hasi98

hasi98 / designpull

Public

Generate Google Stitch compatible DESIGN.md files from any website using AI vision. Bring your own Gemini, OpenAI, Claude, or Ollama key. No backend, no cost.

ai-design bring-your-own-key chrome-extension claude css-extraction
12
9
100% credibility
Found May 01, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
JavaScript
AI Summary

A Chrome extension that captures a full-page screenshot and design details from any website, then uses user-provided AI services to generate a standardized DESIGN.md file describing the site's design system.

How It Works

1
🔍 Find Designpull

You discover this handy Chrome tool on GitHub that turns any website's look into a clear design guide.

2
🛠️ Add to Chrome

You simply load it into your Chrome browser like any other extension, and it's ready to use.

3
🌐 Pick a Website

You visit any website whose style, colors, and layout you want to capture and understand.

4
First Time Setup?
✅
Already Set Up

If you've connected an AI helper before, skip ahead feeling prepared.

➕
Connect AI Helper

Choose a free or paid AI service, enter your secure passcode, pick a brainy model, and save—it stays safe on your device.

5
✨ Click to Capture

You hit the big generate button, and it scrolls the whole page, snaps a picture, and sends it to your AI for magic.

🎉 Get Your Design Guide

In moments, you receive a complete DESIGN.md file packed with colors, fonts, layouts, brand tips, and more—ready to copy or download.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is designpull?

Designpull is a JavaScript Chrome extension that turns any website into a Google Stitch-compatible DESIGN.md file using AI vision. Visit a page, hit extract, and it scrolls full-page screenshots plus CSS tokens to your choice of Gemini, OpenAI, Claude, or Ollama—BYO API key, no backend needed. It outputs structured docs on colors, typography, layouts, brand voice, and Do's & Don'ts, skipping generic CSS dumps for real design intent.

Why is it gaining traction?

Stands out by blending visual AI analysis with precise tokens, detecting platforms like Webflow or Shopify, and generating semantic insights like photography style or coined brand concepts—far beyond basic extractors. One-click model switching, free Gemini tier, and local Ollama make it zero-cost to try, with easy setup via generate google api key links in docs. Copy or download ready-to-use markdown for AI coders like Copilot.

Who should use this?

Frontend devs reverse-engineering SaaS landing pages for clones, product teams documenting vendor UIs before integration, or indie builders analyzing competitor designs. Ideal for quick audits where you need layout patterns and voice without manual screenshots.

Verdict

Early maturity at 12 stars and 1.0% credibility score, but excellent README with API guides limits risks—load unpacked for prototyping. Solid for niche needs; low traffic suggests room for contributors on edge cases like infinite scroll.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.