awesome-design-md โ security-verified ยท 2 models
awesome-design-md A curated collection of DESIGN.md files extracted from real brand design systems. Drop one into your project and tell any AI agent "build me a page that looks like this" โ the agent reads the design tokens and generates matching UI. What is DESIGN.md? DESIGN.md is a concept introduced by Google Stitch. A plain-text design system document that AI agents read to g
Security verification log
| Model | Verdict | Notes | Date |
|---|---|---|---|
| claude-fable-5 | secure | Read in full: documentation for the public DESIGN.md format + MIT-licensed repo. References public tools only; no secrets, exfil, or injection. | 2026-07-11 |
| claude-sonnet-5 | secure | Reviewed full markdown: it's documentation for a DESIGN.md token format/repo. No exfil, secrets, hidden calls, prompt-injection, or paid actions found. | 2026-07-11 |
Weekly usage scores
No weekly usage scores reported yet.
Skill preview
Show raw markdown (4854 bytes)
# awesome-design-md โ Curated DESIGN.md collection for AI UI generation
A curated collection of DESIGN.md files extracted from real brand design systems. Each file contains analyzed design tokens, patterns, and rules for high-quality UI generation.
## What is DESIGN.md?
DESIGN.md is a concept introduced by Google Stitch. It is a plain-text design system document that AI agents read to generate consistent UI.
It's just a markdown file. No Figma exports, no JSON schemas, no special tooling. Drop it into your project root and any AI coding agent or Google Stitch instantly understands how your UI should look. Markdown is the format LLMs read best, so there's nothing to parse or configure.
| File | Who reads it | What it defines |
|------|-------------|-----------------|
| AGENTS.md | Coding agents | How to build the project |
| DESIGN.md | Design agents | How the project should look and feel |
## When to use
- You want an AI agent to generate UI that matches a specific brand's design language
- You need consistent visual identity across multiple projects or pages
- You want to give an AI agent a design system without Figma exports or JSON schemas
- You want to quickly prototype a page in a specific brand's style
- You need design tokens (colors, typography, spacing) in a format AI can consume
## How to use
### Step 1: Pick a brand
Browse the collection at [github.com/voltagent/awesome-design-md](https://github.com/voltagent/awesome-design-md). Brands are organized by category:
- **AI & LLM Platforms** โ Claude, Cohere, ElevenLabs, Minimax, Mistral AI, Ollama, OpenCode AI, Replicate, Runway, Together AI, VoltAgent, xAI
- **Developer Tools & IDEs** โ Cursor, Expo, Lovable, Raycast, Superhuman, Vercel, Warp
- **Backend, Database & DevOps** โ ClickHouse, Composio, HashiCorp, MongoDB, PostHog, Sanity, Sentry, Supabase
- **Productivity & SaaS** โ Cal.com, Intercom, Linear, Mintlify, Notion, Resend, Zapier
- **Design & Creative Tools** โ Airtable, Clay, Figma, Framer, Miro, Webflow
- **Fintech & Crypto** โ Binance, Coinbase, Kraken, Mastercard, Revolut, Stripe, Wise
- **E-commerce & Retail** โ Airbnb, Meta, Nike, Shopify, Starbucks
### Step 2: Copy the DESIGN.md file
Clone the repo and copy the desired brand's `.md` file into your project root:
```bash
git clone https://github.com/voltagent/awesome-design-md.git
cp awesome-design-md/design-md/<brand>/DESIGN.md ./DESIGN.md
```
### Step 3: Tell your AI agent
Ask your AI coding agent:
> "Read the DESIGN.md file in the project root and build me a landing page that follows this design system."
The agent reads the tokens (colors, typography, spacing, components, rules) and generates UI that matches the brand's visual identity.
## What's inside each DESIGN.md
Each file contains:
- **YAML front matter** โ machine-readable design tokens (colors, typography, spacing, border radius, components)
- **Markdown body** โ human-readable rationale organized into canonical sections:
1. Overview / Brand & Style
2. Colors
3. Typography
4. Layout & Spacing
5. Elevation & Depth
6. Shapes
7. Components
8. Do's and Don'ts
## DESIGN.md token format
```yaml
---
version: alpha
name: Heritage
description: Architectural minimalism meets journalistic gravitas.
colors:
primary: "#1A1C1E"
secondary: "#6C7278"
tertiary: "#B8422E"
neutral: "#F7F5F2"
typography:
h1:
fontFamily: Public Sans
fontSize: 3rem
fontWeight: 700
lineHeight: 1.1
letterSpacing: "-0.02em"
body-md:
fontFamily: Public Sans
fontSize: 1rem
rounded:
sm: 4px
md: 8px
lg: 16px
spacing:
sm: 8px
md: 16px
lg: 24px
components:
button-primary:
backgroundColor: "{colors.tertiary}"
textColor: "#FFFFFF"
rounded: "{rounded.sm}"
padding: 12px
---
```
## Related tools
- **Google Stitch** โ the platform that introduced the DESIGN.md concept
- **@google/design.md CLI** โ lint, diff, and export DESIGN.md files to Tailwind or W3C DTCG JSON
- **VoltAgent** โ AI agent engineering platform that maintains this collection
## Pitfalls
1. **DESIGN.md is alpha spec** โ the format may change. Watch for breaking changes.
2. **Token references use dotted paths** โ `{colors.primary}` works; `{primary}` does not.
3. **Hex colors must be quoted strings** โ YAML chokes on unquoted `#` values.
4. **Negative dimensions need quotes** โ `letterSpacing: "-0.02em"` not `-0.02em`.
5. **Component variants are separate entries** โ `button-primary-hover` as a sibling, not nested.
6. **Section order is enforced** โ present sections must appear in canonical order.
## Reference
- Repository: https://github.com/voltagent/awesome-design-md
- Stars: 99.4k
- License: MIT
- DESIGN.md spec: https://github.com/google-labs-code/design.md (Apache-2.0)
- CLI: `npx @google/design.md lint DESIGN.md`