MCP HubMCP Hub
スキル一覧に戻る

configure-chatkit

majiayu000
更新日 Yesterday
27 閲覧
58
9
58
GitHubで表示
メタaiapidesign

について

このスキルは、OpenAI ChatKitをNext.jsアプリケーションに統合する方法を開発者に案内します。環境設定、UIコンポーネントの構築、APIエンドポイントの統合を含みます。会話履歴とツール呼び出し結果を視覚的に表示するチャットボットフロントエンドを構築する際に使用されます。主な機能には、ChatKit UIの実装、ドメイン許可リスト管理、Better Authセッション統合が含まれます。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/majiayu000/claude-skill-registry
Git クローン代替
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/configure-chatkit

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Configure ChatKit Skill

This skill provides guidance for integrating OpenAI ChatKit in a Next.js frontend.

Purpose

Setup OpenAI ChatKit in Next.js:

  • Add domain allowlist key to environment
  • Build chat UI component
  • POST to /api/chat endpoint with conversation_id
  • Display conversation history and tool calls visually
  • Integrate Better Auth session

When to Use

Use this skill when:

  • Building the chatbot frontend UI
  • Integrating ChatKit components
  • Setting up chat API communication
  • Displaying tool execution results
  • Connecting frontend with authenticated backend

Capabilities

  • ChatKit Integration: Use OpenAI ChatKit for chat UI
  • Environment Configuration: Set up domain allowlist
  • API Communication: POST to chat endpoint with conversation context
  • Visual Feedback: Display history, tool calls, and results
  • Authentication: Integrate Better Auth session

Environment Setup

# .env.local
NEXT_PUBLIC_CHAT_KIT_PUBLIC_KEY=your_chatkit_public_key
CHAT_KIT_SECRET=your_chatkit_secret_key
CHAT_KIT_INSTANCE_ID=your_instance_id
NEXT_PUBLIC_ALLOWED_DOMAINS=localhost:3000,yourdomain.com

Implementation Pattern

Chat Component

"use client";

import { useState, useEffect, useRef } from "react";
import { useChat } from "@openai/chatkit";
import { useSession } from "better-auth/react";

interface ChatWidgetProps {
  conversationId?: string;
}

export function ChatWidget({ conversationId }: ChatWidgetProps) {
  const { data: session } = useSession();
  const [input, setInput] = useState("");
  const [isLoading, setIsLoading] = useState(false);
  const messagesEndRef = useRef<HTMLDivElement>(null);

  const {
    messages,
    sendMessage,
    isLoading: chatLoading,
    error
  } = useChat({
    apiUrl: "/api/chat",
    conversationId,
    auth: {
      getToken: () => session?.accessToken
    }
  });

  const handleSend = async () => {
    if (!input.trim() || isLoading) return;

    setIsLoading(true);
    try {
      await sendMessage(input);
      setInput("");
    } catch (err) {
      console.error("Failed to send message:", err);
    } finally {
      setIsLoading(false);
    }
  };

  return (
    <div className="chat-container">
      <div className="chat-messages">
        {messages.map((msg) => (
          <MessageBubble
            key={msg.id}
            role={msg.role}
            content={msg.content}
            toolCalls={msg.tool_calls}
          />
        ))}
        <div ref={messagesEndRef} />
      </div>

      <div className="chat-input">
        <input
          value={input}
          onChange={(e) => setInput(e.target.value)}
          onKeyDown={(e) => e.key === "Enter" && handleSend()}
          placeholder="Ask me to manage your tasks..."
          disabled={isLoading}
        />
        <button onClick={handleSend} disabled={isLoading}>
          {isLoading ? "Sending..." : "Send"}
        </button>
      </div>

      {error && <ErrorToast message={error.message} />}
    </div>
  );
}

Message Bubble with Tool Calls

interface MessageBubbleProps {
  role: "user" | "assistant" | "tool";
  content: string;
  toolCalls?: ToolCall[];
}

function MessageBubble({ role, content, toolCalls }: MessageBubbleProps) {
  const isUser = role === "user";

  return (
    <div className={`message ${isUser ? "user" : "assistant"}`}>
      <div className="message-content">{content}</div>

      {toolCalls && toolCalls.length > 0 && (
        <div className="tool-calls">
          {toolCalls.map((call) => (
            <ToolCallBadge key={call.id} tool={call} />
          ))}
        </div>
      )}
    </div>
  );
}

function ToolCallBadge({ tool }: { tool: ToolCall }) {
  return (
    <div className="tool-badge">
      <span className="tool-icon">🔧</span>
      <span className="tool-name">{tool.name}</span>
      {tool.status === "completed" && <span className="check">✓</span>}
      {tool.status === "failed" && <span className="x">✗</span>}
    </div>
  );
}

API Communication

async function sendMessage(message: string): Promise<void> {
  const response = await fetch("/api/chat", {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": `Bearer ${session?.accessToken}`
    },
    body: JSON.stringify({
      message,
      conversation_id: conversationId
    })
  });

  if (!response.ok) {
    throw new Error("Failed to send message");
  }

  const data = await response.json();
  // Update conversation_id if new
  if (!conversationId && data.conversation_id) {
    setConversationId(data.conversation_id);
  }
}

Better Auth Integration

"use client";

import { SessionProvider } from "better-auth/react";

export function AuthProvider({ children }: { children: React.ReactNode }) {
  return (
    <SessionProvider>
      {children}
    </SessionProvider>
  );
}

// In your chat component
const { data: session } = useSession();

useEffect(() => {
  if (session?.accessToken) {
    // Configure chat client with auth token
    chatClient.setAuthToken(session.accessToken);
  }
}, [session]);

Styling (Tailwind CSS)

.chat-container {
  @apply flex flex-col h-full max-w-2xl mx-auto border rounded-lg shadow-lg;
}

.chat-messages {
  @apply flex-1 overflow-y-auto p-4 space-y-4;
}

.message {
  @apply p-3 rounded-lg max-w-[80%];
}

.message.user {
  @apply bg-blue-500 text-white ml-auto;
}

.message.assistant {
  @apply bg-gray-100 text-gray-900;
}

.chat-input {
  @apply border-t p-4 flex gap-2;
}

.chat-input input {
  @apply flex-1 px-4 py-2 border rounded-lg focus:outline-none focus:ring-2;
}

.chat-input button {
  @apply px-4 py-2 bg-blue-500 text-white rounded-lg hover:bg-blue-600;
}

.tool-calls {
  @apply mt-2 flex flex-wrap gap-2;
}

.tool-badge {
  @apply inline-flex items-center gap-1 px-2 py-1 bg-yellow-100 text-yellow-800 text-xs rounded;
}

.error-toast {
  @apply absolute bottom-20 right-4 bg-red-500 text-white px-4 py-2 rounded-lg shadow;
}

Error Handling

function ErrorToast({ message }: { message: string }) {
  return (
    <div className="error-toast">
      <span>Error: {message}</span>
      <button onClick={() => clearError()}>Dismiss</button>
    </div>
  );
}

function LoadingIndicator() {
  return (
    <div className="typing-indicator">
      <span></span>
      <span></span>
      <span></span>
    </div>
  );
}

Verification Checklist

  • ChatKit configured with allowed domains
  • Chat widget displays messages correctly
  • Messages sent to /api/chat endpoint
  • Conversation ID maintained across messages
  • Tool calls displayed visually
  • Better Auth session integrated
  • Error toasts shown on failures
  • Loading indicators during API calls

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/configure-chatkit

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

creating-opencode-plugins

メタ

This skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.

スキルを見る

evaluating-llms-harness

テスト

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

スキルを見る

sglang

メタ

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

スキルを見る