Shadcn logo

Shadcn

Community
pedronauck
shadcn

Best practices for building UI components with shadcn/ui. Use when creating, customizing, or styling components with shadcn, working with Radix UI primitives, implementing design tokens, or following compound component patterns.

Overview

Publisherpedronauck
Repositoryskills
Skill nameshadcn
Stars
635
Forks
89
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by pedronauck on GitHub. Read the source before you install it.

Installation

Install the Shadcn AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pedronauck/skills/tree/main/skills/curated/shadcn
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pedronauck/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/curated/shadcn .claude/skills/shadcn
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shadcn in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Shadcn on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Shadcn is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Shadcn UI Developer Guide

This skill provides guidelines, patterns, and best practices for working with shadcn/ui components in this project.

Quick Start

  1. Core Patterns: Read references/patterns.md for comprehensive styling, theming, and component patterns.
  2. Tailwind Integration: For Tailwind CSS patterns, use the tailwindcss skill.

Core Philosophy

  • Ownership: Shadcn is copy-paste, not a dependency - you own the code.
  • Customization: Components are meant to be modified for your needs.
  • Accessibility: Built on Radix UI primitives for proper accessibility.
  • Flexibility: Styled with Tailwind CSS for easy customization.

Critical: Design Token Usage

Always use design system tokens for theme switching compatibility:

Required tokens:

  • Backgrounds: bg-background, bg-card, bg-muted, bg-popover
  • Text: text-foreground, text-muted-foreground, text-card-foreground
  • Borders: border-border, border-input, border-ring
  • Actions: bg-primary text-primary-foreground, bg-secondary text-secondary-foreground
  • States: bg-destructive text-destructive-foreground, bg-accent text-accent-foreground

Never use explicit colors like bg-white, text-black, border-gray-200 - they break theme switching.

Common Tasks

Adding Components

Use the CLI to add components, then customize as needed:

bash
npx shadcn@latest add button card dialog

Extending Components

Add custom props and variants while preserving accessibility:

typescript
export interface ButtonProps
  extends React.ButtonHTMLAttributes<HTMLButtonElement>,
    VariantProps<typeof buttonVariants> {
  loading?: boolean
}

const Button = React.forwardRef<HTMLButtonElement, ButtonProps>(
  ({ className, variant, size, loading, children, ...props }, ref) => {
    return (
      <button
        className={cn(buttonVariants({ variant, size, className }))}
        ref={ref}
        disabled={loading || props.disabled}
        {...props}
      >
        {loading && <Loader2 className="mr-2 h-4 w-4 animate-spin" />}
        {children}
      </button>
    )
  }
)

Compound Components

Always use separate exports, NOT namespaced properties:

tsx
// CORRECT
export const CardTech = CardTechRoot;
export const CardTechHeader = CardHeader;
export const CardTechTitle = CardTitle;
export const CardTechContent = CardContent;

// WRONG - Do not use
export const CardTech = Object.assign(CardTechRoot, {
  Header: CardHeader,
  Content: CardContent,
});

Preserving Accessibility

Never remove Radix UI's accessibility attributes:

tsx
<Dialog>
  <DialogTrigger asChild>
    <Button>Open Dialog</Button>
  </DialogTrigger>
  <DialogContent>
    <DialogHeader>
      <DialogTitle>Accessible Title</DialogTitle>
      <DialogDescription>
        This description helps screen readers understand the dialog's purpose
      </DialogDescription>
    </DialogHeader>
  </DialogContent>
</Dialog>

Theming

Use CSS variables for all color values in globals.css:

css
@layer base {
  :root {
    --success: 142 76% 36%;
    --success-foreground: 355 100% 100%;
  }

  .dark {
    --success: 142 76% 46%;
    --success-foreground: 142 76% 10%;
  }
}

Validation Checklist

Before finishing a task involving shadcn/ui:

  • Verify all colors use design tokens, not explicit values.
  • Ensure accessibility attributes from Radix UI are preserved.
  • Test keyboard navigation works correctly.
  • Use separate exports for compound components (not namespaced).
  • Run type checks (pnpm run typecheck) and tests (pnpm run test).

For comprehensive patterns, component examples, and detailed guidelines, read references/patterns.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Shadcn AI skill do?

Best practices for building UI components with shadcn/ui. Use when creating, customizing, or styling components with shadcn, working with Radix UI primitives, implementing design tokens, or following compound component patterns.

Why use Shadcn on TypingMind?

Because you install it once and use it with any model. Shadcn is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Shadcn in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pedronauck/skills/tree/main/skills/curated/shadcn. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Shadcn?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Shadcn?

As many as you like. As long as a model supports skills, you can use Shadcn with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Shadcn AI skill free?

It is published on GitHub by pedronauck. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇