Public DESIGN.md catalog
Browse a public catalog of DESIGN.md files covering named websites and brands. Each entry summarizes a design language that can be reused as reference material.
getdesign.md
getdesign.md is a DESIGN.md collection for AI coding agents. Explore public design-system analyses and request a private website reference by email.
Overview
getdesign.md is a DESIGN.md collection for AI coding agents. It curates independent design system analyses from popular websites and lets readers drop a reference into a project so an agent can follow an existing visual language instead of inventing one from scratch.
The site combines a public catalog of analyzed websites with a paid private-request flow. The public browsing experience focuses on website entries such as BMW, Airbnb, Airtable, Stripe, and Vercel, while the request flow offers a private DESIGN.md generated from a customer-chosen website and delivered by email.
Features
Browse and discover analyses
Filter and browse website analyses from the catalog, including a dedicated websites view and featured selections from the community.
AI-readable design references
Open individual analyses that describe visual patterns, tokens, and rules in a format built for AI coding agents.
Private website requests
Request a private DESIGN.md for a website and receive it by email without publishing it to the public catalog.
Light and dark theme previews
Preview both light and dark themes in the private request flow so the output can be reviewed as live HTML pages before use.
Template and add-on workflow
Use the Vibecoder kit option to get a working website template plus the DESIGN.md file, with optional add-ons for analytics, forms, SEO, AI features, auth, payments, uploads, localization, and deployment.
Use cases
Guide an AI build with a known design language
A developer wants an existing visual system for a client site or side project. They browse the catalog, pick a brand reference, and use the DESIGN.md file to steer the agent toward that style.
Create a private website reference
A founder wants their own site analyzed without publishing the result publicly. They submit a URL through the request flow and receive a private DESIGN.md by email.
Start from a template with bundled design guidance
A team wants a working starter instead of only a reference file. They choose the Vibecoder kit and use the included DESIGN.md together with the template code and add-ons.
Tune layout and UI details in prompt-driven workflows
A builder wants to make an AI-generated page feel closer to a target site’s typography, spacing, and visual system. They use the analysis pages as a reference while prompting their coding assistant.
Pros and Cons
Pros
- Provides a browsable collection of design-system analyses from recognizable websites.
- Separates public examples from private requested files, which keeps custom website analysis out of the public catalog.
- Frames DESIGN.md as an AI-readable reference for coding assistants, which fits prompt-driven UI implementation workflows.
- Includes both a standalone request flow and a template-based kit option, giving users two ways to work with DESIGN.md.
Cons
- The public catalog is descriptive rather than interactive; the source does not show editing, collaboration, or versioning tools for the files themselves.
- The site gives only partial detail about integrations and compatibility outside the AI tools mentioned in the request and kit flows.
FAQ
What is getdesign.md for?
It lets you browse public DESIGN.md files and related design-system analyses from popular websites, then use them as reference material for an AI coding agent.
Can I request a private DESIGN.md for my own website?
The request flow says it can analyze a requested website and deliver a private DESIGN.md file by email. The public catalog is separate from the private request flow.
How do people use a DESIGN.md file in practice?
The site indicates DESIGN.md files can be used in a prompt such as applying the design system across a site, and the Vibecoder kit includes the file as part of a working template. That points to use with AI coding tools that can read markdown files.
Is everything on the site public?
The public catalog is for browsing websites already analyzed. The request flow and pricing page both indicate private DESIGN.md delivery is separate and never published on the public landing page.
What tools does it work with?
The source does not list a full integration catalog. It does mention compatibility with AI chat tools and code editors such as ChatGPT, Claude, Gemini, Cursor, and VS Code in the context of the Vibecoder kit.
Quick Facts
- Category
- Developer Tool
- Primary use
- Design-system references for AI coding agents
- Source domain
- getdesign.md
- Public catalog
- Yes
- Private requests
- Yes
- Pricing signal
- Paid request flow and paid kit option
getdesign.md Alternatives
Refero MCP
Refero MCP for AI agents connects an MCP-compatible agent to Refero’s curated library of web and iOS product interfaces and user flows. It helps agents research real design patterns before generating UI, with access included in the Refero Pro plan.
AakarDev AI
AakarDev AI helps teams manage AI provider access, project-level setups, logs, and analytics from one dashboard. It supports BYOK workflows and lists providers including OpenAI, Google Gemini, Anthropic, Groq, Mistral AI, and Perplexity AI.
BookAI.chat
BookAI allows you to chat with your books using AI by simply providing the title and author.
Skills Janitor
Skills Janitor is a GitHub-hosted set of slash commands for auditing, tracking, and managing Claude Code and OpenAI Codex skills. It helps users find duplicates, broken links, and unused skills, then clean them up with self-contained commands.
FeelFish
FeelFish is a PC client for AI-assisted novel writing, designed to help fiction writers plan characters and settings, draft and revise long-form content, and manage story context. It includes a free tier and paid plans, with support for multiple large-model providers.
Benchspan
Benchspan is an AI agent security platform that discovers agents, blocks prompt injection and data exfiltration in real time, and supports pre-launch red teaming. It is aimed at teams running agents in production and includes Python and TypeScript SDKs.