List of awesome design md skill files for agentic tools like Claude, Codex, and Gemini
# Awesome Design Skills [](https://awesome.re) > A curated registry of design system skill files for AI-powered agentic tools like [Claude Code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview), [Gemini](https://www.gemini.com/), [Codex](https://openai.com/index/codex/), and others. Pull any skill into your project with a single command. Each skill is a `SKILL.md` file containing design tokens, component guidelines, accessibility rules, and implementation-ready specifications that instruct AI agents to follow a specific design system when building interfaces. **[Preview all design skills on typeui.sh](https://typeui.sh/design-skills)** Built and maintained by [Bergside](https://github.com/bergside). Powered by [typeui.sh](https://github.com/bergside/typeui.sh). ## Contents - [Quick Start](#quick-start) - [What is a Design Skill?](#what-is-a-design-skill) - [Design Skills](#design-skills) - [Usage](#usage) - [Registry Structure](#registry-structure) - [Contributing](#contributing) - [License](#license) ## Quick Start Pull any design skill directly into your project using [typeui.sh](https://github.com/bergside/typeui.sh): ```bash npx typeui.sh pull <slug> ``` For example, to pull the Glassmorphism design skill: ```bash npx typeui.sh pull glassmorphism ``` Or browse all available skills interactively: ```bash npx typeui.sh list ``` ## What is a Design Skill? A design skill is a `SKILL.md` file that acts as a set of instructions for AI agents and LLMs. Each file contains: - **Brand & mission** — the design philosophy and visual identity - **Style foundations** — typography scale, color palette, spacing system - **Component families** — buttons, inputs, cards, modals, navigation, and more - **Accessibility rules** — WCAG 2.2 AA compliance, keyboard-first interactions - **Writing tone** — content and voice guidelines - **Do/Don't rules** — explicit patterns and anti-patterns - **Quality gate
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.