you'll give the agent license to be more creative. You'll end up with a much deeper, better conversation.
- 127Replies
- 150Reposts
- 3KLikes
- 140.6KViews

@mattpocockuk ·
Just wanted to defend the term "Software Factory" for a second. First, the caveats: It's bullshit. It sounds fancier than it really is. It's a bandwagon. People are using it to get you and their VC's hyped. But it's also referring to a real change. Earlier this year, most SOTA teams were using agents to work on the product. Shipping features, fixing bugs. But now, they're building automations to help agents work on the product for them. They've moved up a layer. What do we call the thing they're building? Loops? Workflows? Some other generic label? "Software Factory" is as good a term as any other. - "We're not working on the product, we're working on the factory that builds the product." - "We're not product engineers, we're factory engineers." I like it. I'll continue using it.
- 278Replies
- 88Reposts
- 2KLikes
- 186KViews

@mattpocockuk ·
Last cohort of the year starting today. A huge chunk of all-new material. Always exciting, always electrifying, always slightly terrifying. For folks who bought a ticket, enjoy ❤️
- 11Replies
- 0Reposts
- 228Likes
- 31.3KViews

@mattpocockuk ·
Thanks @thoughtworks! Markdown files in the Thoughtworks Technology Radar, who'd have thunk

- 51Replies
- 5Reposts
- 334Likes
- 41.1KViews

@mattpocockuk ·
And specifically, does understanding React still matter? I'd say yes, more than ever
- 86Replies
- 67Reposts
- 1.1KLikes
- 121.2KViews

@mattpocockuk ·
Rob is one of the voices I trust most on engineering Bend2 looks good eh
- 27Replies
- 46Reposts
- 1.2KLikes
- 92.1KViews

@mattpocockuk ·
Prompt of the day is a simple one: "How do we make this change fully verifiable?" Makes the agent bend over backwards to verify all its changes. Signing up for real services, clicking through the frontend. Quality goes through the roof.
- 242Replies
- 110Reposts
- 2.8KLikes
- 127.6KViews
Formats
Content mix
- Text only
- 63%
- With media
- 27%
- With links
- 3 posts
- With hashtags
- 0 posts
Creator style: High-reach broadcaster
See the full app
This creator report is one small part of Xholic
Click through a sample creator's account in the real app. No sign-up, nothing to install.
- Posts written in your voice and scheduled for your best hours
- Buyers found on 𝕏, with a reply drafted for each one
- Analytics that show which posts grow you
No sign-up or login needed · Takes about 2 minutes

Want numbers like @mattpocockuk's?
Xholic writes posts in your voice, schedules them for the hours your audience is active, and tracks what's working every day.
No card needed · Nothing to cancel
Live demo: no sign-up or login needed · takes about 2 minutes
Keep browsing
More in AI & developers
Keep exploring
Free tools
- Compare Twitter AccountsPut two public accounts head to head and see who leads on views, engagement, grade and posting pace.
- Twitter Engagement Rate CalculatorCalculate engagement rate from your numbers or a public profile and grade it against your tier.
- X Monetization CalculatorChange the assumptions behind six X revenue models and compare gross revenue with direct contribution.
Guides
- How to Write a Tweet With an AI Tweet GeneratorTurn a rough idea into a tweet worth posting: write a specific prompt, pick a tone and length, compare three drafts and make the best one sound like you.
- How to Analyze Any X Profile and Read the ReportAnalyze any public X profile and read the report properly: how each metric is calculated, what is measured vs estimated, and three worked readings.
From the blog
- 10 X Analytics API Alternative Options for 2026Compare 10 X analytics API alternatives for 2026, from low-cost data providers and custom scrapers to enterprise listening platforms.
- Twitter API Examples: A Practical Guide for BuildersExplore real Twitter API examples with code, auth flows, rate limits, and patterns for posting, streaming, analytics, and growth workflows on X.
Best tweets on this topic
- Best tweets about Open-Source AIBrowse the best tweets about open-source AI, open-weight models, community tools, training, deployment, licensing, and research. Updated every two weeks.
- Best tweets about Google AI StudioDiscover the best tweets about Google AI Studio, covering Gemini API prototypes, prompting, structured output, model testing, and developer workflows.
- Best tweets about GitHub CopilotThe best tweets about GitHub Copilot: coding workflows, agent features, reviews, limitations and developer productivity. Updated every two weeks.
About this data
- Analytics are inferred from public profile and recent post data. They do not include private impressions, profile visits, link clicks, or follower-source data.
- Deleted, protected, unavailable, or rate-limited posts may be missing from the sample.
- Stats come from public posts Xholic has stored, not private X Analytics. Xholic is not affiliated with X Corp or @mattpocockuk.
- Own this account and want it hidden? Email support@xholic.ai — we verify ownership and handle requests within 2 working days.