secondsky/claude-skills / plugins/tanstack-ai/skills/tanstack-ai
tanstack-ai
VerifiedTanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama. Use for chat APIs, React/Solid frontends with useChat/ChatClient, isomorphic tools, tool approval flows, agent loops, multimodal inputs, or troubleshooting streaming and tool definitions.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.4 KB |
| assets/api-chat-route.ts | script | 859 B |
| assets/tool-definitions.ts | script | 1.0 KB |
| references/adapter-matrix.md | markdown | 2.4 KB |
| references/react-integration.md | markdown | 1.5 KB |
| references/start-vs-next-routing.md | markdown | 1.8 KB |
| references/streaming-troubleshooting.md | markdown | 2.2 KB |
| references/tanstack-ai-cheatsheet.md | markdown | 2.4 KB |
| references/tool-patterns.md | markdown | 2.0 KB |
| references/type-safety.md | markdown | 1.5 KB |
| scripts/check-ai-env.shexecutable | script | 512 B |
assets/tool-definitions.ts
View on GitHubimport { z } from 'zod'
import { toolDefinition } from '@tanstack/ai'
// Shared definition sent to the model (never include sensitive logic here)
export const createTodoDef = toolDefinition({
name: 'createTodo',
description: 'Create a todo item with a title and optional due date',
inputSchema: z.object({
title: z.string().min(3),
due: z.string().optional(),
}),
needsApproval: true, // ask the user before creating data
})
// Server implementation (runs on your server)
export const createTodo = createTodoDef.server(async ({ title, due }) => {
// Replace with your persistence layer
const todo = { id: crypto.randomUUID(), title, due: due ?? null }
// e.g., await db.todo.insert(todo)
return { todo }
})
// Client implementation (runs in the browser)
export const showToast = createTodoDef.client(({ title }) => {
// Replace with your UI toast system
console.info(`Todo created: ${title}`)
return { acknowledged: true }
})
// Export definitions array for convenience
export const tools = [createTodo]
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 |