Shadcn Ui logo

Shadcn Ui

CommunityPopular
jezweb
shadcn-ui

Install and configure shadcn/ui components for React projects. Guides component selection, installation order, dependency management, customisation with semantic tokens, and common UI recipes (forms, data tables, navigation, modals). Use after tailwind-theme-builder has set up the theme infrastructure, when adding components, building forms, creating data tables, or setting up navigation.

Overview

Publisherjezweb
Repositoryclaude-skills
Skill nameshadcn-ui
Stars
1K
Forks
102
Bundled files
2
LicenseMIT
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Shadcn Ui 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.
  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/jezweb/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/plugins/frontend/skills/shadcn-ui .claude/skills/shadcn-ui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shadcn Ui 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 Ui 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 Ui 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 Components

Add shadcn/ui components to a themed React project. This skill runs AFTER tailwind-theme-builder has set up CSS variables, ThemeProvider, and dark mode. It handles component installation, customisation, and combining components into working patterns.

Prerequisite: Theme infrastructure must exist (CSS variables, components.json, cn() utility). Use tailwind-theme-builder first if not set up.

Installation Order

Install components in dependency order. Foundation components first, then feature components:

Foundation (install first)

bash
pnpm dlx shadcn@latest add button
pnpm dlx shadcn@latest add input label
pnpm dlx shadcn@latest add card

Feature Components (install as needed)

bash
# Forms
pnpm dlx shadcn@latest add form        # needs: react-hook-form, zod, @hookform/resolvers
pnpm dlx shadcn@latest add textarea select checkbox switch

# Feedback
pnpm dlx shadcn@latest add toast        # needs: sonner
pnpm dlx shadcn@latest add alert badge

# Overlay
pnpm dlx shadcn@latest add dialog sheet popover dropdown-menu

# Data Display
pnpm dlx shadcn@latest add table        # for data tables, also: @tanstack/react-table
pnpm dlx shadcn@latest add tabs separator avatar

# Navigation
pnpm dlx shadcn@latest add navigation-menu command

External Dependencies

ComponentRequires
Formreact-hook-form, zod, @hookform/resolvers
Toastsonner
Data Table@tanstack/react-table
Commandcmdk
Date Pickerdate-fns (optional)

Install external deps separately: pnpm add react-hook-form zod @hookform/resolvers

Known Gotchas

These are documented corrections that prevent common bugs:

Radix Select — No Empty Strings

tsx
// Don't use empty string values
<SelectItem value="">All</SelectItem>           // BREAKS

// Use sentinel value
<SelectItem value="__any__">All</SelectItem>    // WORKS
const actual = value === "__any__" ? "" : value

React Hook Form — Null Values

tsx
// Don't spread {...field} — it passes null which Input rejects
<Input
  value={field.value ?? ''}
  onChange={field.onChange}
  onBlur={field.onBlur}
  name={field.name}
  ref={field.ref}
/>

Lucide Icons — Tree-Shaking

tsx
// Don't use dynamic import — icons get tree-shaken in production
import * as LucideIcons from 'lucide-react'
const Icon = LucideIcons[iconName]  // BREAKS in prod

// Use explicit map
import { Home, Users, Settings, type LucideIcon } from 'lucide-react'
const ICON_MAP: Record<string, LucideIcon> = { Home, Users, Settings }
const Icon = ICON_MAP[iconName]

Dialog Width Override

tsx
// Default sm:max-w-lg won't be overridden by max-w-6xl
<DialogContent className="max-w-6xl">       // DOESN'T WORK

// Use same breakpoint prefix
<DialogContent className="sm:max-w-6xl">    // WORKS

Customising Components

shadcn components use semantic CSS tokens from your theme. To customise:

Variant extension

Add custom variants by editing the component file in src/components/ui/:

tsx
// button.tsx — add a "brand" variant
const buttonVariants = cva("...", {
  variants: {
    variant: {
      default: "bg-primary text-primary-foreground",
      brand: "bg-brand text-brand-foreground hover:bg-brand/90",
      // ... existing variants
    },
  },
})

Colour overrides

Use semantic tokens from your theme — never raw Tailwind colours:

tsx
// Don't use raw colours
<Button className="bg-blue-500">             // WRONG

// Use semantic tokens
<Button className="bg-primary">              // RIGHT
<Card className="bg-card text-card-foreground">  // RIGHT

Workflow

Step 1: Assess Needs

Determine what UI patterns the project needs:

NeedComponents
Forms with validationForm, Input, Label, Select, Textarea, Button, Toast
Data display with sortingTable, Badge, Pagination
Admin CRUD interfaceDialog, Form, Table, Button, Toast
Marketing/landing pageCard, Button, Badge, Separator
Settings/preferencesTabs, Form, Switch, Select, Toast
NavigationNavigationMenu (desktop), Sheet (mobile), ModeToggle

Step 2: Install Components

Install foundation first, then feature components for the identified needs. Use the commands above.

Step 3: Build Recipes

Combine components into working patterns. See references/recipes.md for complete working examples:

  • Contact Form — Form + Input + Textarea + Button + Toast
  • Data Table — Table + Column sorting + Pagination + Search
  • Modal CRUD — Dialog + Form + Button
  • Navigation — Sheet + NavigationMenu + ModeToggle
  • Settings Page — Tabs + Form + Switch + Select + Toast

Step 4: Customise

Apply project-specific colours and variants using semantic tokens from the theme.

Reference Files

WhenRead
Choosing components, install commands, propsreferences/component-catalogue.md
Building complete UI patternsreferences/recipes.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 Ui AI skill do?

Install and configure shadcn/ui components for React projects. Guides component selection, installation order, dependency management, customisation with semantic tokens, and common UI recipes (forms, data tables, navigation, modals). Use after tailwind-theme-builder has set up the theme infrastructure, when adding components, building forms, creating data tables, or setting up navigation.

Why use Shadcn Ui on TypingMind?

Because you install it once and use it with any model. Shadcn Ui 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 Ui in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jezweb/claude-skills/tree/main/plugins/frontend/skills/shadcn-ui. 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 Ui?

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 Ui?

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

Is the Shadcn Ui AI skill free?

Yes. It is published on GitHub by jezweb under the MIT license. 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 👇