UIDrop
Send your favorite design systems to the AI agents you use.
What it does
Capture any website's design system, standout components, and implementation-ready prompts. Send them directly to Claude, ChatGPT, Gemini, Cursor, Lovable, or Manus, in one click. Then check your favorite snaps, pick elements from each of them (navbar, pricing, buttons) and merge them into one master prompt that your agents receive.
Capture any website
One click extracts every color, font, spacing value and component style — then sends it straight to your AI. Here's a dashboard inspired by Stripe! I've used a blue (#1D4ED8) primary color and clean sans-serif typography to match their aesthetic. Reads the live DOM, not source HTML, so it catches exactly what renders in the browser. One click opens Claude, ChatGPT, Gemini, Cursor, Lovable, Manus and more — with the tokens and screenshot already in the chat. I'll build a clean payment UI using that blue + teal palette with the Inter type scale. Starting with the nav, hero section, and pricing cards... Browse your full design history, compare two sites side by side, tag and filter, export…from uidrop.site
Does the same job
all alternatives →More dev tools this month
the category →



Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com


OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io


- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io


I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com