@FaizalSukaimi npx skills add shadcn/ui, then find a design.md. Search for awesome-design-md on GitHub, or https://t.co/qxilvKrhqv by @thekitze or @typeui_sh by @zoltanszogyenyi
(there are a lot online but these are the ones I used recently)
Claude Code is terrible at UI design and everyone knows it.
so this repo fixed it.
awesome-design-md by VoltAgent is a collection of DESIGN.md files extracted from 31 real websites Stripe, Vercel, Notion, Supabase, Linear, NVIDIA, Apple, and more.
you drop one file into your project root, tell your AI agent "build me a page that looks like this" and it generates UI that actually matches.
no Figma exports. no JSON schemas. no special tooling.
just a markdown file your agent can read colors, typography, spacing, buttons, cards, shadows, responsive rules, everything.
it works because DESIGN.md is a concept Google Stitch introduced. plain-text design systems that LLMs understand natively.
if you're tired of Inter font, purple gradients, and card grid layouts on every single project — this is the fix.
https://t.co/67H23zJp4E
Google Stitch has released 𝗗𝗘𝗦𝗜𝗚𝗡.𝗺𝗱 🤯
One markdown file that teaches your AI coding agent your entire design system.
→ No Figma exports
→ No JSON schemas
→ Nothing to configure
The part that saves the most time:
A free collection of 40+ pre-built files already exists, extracted from real products. Stripe, Vercel, Linear, Notion, Lovable, Claude, ElevenLabs, Cursor, Warp, Zapier, and more.
Drop it in your project root. Claude Code, Cursor, Gemini CLI, and GitHub Copilot all read it natively.
100% Free and Open-Source.
🚨 Someone reverse-engineered the design systems of Apple, Spotify, Airbnb, and 30+ billion-dollar companies.
Packed each one into a single file. Free.
It's called Awesome Design MD.
Drop one file into your project. Your AI agent builds UI that looks like Spotify. Or Apple. Or Airbnb. Instantly.
Not screenshots. Not Figma links. A single DESIGN .md file that captures every color, font, spacing value, button style, and layout pattern from a real website. In a format AI agents read and reproduce.
Here's the difference:
Tell Claude Code "build me a landing page" and it gives you generic UI.
Tell Claude Code "build me a landing page" with Spotify's DESIGN .md in your project and it gives you Spotify.
Here's what's inside:
→ Apple. Premium white space, SF Pro typography, cinematic imagery.
→ Spotify. Vibrant green on dark, bold type, album-art-driven layout.
→ Airbnb. Warm coral accent, photography-driven, rounded UI.
→ Linear. Ultra-minimal, precise spacing, purple accent.
→ SpaceX. Stark black and white, full-bleed imagery, futuristic.
→ BMW. Dark premium surfaces, precise German engineering aesthetic.
→ NVIDIA. Green-black energy, technical power aesthetic.
→ Uber. Bold black and white, tight type, urban energy.
→ Sentry, PostHog, Raycast, Cursor, ElevenLabs, and 20+ more.
Here's how to use it:
→ Pick a design system from the collection
→ Copy the DESIGN .md file into your project root
→ Tell your AI agent to use it
→ Get UI that matches the design language of a billion-dollar company
That's it. One file. Your AI agent now has the design taste of a $200/hour design consultant.
Designers charge $5,000+ for a custom design system. Companies spend $50,000+ building one from scratch.
This is free. 31 design systems. Copy. Paste. Ship beautiful UI.
Works with Claude Code, Cursor, Codex, and any AI coding agent that reads project files.
100% Open Source. MIT License.
You can now push what you’re building in Claude Code directly into Figma.
With the latest updates to the Figma MCP server, build a working prototype in code, then send it to a Figma canvas to explore multiple versions.
If you're building an iOS app with Claude Code - copy and paste this into your https://t.co/NAvUlpakOC file. It prevents 90% of the issues I hit in the first month:
Essential Rules for iOS work with @claudeai
1. Never let AI modify .pbxproj files. Create files with Claude Code, add them to Xcode manually. One corrupted project file will waste hours.
2. Document platform gotchas immediately. Hit an iOS 26 API issue? Add it to https://t.co/NAvUlpakOC that session. "NO .background() before .glassEffect()" saved me from
repeating that mistake 50+ times.
3. Use feature flags for experimental code. Toggle new features on/off without rebuilding. Makes rolling back instant when something breaks at 11pm.
4. Always request debug logging. Ask Claude Code to add Logger statements for complex flows. Future you will thank past you when debugging async camera issues.
5. Test after every change!! Clean build folder (Cmd+Shift+K), run on device, verify in console. Catch issues before they compound.
6. Keep conversations focused on single components. Don't ask to "refactor the whole app" Smaller scope = better results.
7. Document what changed in session. End every major change with a markdown file explaining what broke, how it was fixed, and rollback steps.
I built a performant, full featured iOS app this way. Zero project corruption. Every session leaves the codebase better than it found it.
how do Adaline and Apple make these crazy 3d zooming effects as you scroll?
it's easier than you think - let me show you how
prompts and code in thread:
Many are asking if they can move their Next.js projects from Vercel to Replit?
Yes!
- Go to Import then GitHub
- enter repo URL
- Agent will take care of the rest
It will set up the dev and deployment environments!
For companies moving lots of work, happy to help + discount.
📣 This is not a drill: Email Sending is coming to Workers: just call email.send() - !
As part of this, we're combining Email Sending and Email Routing together into a cohesive, unified hub to manage emails.
Build a market research agent with Gemini and @aisdk by Vercel. Learn how to research trends with Google Search, extract structured data into charts, and generate a final PDF report.
The last few years were about proving what AI can do. Now, it's about building with it.
We've put together a new list of startup ideas we're especially excited about— ideas that treat AI not as a feature, but as a foundation.
https://t.co/AbQWcpKCZX
[New post] 🔥A Deep Dive Into MCP and the Future of AI Tooling
APIs were the internet’s first great unifier but AI models lack an equivalent. What are the use cases of MCPs today? Where are the challenges?
Here's a technical deep dive & map of the current ecosystem 👇