Your own components, right inside Markdown 🧩
Custom block renderers in Enriched Markdown, built with @jullerino for @t3dotcodes.
Images, videos, and links become your React components, while the rest of the Markdown renders as before.
Demo below 🎷👇
We're donating Agent Skills to the Agentic AI Foundation (@AgenticAIFdn), the same foundation we donated MCP to.
Since December 2025, 70+ agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code.
Here's what that means for you:
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence.
https://t.co/r0qFLdvd6c
@leerob@poteto I can call grok bot, it would be nice for grok bot to be able to call me in cases where something is urgent like an appointment reminder, security vulnerability on one of my servers etc notifications are not always effective sometimes
i built a skill that makes any app ready for the new iphone duo
most apps will just be stretched to fit the bigger screen
this skill actually redesigns them for both displays
here's what it does:
→ designs your app for both folded and unfolded screens
→ creates stunning UI concepts from your references
→ adapts existing apps built with swiftui, react native, flutter, etc.
→ handles the transition between both screens
→ generates apple-style product mockups of your app
works with claude code and codex
and i’m giving it away completely for free
retweet + comment "duo" and i'll send you the skill
(follow so i can dm you)
Every once in a while, some unsuspecting country's domain economy goes vertical 😂
.𝚌𝚘 → Colombia
.𝚒𝚘 → I/O → Island Ocean
.𝚖𝚍 → Markdown → Moldova
.𝚛𝚜 → Rust → Serbia
.𝚊𝚒 → AI → Anguilla
.𝚜𝚒 → SI → Slovenia
i'm doing a bunch of work on our desktop app
my flow is a single pinned "gooey" session where i tell it to do all work in subagents
then as i use it i keep telling it ideas/fixes i want and it goes off in a subagent to implement them - these can even be in different worktrees if it's complicated
it'll pop open html documents with screenshots to communicate before/after and give me options to pick
because a lot is going on in parallel i often will ask "what do you need from me" so it tells me what is ready for review