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!
When you go talk to users, don't (just) ask them what features they want. Ask them what problems they have. In the best case this will lead you to think of features they'll love but would never have thought to ask for. And expect to go through multiple cycles of ask-and-build.
My account has been suspended twice in three days. I have asked support for an explanation, but I haven't received a response. The worst part is that they reactivate it without telling me why it was suspended in the first place, and for two days I haven't been able to use my premium subscription. I would like to know why this is happening @Support@X
Is anyone else experiencing this?
I might never look the source again. It was nearly a half century ago that I stopped looking at assembly because I trusted the compiler to get it right. This feels like that.
As someone young in this industry, this is one of my favorite things: knowing brilliant people came before us, willing to share their knowledge and experience, and who actually care about investing in the next generation — because without that, this industry wouldn't move at the pace it does. Appreciate you sharing this @joshpuckett
Now I'd love to talk about the responsibilities of the young. Where should we invest our time to build the judgment to understand the "why" behind the decisions elders or AI make, instead of just copying/using them because everyone else does?
On Being an Elder
Finally took the time this morning to write down some thoughts I’ve been pondering lately about what it means to be someone in tech who’s been doing this for a while.
It’s a reminder for myself as much as anything, but I hope it might inspire you as well.
Made a @raycast script that grabs any highlighted URL and drops it into a markdown note in my wiki. Here's the setup:
In Raycast, run "Create Script Command"
Shell > Silent mode > name it whatever > check "With argument"
Save it wherever, e.g. ~/Scripts/Raycast
Then in Terminal:
`open -e /your/path/to/the/script` to edit it
Delete the "Hello World" line
Drop in this (code bellow 👇🏻)
Then, `chmod +x https://t.co/8pBPlJQspn `
Setup a hotkey or an alias — your call
Select a URL and run the script
https://t.co/Tcbw1xBILg
Note: hotkeys skip the argument prompt entirely, so if you want to attach a extra note besides the url, you'll need to run it via alias instead.
Made a @raycast script that grabs any highlighted URL and drops it into a markdown note in my wiki. Here's the setup:
In Raycast, run "Create Script Command"
Shell > Silent mode > name it whatever > check "With argument"
Save it wherever, e.g. ~/Scripts/Raycast
Then in Terminal:
`open -e /your/path/to/the/script` to edit it
Delete the "Hello World" line
Drop in this (code bellow 👇🏻)
Then, `chmod +x https://t.co/8pBPlJQspn `
Setup a hotkey or an alias — your call
Select a URL and run the script
@mattpocockuk@JohnOusterhout Awesome book. How do you apply the concepts addressed in the book to your AI agent workflow? I’ve heard you say that we should be strategic programmers, but could you elaborate on that, please?