Moai Library Shadcn logo

Moai Library Shadcn

Organization
Asymmetric-al
moai-library-shadcn

Build UI with Core's shadcn/Base UI system. Use for selecting, installing, composing, or customizing shadcn/ui, registry items, themes, and wrappers. Always preserve exact style `base-maia`, Zinc-oriented semantic CSS-variable tokens, and Base UI primitives. Do not use to switch styles, run `shadcn init`, or introduce Radix/React Aria. Pair with `packages/ui/AGENTS.md`.

Overview

PublisherAsymmetric-al
Repositorycore
Skill namemoai-library-shadcn
Stars
383
Forks
7
Bundled files
1
LicenseAGPL-3.0
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 Asymmetric-al on GitHub. Read the source before you install it.

Installation

Install the Moai Library 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.
  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/Asymmetric-al/core.git /tmp/core
mkdir -p .claude/skills
cp -r /tmp/core/docs/ai/skills/moai-library-shadcn .claude/skills/moai-library-shadcn
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Moai Library 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 Moai Library 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 Moai Library 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.

This repository (Asymmetric-al/core)

These repo-owned sections are intentionally kept on top of the vendored shadcn skill. If upstream refreshes replace this file, reconcile this overlay before running bun run skills:sync.

Triggers

  • Use for selecting, installing, composing, or customizing shadcn/ui, registry items, themes, and wrappers in this repo.
  • Use together with packages/ui/AGENTS.md and docs/ai/rules/frontend.md.
  • Do not use to switch styles, run shadcn init / shadcn create, or introduce Radix or React Aria. Never run shadcn init. Do not switch Core to base-nova, base-luma, base-mira, base-rhea, base-sera, base-vega, base-lyra, a Radix-based style, or a React Aria-based style.

Workflow

  1. Read packages/ui/components.json and confirm style: "base-maia", tailwind.baseColor: "zinc", tailwind.cssVariables: true.
  2. Run bunx shadcn@latest info --json from packages/ui (never from an app).
  3. Search existing @asym/ui components before adding anything new.
  4. For registry or generated components, inspect CLI output, adapt to Maia, and review the full diff. Never --overwrite without reviewing customizations.
  5. Use Base UI render (not Radix asChild). Prefer semantic tokens over literal zinc-* or hardcoded colors.
  6. Verify with existing shadcn guardrails and browser evidence when visible.

Checklist

  • Exact base-maia / Zinc / CSS variables remain unchanged
  • Shared ownership stays in packages/ui
  • Registry output adapted to Core tokens, radii, and primitives
  • No shadcn init, preset-switch, Radix, or React Aria
  • Overlay reconciled before bun run skills:sync

shadcn/ui Design System - Skill

Name: moai-library-shadcn Purpose: Build consistent, accessible UI using shadcn/ui components, tokens, and composable primitives. Use this skill whenever selecting, installing, composing, or customizing shadcn/ui in this repo.

Applies when: Working with shadcn/ui components, Tailwind tokens/themes, registry items, or component wrappers. Do not use when: Switching shadcn styles, running shadcn init / shadcn create, or introducing Radix / React Aria. Core UI is always Base UI + exact base-maia; pair this skill with packages/ui/AGENTS.md. Use base-ui for primitive API details after this skill.

Rules

  • Docs first: Start with reference-links.md, then open the exact component doc before editing.
  • Copied-in code is first-party: Treat components/ui/* as owned project code with stable conventions.
  • Prefer install over reinvention: Use CLI/registry install paths for base components, then customize in wrappers.
  • Behavior primitives stay intact: Keep accessibility and keyboard behavior from the Base UI-backed internals (this repo is Base UI only).
  • Tokens over one-offs: Centralize color, radius, spacing, and typography; avoid hardcoded one-off styles.
  • Composable APIs: Keep props minimal, use Base UI's render prop intentionally (no asChild here), and avoid boolean-prop explosion.
  • Interoperability guardrail: If mixing with Base UI primitives, document the boundary and keep one clear owner per interaction.

Workflow

  1. Check whether an existing component already solves the need in components/ui/*.
  2. Open the relevant docs from reference-links.md.
  3. Choose install path:
    • CLI/registry install for standard components and blocks.
    • Manual composition only when customization requires it.
  4. Compose app-specific wrappers outside components/ui/*.
  5. Verify keyboard, focus, labels/descriptions, and light/dark behavior.
  6. Run scoped quality gates for changed packages.

Checklists

Implementation checklist

  • Existing shadcn component evaluated before creating new primitive
  • Token-based styling used (no unnecessary arbitrary values)
  • cn() and variants are consistent with existing patterns
  • render prop and composition semantics are correct
  • a11y behavior (focus, keyboard, ARIA) preserved

Review checklist

  • No duplicate component variants that should be shared
  • Wrapper components are outside components/ui/*
  • Forms include labels, help text, and error messaging
  • Any Base UI crossover is explicit and justified

Minimal examples

Reuse existing primitive

tsx
import { Button } from "@/components/ui/button";

export function Actions() {
  return (
    <div className="flex gap-2">
      <Button>Save</Button>
      <Button variant="secondary">Cancel</Button>
    </div>
  );
}

Extend in wrapper layer

tsx
import { Button } from "@/components/ui/button";

type LoadingButtonProps = React.ComponentProps<typeof Button> & {
  loading?: boolean;
};

export function LoadingButton({
  loading,
  children,
  ...props
}: LoadingButtonProps) {
  return (
    <Button disabled={loading} {...props}>
      {children}
    </Button>
  );
}

Additional resources

Common mistakes / pitfalls

  • Editing copied-in primitives when a thin wrapper is enough
  • Ignoring docs updates and relying on stale memory
  • Mixing primitive systems inside one component without clear ownership
  • Breaking keyboard/focus behavior while styling

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 Moai Library Shadcn AI skill do?

Build UI with Core's shadcn/Base UI system. Use for selecting, installing, composing, or customizing shadcn/ui, registry items, themes, and wrappers. Always preserve exact style `base-maia`, Zinc-oriented semantic CSS-variable tokens, and Base UI primitives. Do not use to switch styles, run `shadcn init`, or introduce Radix/React Aria. Pair with `packages/ui/AGENTS.md`.

Why use Moai Library Shadcn on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Asymmetric-al/core/tree/develop/docs/ai/skills/moai-library-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 Moai Library 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 Moai Library Shadcn?

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

Is the Moai Library Shadcn AI skill free?

Yes. It is published on GitHub by Asymmetric-al under the AGPL-3.0 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 👇