vercel/ai▌
5 approved skills in this repository
add-provider-package
Productivity
This guide covers the process of creating a new @ai-sdk/<provider> package to integrate an AI service into the AI SDK.
capture-api-response-test-fixture
Backend
Store and manage API response test fixtures for provider parsing validation. \n \n Fixtures are organized in __fixtures__ subfolders within provider packages, using naming conventions documented in existing examples \n Supports two testing patterns: generateText (log raw response to console and copy into fixture) and streamText (use includeRawChunks and saveRawChunks helper to capture streaming chunks) \n Recommends storing true provider responses unless size constraints require semantic-preserv
list-npm-package-content
Marketing
Inspect npm package tarball contents before publishing to verify what files will be distributed. \n \n Lists exact files that would be uploaded to npm, helping catch missing or unwanted inclusions before publish \n Respects files field in package.json, .npmignore , and .gitignore rules to show the actual bundle contents \n Automatically builds the package, creates a tarball, displays contents, and cleans up in a single command \n Run from the package directory with a simple bash script; useful f
develop-ai-functions-example
AI/ML
Development and validation scripts for AI SDK functions across multiple providers and capabilities. \n \n Organized by AI SDK function category (text generation, streaming, structured output, embeddings, image generation, speech, transcription, reranking, and agents) \n File naming convention maps provider and feature combinations (e.g., openai-tool-call.ts , amazon-bedrock-anthropic-cache-control.ts ) for quick identification \n Includes shared utility helpers for error handling, environment lo
ai-sdk
AI/ML
AI SDK documentation and guidance for building AI-powered features with Vercel's framework. \n \n Covers core APIs including generateText , streamText , ToolLoopAgent , embed , and tool calling across multiple AI providers (OpenAI, Anthropic, Google, etc.) \n Supports building agents, chatbots, RAG systems, and text generation with structured output and streaming capabilities \n Includes React hooks ( useChat , useCompletion ) and framework-specific patterns for Next.js, SvelteKit, and other pla