Moai Domain Frontend logo

Moai Domain Frontend

OrganizationPopular
modu-ai
moai-domain-frontend

Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture. Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management.

Overview

Publishermodu-ai
Repositorymoai-adk
Skill namemoai-domain-frontend
Stars
1.2K
Forks
226
Bundled files
Instructions only
LicenseApache-2.0
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by modu-ai on GitHub. Read the source before you install it.

Installation

Install the Moai Domain Frontend 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/modu-ai/moai-adk/tree/main/.claude/skills/moai-domain-frontend
  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/modu-ai/moai-adk.git /tmp/moai-adk
mkdir -p .claude/skills
cp -r /tmp/moai-adk/.claude/skills/moai-domain-frontend .claude/skills/moai-domain-frontend
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Moai Domain Frontend 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 Domain Frontend 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 Domain Frontend 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.

Frontend Development Specialist

Quick Reference

Modern Frontend Development - Comprehensive patterns for React 19, Next.js 16, Vue 3.5.

Core Capabilities:

  • React 19: Server components, concurrent features, cache(), Suspense
  • Next.js 16: App Router, Server Actions, ISR, Route handlers
  • Vue 3.5: Composition API, TypeScript, Pinia state management
  • Component Architecture: Design systems, compound components, CVA
  • Performance: Code splitting, dynamic imports, memoization, Framer Motion animations

When to Use:

  • Modern web application development
  • Component library creation
  • Frontend performance optimization
  • UI/UX with accessibility

Patterns

Framework Patterns

React 19 Patterns:

  • Server Components, Concurrent features, cache() API, Form handling

Next.js 16 Patterns:

  • App Router, Server Actions, ISR, Route Handlers, Parallel Routes

Vue 3.5 Patterns:

  • Composition API, Composables, Reactivity, Pinia, Provide/Inject

Architecture Patterns

Component Architecture:

  • Design tokens, CVA variants, Compound components, Accessibility

State Management:

  • Zustand, Redux Toolkit, React Context, Pinia

Performance Optimization:

  • Code splitting, Dynamic imports, Image optimization, Memoization

AI-Assisted Frontend Patterns:

  • Visual reference strategy, Playwright verification, motion design, reasoning-level tuning

Vercel React Best Practices:

  • 45 rules across 8 categories from Vercel Engineering
  • Eliminating waterfalls, bundle optimization, server-side performance
  • Client-side data fetching, re-render optimization, rendering performance

Implementation Quickstart

React 19 Server Component

Create an async page component that uses the cache function from React to memoize data fetching. Import Suspense for loading states. Define a getData function that fetches from the API endpoint with an id parameter and returns JSON. In the page component, wrap the DataDisplay component with Suspense using a Skeleton fallback, and pass the awaited getData result as the data prop.

Next.js Server Action

Create a server action file with the use server directive. Import revalidatePath from next/cache and z from zod for validation. Define a schema with title (minimum 1 character) and content (minimum 10 characters). The createPost function accepts FormData, validates with safeParse, returns errors on failure, creates the post in the database, and calls revalidatePath for the posts page.

Vue Composable

Create a useUser composable that accepts a userId ref parameter. Define user as a nullable ref, loading as a boolean ref, and fullName as a computed property that concatenates firstName and lastName. Use watchEffect to set loading true, fetch the user data asynchronously, assign to user ref, and set loading false. Return the user, loading, and fullName refs.

CVA Component

Import cva and VariantProps from class-variance-authority. Define buttonVariants with base classes for inline-flex, items-center, justify-center, rounded-md, and font-medium. Add variants object with variant options for default (primary background with hover) and outline (border with hover accent). Add size options for sm (h-9, px-3, text-sm), default (h-10, px-4), and lg (h-11, px-8). Set defaultVariants for variant and size. Export a Button component that applies the variants to a button element className.


Works Well With

  • moai-domain-backend - Full-stack development
  • moai-ref-ui-polish - Component library integration
  • moai-ref-ui-polish - UI/UX design principles
  • .claude/rules/moai/languages/typescript.md - TypeScript patterns (auto-loaded via paths frontmatter)
  • moai-workflow-testing - Frontend testing

Technology Stack

Frameworks: React 19, Next.js 16, Vue 3.5, Nuxt 3

Languages: TypeScript 5.9+, JavaScript ES2024

Styling: Tailwind CSS 3.4+, CSS Modules, shadcn/ui

Animation: Framer Motion

State: Zustand, Redux Toolkit, Pinia

Testing: Vitest, Testing Library, Playwright

Verification: Playwright (visual inspection, functional testing)


Resources

Official documentation:


Version: 2.1.0

Common Rationalizations

RationalizationReality
"Accessibility can be added after launch"Post-launch accessibility is a rewrite, not an addition. Semantic HTML and ARIA are foundational, not decorative.
"This component is too simple to need its own test"Simple components compose into complex UIs. A broken simple component cascades failures everywhere it is used.
"Server components are always faster"Server components add network round trips. Client components with proper caching can outperform naive server components. Measure, do not assume.
"I will just use any as the TypeScript type for now"any disables the type checker for everything downstream. One any infects the entire call chain.
"Global CSS is fine for this project"Global CSS creates specificity conflicts as the project grows. Scoped styles (CSS modules, Tailwind) prevent collisions.

Red Flags

  • Component renders user-provided HTML without sanitization (XSS vector)
  • TypeScript any type used in component props or state definitions
  • No loading or error states defined for async data fetching components
  • Accessibility attributes (aria-label, role) missing from interactive elements
  • Bundle size increased by more than 50KB without justification
  • Component has more than 300 lines without extraction into sub-components

Verification

  • All interactive elements have accessible names (aria-label or visible text)
  • Components handle loading, error, and empty states
  • No TypeScript any in new or modified code (show grep results)
  • Bundle size impact measured for new dependencies (show analyzer output)
  • User-provided content rendered with proper escaping or sanitization
  • Components under 300 lines or decomposed with clear sub-component boundaries

Frequently asked questions

What does the Moai Domain Frontend AI skill do?

Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture. Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management.

Why use Moai Domain Frontend on TypingMind?

Because you install it once and use it with any model. Moai Domain Frontend 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 Domain Frontend in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/moai-domain-frontend. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Moai Domain Frontend?

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 Domain Frontend?

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

Is the Moai Domain Frontend AI skill free?

Yes. It is published on GitHub by modu-ai under the Apache-2.0 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 👇