
awesome-design-skills-registry
Pull and use curated DESIGN.md and SKILL.md files for AI-powered design systems and agentic workflows
- Installs
- 149
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/reason-machines/design-skills --skill awesome-design-skills-registry- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads awesome-design-skills-registry automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Awesome Design Skills Registry
Skill by ara.so — Design Skills collection.
Overview
awesome-design-skills is a curated registry of 67 design system skill files optimized for AI-powered agentic tools (Claude Code, Cursor, Codex, Google Stitch). Each skill ships as a folder containing:
SKILL.md— AI-agent instructions (tokens, component rules, accessibility constraints, quality gates)DESIGN.md— Human-readable design intent, rationale, and implementation notes
Pull any skill into your project with a single command using the TypeUI CLI.
Official registry: https://typeui.sh/design-skills
Installation
Install TypeUI CLI
The TypeUI CLI is the recommended way to pull design skills:
npx typeui.sh pull <slug>
No installation required — npx runs the latest version directly.
Alternatively, install globally:
npm install -g typeui.sh
Core Commands
Pull a Design Skill
Pull a specific design skill by slug:
npx typeui.sh pull glassmorphism
This creates a design-skills/glassmorphism/ folder in your project with:
SKILL.md(AI agent instructions)DESIGN.md(human documentation)
List All Available Skills
Browse all 67 skills interactively:
npx typeui.sh list
Outputs a filterable list with slugs, descriptions, and preview URLs.
Pull Multiple Skills
Pull multiple skills in one command:
npx typeui.sh pull brutalism glassmorphism claymorphism
Preview Before Pulling
Visit the web gallery to preview styles before pulling:
# Open in browser
open https://typeui.sh/design-skills
Or preview a specific skill:
open https://typeui.sh/design-skills/glassmorphism
Available Design Skills (67 Total)
Style Categories
Modern & Minimalist:
clean— Clean, minimal design with breathing roomflat— Flat design with bold colors and simple shapescontemporary— Modern, balanced, accessibleelegant— Refined typography and subtle interactions
Expressive & Creative:
brutalism— Bold, raw, unapologetic designglassmorphism— Frosted glass effects with depthclaymorphism— Soft, tactile, 3D elementsgradient— Vibrant gradients and smooth color transitionsartistic— Asymmetric layouts and creative freedomdoodle— Hand-drawn, playful, sketch-likecolorful— Vibrant, saturated color palettes
Professional & Enterprise:
enterprise— Conservative, scalable, accessiblecorporate— Professional, trustworthy, structureddashboard— Data-dense interfaces with clear hierarchyapplication— Functional, utilitarian UI patterns
Specialized:
agentic— AI-first design patterns for agentic workflowsclaude— Claude Code-optimized design tokensbento— Grid-based card layoutslevels— Gaming-inspired progression UIcafe— Warm, inviting, community-focused
Full list of 67 skills: https://typeui.sh/design-skills
Using Design Skills with AI Agents
Claude Code (Claude Desktop)
- Pull the skill into your project:
npx typeui.sh pull agentic
- Reference it in your conversation:
@design-skills/agentic/SKILL.md
Build a dashboard using this design system
- Claude Code reads
SKILL.mdand generates code following:- Color tokens
- Typography scale
- Component patterns
- Accessibility rules
- Quality gates
Cursor
- Pull the skill:
npx typeui.sh pull glassmorphism
- Add to
.cursorrulesor reference directly:
Use the design system defined in design-skills/glassmorphism/SKILL.md
- Cursor applies the design tokens when generating UI code.
Codex / GitHub Copilot
- Pull the skill:
npx typeui.sh pull brutalism
- Open
SKILL.mdin your editor alongside your code files - Copilot reads context and suggests components matching the design system
File Structure
After pulling a skill, your project structure:
your-project/
├── design-skills/
│ ├── glassmorphism/
│ │ ├── SKILL.md # AI agent instructions
│ │ └── DESIGN.md # Human documentation
│ ├── brutalism/
│ │ ├── SKILL.md
│ │ └── DESIGN.md
│ └── claymorphism/
│ ├── SKILL.md
│ └── DESIGN.md
├── src/
└── package.json
Anatomy of SKILL.md
A typical SKILL.md file contains:
1. Brand & Mission
## Brand & Mission
A design system focused on glass-like surfaces with depth and blur.
2. Color Tokens
## Color Palette
- Primary: hsl(220, 90%, 56%)
- Background: hsl(220, 20%, 10%)
- Surface: hsl(220, 20%, 16%) with 40% opacity
- Border: hsl(0, 0%, 100%) with 10% opacity
3. Typography
## Typography
- Font family: Inter, system-ui, sans-serif
- Scale: 12px, 14px, 16px, 20px, 24px, 32px, 48px
- Line height: 1.5 for body, 1.2 for headings
4. Component Patterns
## Button
- Background: rgba(255, 255, 255, 0.1)
- Backdrop-filter: blur(10px)
- Border: 1px solid rgba(255, 255, 255, 0.2)
- Padding: 12px 24px
- Border-radius: 12px
5. Accessibility Rules
## Accessibility
- WCAG 2.2 AA compliant contrast ratios (4.5:1 for text)
- Keyboard-first navigation (Tab, Enter, Escape)
- Focus visible: 2px solid ring with 2px offset
- ARIA labels on all interactive elements
6. Quality Gates
## Quality Gates
- [ ] All interactive elements keyboard-accessible
- [ ] Color contrast passes WCAG AA
- [ ] Focus states visible
- [ ] Loading states for async actions
- [ ] Error messages actionable and clear
DESIGN.md Overview
DESIGN.md is the human companion to SKILL.md. It includes:
- Design Overview: High-level visual direction
- Rationale: Why these tokens/patterns exist
- References: Links to inspiration (Dribbble, Behance, etc.)
- Maintenance Notes: How to keep the system aligned
Example snippet:
## Design Overview
Glassmorphism creates depth through layered, semi-transparent surfaces.
Inspired by Apple's Big Sur and Microsoft Fluent Design.
## Rationale
- Blur effects create visual hierarchy without heavy shadows
- Translucency allows background content to remain contextually visible
- Works well in dark mode with reduced eye strain
Code Examples
React Component Using Glassmorphism Skill
import React from 'react';
export function GlassCard({ title, children }: { title: string; children: React.ReactNode }) {
return (
<div
className="glass-card"
style={{
background: 'rgba(255, 255, 255, 0.1)',
backdropFilter: 'blur(10px)',
border: '1px solid rgba(255, 255, 255, 0.2)',
borderRadius: '12px',
padding: '24px',
}}
>
<h2 style={{ fontSize: '24px', fontWeight: 600, marginBottom: '16px' }}>
{title}
</h2>
{children}
</div>
);
}
Tailwind CSS Config for Brutalism Skill
// tailwind.config.js
module.exports = {
theme: {
extend: {
colors: {
primary: '#FF6B00',
background: '#FFFFFF',
text: '#000000',
border: '#000000',
},
fontFamily: {
sans: ['Space Grotesk', 'monospace'],
display: ['Space Mono', 'monospace'],
},
borderWidth: {
DEFAULT: '3px',
thick: '6px',
},
boxShadow: {
brutal: '8px 8px 0 0 #000000',
},
},
},
};
CSS Variables from Enterprise Skill
:root {
/* Colors */
--color-primary: hsl(210, 100%, 50%);
--color-background: hsl(0, 0%, 100%);
--color-surface: hsl(210, 20%, 98%);
--color-border: hsl(210, 20%, 88%);
--color-text: hsl(210, 20%, 14%);
/* Typography */
--font-sans: 'Inter', system-ui, sans-serif;
--font-size-sm: 14px;
--font-size-base: 16px;
--font-size-lg: 18px;
--font-size-xl: 24px;
/* Spacing */
--spacing-xs: 4px;
--spacing-sm: 8px;
--spacing-md: 16px;
--spacing-lg: 24px;
--spacing-xl: 32px;
/* Border radius */
--radius-sm: 4px;
--radius-md: 8px;
--radius-lg: 12px;
}
Common Patterns
Pattern 1: Multi-Skill Projects
Use multiple skills for different sections:
# Landing page uses Glassmorphism
npx typeui.sh pull glassmorphism
# Dashboard uses Enterprise
npx typeui.sh pull enterprise
# Marketing uses Gradient
npx typeui.sh pull gradient
Reference each skill in the appropriate component folder:
src/
├── landing/ # Uses design-skills/glassmorphism/SKILL.md
├── dashboard/ # Uses design-skills/enterprise/SKILL.md
└── marketing/ # Uses design-skills/gradient/SKILL.md
Pattern 2: Custom Overrides
Pull a base skill and override specific tokens:
npx typeui.sh pull clean
Edit design-skills/clean/SKILL.md:
## Color Palette (Customized)
- Primary: hsl(280, 90%, 56%) /* Changed from blue to purple */
- Background: hsl(0, 0%, 100%)
- Text: hsl(0, 0%, 10%)
Pattern 3: Git Workflow
Commit design skills to your repository:
git add design-skills/
git commit -m "Add glassmorphism and enterprise design skills"
git push
Now all team members and AI agents reference the same design system.
Pattern 4: Monorepo Setup
Pull skills at the root or per package:
# Root-level (shared across packages)
npx typeui.sh pull enterprise
# Package-specific
cd packages/web
npx typeui.sh pull glassmorphism
cd ../mobile
npx typeui.sh pull friendly
Configuration
Custom Output Directory
Specify a custom directory for design skills:
npx typeui.sh pull glassmorphism --output ./docs/design-system
Environment Variables
If you fork the TypeUI CLI or self-host the registry:
# .env
TYPEUI_REGISTRY_URL=https://your-registry.com/api
Then pull from your custom registry:
export TYPEUI_REGISTRY_URL=https://your-registry.com/api
npx typeui.sh pull custom-skill
Troubleshooting
Skill Not Found
If a skill slug is invalid:
npx typeui.sh pull nonexistent-skill
# Error: Skill "nonexistent-skill" not found in registry
Solution: List available skills:
npx typeui.sh list
Or browse at https://typeui.sh/design-skills
Network Timeout
If the registry is unreachable:
npx typeui.sh pull glassmorphism
# Error: Request timeout
Solution: Check your internet connection or try again later.
Permission Denied
If npx cannot create the design-skills/ folder:
npx typeui.sh pull glassmorphism
# Error: EACCES: permission denied, mkdir 'design-skills'
Solution: Run with elevated permissions or change directory ownership:
sudo npx typeui.sh pull glassmorphism
Or:
sudo chown -R $USER:$USER .
npx typeui.sh pull glassmorphism
Stale Cache
If you're seeing outdated skill content:
Solution: Clear npx cache:
npx clear-npx-cache
npx typeui.sh pull glassmorphism
Or force-reinstall:
npm install -g typeui.sh@latest
typeui.sh pull glassmorphism
Advanced Usage
Programmatic Access
If you're building tooling that integrates the registry:
import { fetch } from 'node-fetch';
async function fetchSkill(slug) {
const response = await fetch(`https://typeui.sh/api/skills/${slug}`);
const data = await response.json();
return data;
}
const glassmorphism = await fetchSkill('glassmorphism');
console.log(glassmorphism.skill_md); // SKILL.md content
console.log(glassmorphism.design_md); // DESIGN.md content
Creating Custom Skills
Fork the registry and create your own skill:
git clone https://github.com/bergside/awesome-design-skills.git
cd awesome-design-skills/skills
mkdir my-custom-skill
Create SKILL.md and DESIGN.md:
<!-- skills/my-custom-skill/SKILL.md -->
# My Custom Skill
## Brand & Mission
A custom design system for internal tools.
## Color Palette
- Primary: hsl(180, 80%, 50%)
- Background: hsl(0, 0%, 98%)
Submit a pull request to add your skill to the registry.
Integration with Other Tools
Storybook
Document design tokens in Storybook:
// .storybook/preview.tsx
import { SKILL_MD } from '../design-skills/glassmorphism/SKILL.md';
export const parameters = {
docs: {
page: () => <Markdown>{SKILL_MD}</Markdown>,
},
};
Figma Variables
Export design tokens from SKILL.md to Figma variables:
# Use a community plugin or script
npx figma-export design-skills/glassmorphism/SKILL.md
Design Linter
Lint your codebase against SKILL.md rules:
npx design-lint --skill design-skills/enterprise/SKILL.md src/
(Example tool — replace with your preferred linter)
Best Practices
- Commit design skills to version control — Keep design and code in sync
- Reference SKILL.md in AI agent prompts — Use
@design-skills/slug/SKILL.mdin Cursor/Claude - Update DESIGN.md when you override tokens — Document why you diverged
- Use one skill per product area — Landing (Glassmorphism), Dashboard (Enterprise), Docs (Clean)
- Pull skills early in the project — Establish design foundations before building components
Resources
- Registry: https://typeui.sh/design-skills
- GitHub: https://github.com/bergside/awesome-design-skills
- CLI: https://github.com/bergside/typeui.sh
- Awesome Badge:
License
MIT License — See LICENSE
When to use this skill:
- You need a design system for AI agents (Claude Code, Cursor, Codex)
- You want consistent design tokens across your project
- You're building with agentic workflows and need design constraints
- You want to preview and pull pre-built design systems quickly
Quick reference:
# Pull a skill
npx typeui.sh pull glassmorphism
# List all skills
npx typeui.sh list
# Preview in browser
open https://typeui.sh/design-skills
FAQ
What does the awesome-design-skills-registry skill do?
Pull and use curated DESIGN.md and SKILL.md files for AI-powered design systems and agentic workflows
How do I install awesome-design-skills-registry?
Run npx skills add https://github.com/reason-machines/design-skills --skill awesome-design-skills-registry in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/awesome-design-skills-registry/ (personal) or .claude/skills/awesome-design-skills-registry/ (project).
Which AI agents can use awesome-design-skills-registry?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is awesome-design-skills-registry safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains awesome-design-skills-registry?
It is published by reason-machines in reason-machines/design-skills. It has 149 recorded installs.
More from reason-machines/design-skills
awesome-claude-design
reason-machines/design-skills
Open the skill to read its SKILL.md instructions.
design-md-format
reason-machines/design-skills
Create and validate DESIGN.md files that give AI coding agents structured understanding of design systems through machine-readable tokens and human-readable rationale.
open-codesign-ai-design
reason-machines/design-skills
Use Open CoDesign to generate prototypes, slides, and PDFs from prompts with Claude, GPT, Gemini, or local models
open-design-ai-prototyping
reason-machines/design-skills
Open the skill to read its SKILL.md instructions.
diagram-design-editorial
reason-machines/design-skills
Create editorial-quality diagrams in HTML + SVG matching your brand — architecture, flowcharts, sequences, timelines, quadrants, and 9 more types.
keychron-hardware-design
reason-machines/design-skills
Access and work with Keychron keyboard and mouse industrial design files (STEP, DXF, DWG, PDF) for 135+ models to create compatible accessories, remixes, and modifications.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available