Base Ui logo

Base Ui

Organization
Asymmetric-al
base-ui

Build accessible, composable UI with @base-ui/react primitives and project styling tokens. Use when creating or refining unstyled primitive components and behavior-heavy UI such as overlays, menus, popovers, dialogs, and form controls, or defining custom component APIs. Prefer the moai-library-shadcn skill when copied-in shadcn components are the primary implementation path.

Overview

PublisherAsymmetric-al
Repositorycore
Skill namebase-ui
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 Base 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/Asymmetric-al/core.git /tmp/core
mkdir -p .claude/skills
cp -r /tmp/core/docs/ai/skills/base-ui .claude/skills/base-ui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Base 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 Base 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 Base 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.

Base UI Primitives - Skill

Name: base-ui Purpose: Build accessible, composable UI with @base-ui/react primitives and project styling tokens. Use this when creating or refining unstyled primitive components and behavior-heavy UI.

Applies when: Building overlays, menus, form controls, or custom component APIs with Base UI. Do not use when: You are using copied-in shadcn components as the primary implementation path (use moai-library-shadcn first).

Rules

  • Docs first: Start from reference-links.md, then read the exact component page before writing code.
  • Behavior before styling: Preserve Base UI interaction and accessibility behavior before adding project styles.
  • Styling agnostic: Keep logic and visuals decoupled; prefer wrappers and class composition over forking behavior code.
  • Tailwind compatibility: Base UI examples target Tailwind v4. If a target package uses v3, convert unsupported utilities to v3-safe equivalents.
  • Composable APIs: Favor controlled/uncontrolled patterns, small props, and clear slots over monolithic components.
  • A11y is non-negotiable: Keep labels, descriptions, focus handling, keyboard support, and ARIA relationships intact.

Workflow

  1. Confirm @base-ui/react is present in the target workspace package.json.
  2. Open the exact docs page from reference-links.md for the primitive you need.
  3. Implement behavior with Base UI primitives first, then layer project styles (cn, tokens, Tailwind).
  4. Convert any Tailwind v4-only example classes if the target workspace is still on Tailwind v3.
  5. Validate keyboard navigation, focus states, and screen-reader output.
  6. Run local quality gates (typecheck/lint/tests relevant to changed scope).

Checklists

Implementation checklist

  • Primitive choice matches the interaction model (dialog/menu/select/etc.)
  • Controlled/uncontrolled behavior is explicit and testable
  • Styling is layered without breaking interaction semantics
  • Tailwind classes are compatible with the target package version
  • Labels, descriptions, and focus behavior are preserved

Review checklist

  • No unnecessary re-implementation of behavior primitives
  • No prop explosion; component API stays composable
  • Keyboard-only interaction works end-to-end
  • Error/help text is correctly announced for form fields

Minimal examples

Wrapper-first composition

tsx
type FieldShellProps = {
  label: string;
  error?: string;
  children: React.ReactNode;
};

export function FieldShell({ label, error, children }: FieldShellProps) {
  return (
    <div className="grid gap-1.5">
      <span className="text-sm font-medium">{label}</span>
      {children}
      {error ? <p className="text-sm text-destructive">{error}</p> : null}
    </div>
  );
}

Tailwind v4 to v3 guardrail

txt
When docs examples rely on Tailwind v4-only utilities,
replace them with equivalent v3-safe utilities before commit.

Common mistakes / pitfalls

  • Styling first, then patching broken interactions later
  • Copying examples without checking Tailwind version compatibility
  • Mixing multiple primitive systems in one component without intent
  • Building large wrapper components with too many boolean props

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 Base Ui AI skill do?

Build accessible, composable UI with @base-ui/react primitives and project styling tokens. Use when creating or refining unstyled primitive components and behavior-heavy UI such as overlays, menus, popovers, dialogs, and form controls, or defining custom component APIs. Prefer the moai-library-shadcn skill when copied-in shadcn components are the primary implementation path.

Why use Base Ui on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Asymmetric-al/core/tree/develop/docs/ai/skills/base-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 Base 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 Base Ui?

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

Is the Base Ui 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 👇