chat-ui
Chat UI building blocks for React/Next.js from ui.inference.sh. Components: container, messages, input, typing indicators, avatars. Capabilities: chat interfaces, message lists, input handling, streaming. Use for: building custom chat UIs, messaging interfaces, AI assistants. Triggers: chat ui, chat component, message list, chat input, shadcn chat, react chat, chat interface, messaging ui, conversation ui, chat building blocks
Install
npx skills add https://github.com/inference-sh/skills --skill chat-uiSKILL.md
Install the belt CLI skill:
npx skills add belt-sh/cli
Chat UI Components
Chat building blocks from ui.inference.sh.

Quick Start
# Install chat components
npx shadcn@latest add https://ui.inference.sh/r/chat.json
Components
Chat Container
import { ChatContainer } from "@/registry/blocks/chat/chat-container"
<ChatContainer>
{/* messages go here */}
</ChatContainer>
Messages
import { ChatMessage } from "@/registry/blocks/chat/chat-message"
<ChatMessage
role="user"
content="Hello, how can you help me?"
/>
<ChatMessage
role="assistant"
content="I can help you with many things!"
/>
Chat Input
import { ChatInput } from "@/registry/blocks/chat/chat-input"
<ChatInput
onSubmit={(message) => handleSend(message)}
placeholder="Type a message..."
disabled={isLoading}
/>
Typing Indicator
import { TypingIndicator } from "@/registry/blocks/chat/typing-indicator"
{isTyping && <TypingIndicator />}
Full Example
import {
ChatContainer,
ChatMessage,
ChatInput,
TypingIndicator,
} from "@/registry/blocks/chat"
export function Chat() {
const [messages, setMessages] = useState([])
const [isLoading, setIsLoading] = useState(false)
const handleSend = async (content: string) => {
setMessages(prev => [...prev, { role: 'user', content }])
setIsLoading(true)
// Send to API...
setIsLoading(false)
}
return (
<ChatContainer>
{messages.map((msg, i) => (
<ChatMessage key={i} role={msg.role} content={msg.content} />
))}
{isLoading && <TypingIndicator />}
<ChatInput onSubmit={handleSend} disabled={isLoading} />
</ChatContainer>
)
}
Message Variants
| Role | Description |
|---|---|
user |
User messages (right-aligned) |
assistant |
AI responses (left-aligned) |
system |
System messages (centered) |
Styling
Components use Tailwind CSS and shadcn/ui design tokens:
<ChatMessage
role="assistant"
content="Hello!"
className="bg-muted"
/>
Related Skills
# Full agent component (recommended)
npx skills add inference-sh/skills@agent-ui
# Declarative widgets
npx skills add inference-sh/skills@widgets-ui
# Markdown rendering
npx skills add inference-sh/skills@markdown-ui
Documentation
- Chatting with Agents - Building chat interfaces
- Agent UX Patterns - Chat UX best practices
- Real-Time Streaming - Streaming responses
Component docs: ui.inference.sh/blocks/chat
Related skills
vercel-react-best-practicesvercel-labs751KReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.vercel-composition-patternsvercel-labs361KReact composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.vercel-react-view-transitionsvercel-labs135KGuide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components, animate list reorder, implement directional (forward/back) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions viewpick-ui-libraryemilkowalski124KPick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly invoked; it does not trigger on its own.
