chat-sdk
Provides expert guidance for building production AI chatbots using Vercel's unified AI SDK and Next.js.
Install
mkdir -p .claude/skills/chat-sdk && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16417" && unzip -o skill.zip -d .claude/skills/chat-sdk && rm skill.zipInstalls to .claude/skills/chat-sdk
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Expert on Vercel's Chat SDK for building production-ready AI chatbots. Use when user wants to build chatbot apps, add generative UI, create artifacts, or deploy AI chat interfaces. Triggers on mentions of chat-sdk, ai-chatbot, chatgpt clone, vercel chat, generative ui.Key capabilities
- →Build AI chatbot applications.
- →Integrate with AI SDK for text generation and tool calls.
- →Utilize generative UI for dynamic interfaces.
- →Create custom artifacts for specialized workspaces.
- →Execute in-browser code via WASM/pyodide.
- →Deploy AI chat interfaces to Vercel.
How it works
The skill use Vercel's Chat SDK, built on Next.js App Router and AI SDK, to create AI chatbots with generative UI, custom artifacts, and in-browser code execution.
Inputs & outputs
When to use chat-sdk
- →Building AI chatbot apps
- →Adding generative UI to interfaces
- →Creating custom chatbot artifacts
- →Deploying AI interfaces to Vercel
About this skill
Chat SDK Skill
Expert at building AI chatbot applications with Vercel's Chat SDK.
Overview
Chat SDK is a free, open-source template for building production-ready chatbots:
- Built on Next.js App Router with AI SDK integration
- Generative UI for dynamic, interactive interfaces
- Custom artifacts for specialized workspaces
- In-browser code execution via WASM/pyodide
- Auth, persistence, multimodal support, and shareable chats
- One-click Vercel deployment
Quick Start
# Clone and setup
npx create-next-app --example https://github.com/vercel/ai-chatbot my-chatbot
cd my-chatbot
# Install and configure
pnpm install
cp .env.example .env.local
# Add your API keys to .env.local
# Database setup
pnpm db:migrate
# Run development server
pnpm dev
Core Concepts
AI SDK Integration
Uses unified API for text generation, structured objects, and tool calls:
import { generateText } from 'ai';
import { xai } from '@ai-sdk/xai';
const { text } = await generateText({
model: xai('grok-2-vision-1212'),
prompt: 'Hello!',
});
Model Providers
Default: AI SDK Gateway with xAI (grok-2-vision-1212). Switch providers easily:
- OpenAI, Anthropic, Google, xAI, and more via unified gateway
- Configure in
lib/ai/models.ts
Generative UI
Dynamic interfaces that adapt to conversation context beyond text.
Documentation
For detailed information, see the reference documentation:
- Overview - Feature summary and doc structure
- Setup - Installation and configuration
- Architecture - Project structure and components
- Models and Providers - AI providers and configuration
- Artifacts - Custom workspaces and tools
- Theming - Customizing appearance
- Deployment - Vercel and self-hosting
- Upstream README - Full original documentation
Common Workflows
Add New AI Provider
// lib/ai/models.ts
import { anthropic } from '@ai-sdk/anthropic';
export const models = {
'claude-3': anthropic('claude-3-5-sonnet-20241022'),
};
Create Custom Artifact
See docs/artifacts.md for creating interactive workspaces.
Deploy to Vercel
vercel deploy
Upstream Sources
- Repository: https://github.com/vercel/ai-chatbot
- Documentation: https://chat-sdk.dev/
Sync & Update
When user runs sync: fetch latest from upstream sources, update docs/ files.
When user runs diff: compare current vs upstream, report changes.
When not to use it
- →When not building chatbot apps.
- →When not using Vercel's Chat SDK.
- →When the user does not want to deploy AI chat interfaces.
Limitations
- →Requires API keys for AI model providers.
- →Database setup is needed for persistence.
- →Deployment is optimized for Vercel.
How it compares
This workflow provides a structured, open-source template for building production-ready AI chatbots with advanced features like generative UI and in-browser code execution, unlike basic chatbot implementations.
Compared to similar skills
chat-sdk side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| chat-sdk (this skill) | 0 | 5mo | Review | Intermediate |
| copilotkit-develop | 0 | 3mo | No flags | Intermediate |
| hr-portal-skill | 0 | 1mo | No flags | Beginner |
| create-mcp-app | 3 | 5mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by diegosouzapw
View all by diegosouzapw →You might also like
copilotkit-develop
jerelvelarde
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
hr-portal-skill
hariventures2000-ship-it
Use this skill when developing, testing, debugging, or modifying code inside the HR Portal frontend (apps/hr-portal). It applies to handling HR administration tasks such as employee roster management, contract seeding, leave request approvals, attendance monitoring, payroll calculation, and recruitm
create-mcp-app
modelcontextprotocol
This skill should be used when the user asks to "create an MCP App", "add a UI to an MCP tool", "build an interactive MCP View", "scaffold an MCP App", or needs guidance on MCP Apps SDK patterns, UI-resource registration, MCP App lifecycle, or host integration. Provides comprehensive guidance for building MCP Apps with interactive UIs.
ai-model-web
TencentCloudBase
Use this skill when developing browser/Web applications (React/Vue/Angular, static websites, SPAs) that need AI capabilities. Features text generation (generateText) and streaming (streamText) via @cloudbase/js-sdk. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended) and DeepSeek (deepseek-v3.2 recommended). NOT for Node.js backend (use ai-model-nodejs), WeChat Mini Program (use ai-model-wechat), or image generation (Node SDK only).
nextjs-developer
zenobi-us
Expert Next.js developer mastering Next.js 14+ with App Router and full-stack features. Specializes in server components, server actions, performance optimization, and production deployment with focus on building fast, SEO-friendly applications.
shadcn-ui-setup
maneeshanif
Install and configure Shadcn/ui component library with Radix UI primitives, Aceternity UI effects, set up components, and manage the component registry. Use when adding Shadcn/ui to a Next.js project or installing specific UI components for Phase 2.