laguagu/claude-code-nextjs-skills / skills/ai-elements
ai-elements
VerifiedMaintains AI chat UI built from elements.ai-sdk.dev AI Elements components already copied into the project. Use when changing or debugging those components (conversations, messages, prompt inputs, attachments, reasoning, tool output, sources). New chat UI uses the shadcn/ui AI Elements patterns (`shadcn` skill).
scripts/reasoning.tsx
View on GitHub"use client";
import {
Reasoning,
ReasoningContent,
ReasoningTrigger,
} from "@/components/ai-elements/reasoning";
import { useCallback, useEffect, useState } from "react";
const reasoningSteps = [
"Let me think about this problem step by step.",
"\n\nFirst, I need to understand what the user is asking for.",
"\n\nThey want a reasoning component that opens automatically when streaming begins and closes when streaming finishes. The component should be composable and follow existing patterns in the codebase.",
"\n\nThis seems like a collapsible component with state management would be the right approach.",
].join("");
const Example = () => {
const [content, setContent] = useState("");
const [isStreaming, setIsStreaming] = useState(false);
const [currentTokenIndex, setCurrentTokenIndex] = useState(0);
const [tokens, setTokens] = useState<string[]>([]);
// Function to chunk text into fake tokens of 3-4 characters
const chunkIntoTokens = useCallback((text: string): string[] => {
const chunks: string[] = [];
let i = 0;
while (i < text.length) {
// Random size between 3-4
const chunkSize = Math.floor(Math.random() * 2) + 3;
chunks.push(text.slice(i, i + chunkSize));
i += chunkSize;
}
return chunks;
}, []);
useEffect(() => {
const tokenizedSteps = chunkIntoTokens(reasoningSteps);
setTokens(tokenizedSteps);
setContent("");
setCurrentTokenIndex(0);
setIsStreaming(true);
}, [chunkIntoTokens]);
useEffect(() => {
if (!isStreaming || currentTokenIndex >= tokens.length) {
if (isStreaming) {
setIsStreaming(false);
}
return;
}
// Faster interval since we're streaming smaller chunks
const timer = setTimeout(() => {
setContent((prev) => prev + tokens[currentTokenIndex]);
setCurrentTokenIndex((prev) => prev + 1);
}, 25);
return () => clearTimeout(timer);
}, [isStreaming, currentTokenIndex, tokens]);
return (
<div className="w-full p-4" style={{ height: "300px" }}>
<Reasoning className="w-full" isStreaming={isStreaming}>
<ReasoningTrigger />
<ReasoningContent>{content}</ReasoningContent>
</Reasoning>
</div>
);
};
export default Example;
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |