ai-sdk
Scannednpx machina-cli add skill petekp/claude-code-setup/ai-sdk --openclawPrerequisites
Before searching docs, check if node_modules/ai/docs/ exists. If not, install only the ai package using the project's package manager (e.g., pnpm add ai).
Do not install other packages at this stage. Provider packages (e.g., @ai-sdk/openai) and client packages (e.g., @ai-sdk/react) should be installed later when needed based on user requirements.
Critical: Do Not Trust Internal Knowledge
Everything you know about the AI SDK is outdated or wrong. Your training data contains obsolete APIs, deprecated patterns, and incorrect usage.
When working with the AI SDK:
- Ensure
aipackage is installed (see Prerequisites) - Search
node_modules/ai/docs/andnode_modules/ai/src/for current APIs - If not found locally, search ai-sdk.dev documentation (instructions below)
- Never rely on memory - always verify against source code or docs
useChathas changed significantly - check Common Errors before writing client code- When deciding which model and provider to use (e.g. OpenAI, Anthropic, Gemini), use the Vercel AI Gateway provider unless the user specifies otherwise. See AI Gateway Reference for usage details.
- Always fetch current model IDs - Never use model IDs from memory. Before writing code that uses a model, run
curl -s https://ai-gateway.vercel.sh/v1/models | jq -r '[.data[] | select(.id | startswith("provider/")) | .id] | reverse | .[]'(replacingproviderwith the relevant provider likeanthropic,openai, orgoogle) to get the full list with newest models first. Use the model with the highest version number (e.g.,claude-sonnet-4-5overclaude-sonnet-4overclaude-3-5-sonnet). - Run typecheck after changes to ensure code is correct
- Be minimal - Only specify options that differ from defaults. When unsure of defaults, check docs or source rather than guessing or over-specifying.
If you cannot find documentation to support your answer, state that explicitly.
Finding Documentation
ai@6.0.34+
Search bundled docs and source in node_modules/ai/:
- Docs:
grep "query" node_modules/ai/docs/ - Source:
grep "query" node_modules/ai/src/
Provider packages include docs at node_modules/@ai-sdk/<provider>/docs/.
Earlier versions
- Search:
https://ai-sdk.dev/api/search-docs?q=your_query - Fetch
.mdURLs from results (e.g.,https://ai-sdk.dev/docs/agents/building-agents.md)
When Typecheck Fails
Before searching source code, grep Common Errors for the failing property or function name. Many type errors are caused by deprecated APIs documented there.
If not found in common-errors.md:
- Search
node_modules/ai/src/andnode_modules/ai/docs/ - Search ai-sdk.dev (for earlier versions or if not found locally)
Building and Consuming Agents
Creating Agents
Always use the ToolLoopAgent pattern. Search node_modules/ai/docs/ for current agent creation APIs.
File conventions: See type-safe-agents.md for where to save agents and tools.
Type Safety: When consuming agents with useChat, always use InferAgentUIMessage<typeof agent> for type-safe tool results. See reference.
Consuming Agents (Framework-Specific)
Before implementing agent consumption:
- Check
package.jsonto detect the project's framework/stack - Search documentation for the framework's quickstart guide
- Follow the framework-specific patterns for streaming, API routes, and client integration
References
- Common Errors - Renamed parameters reference (parameters → inputSchema, etc.)
- AI Gateway - Gateway setup and usage
- Type-Safe Agents with useChat - End-to-end type safety with InferAgentUIMessage
- DevTools - Set up local debugging and observability (development only)
Source
git clone https://github.com/petekp/claude-code-setup/blob/main/skills/ai-sdk/SKILL.mdView on GitHub Overview
This skill answers questions about the AI SDK and assists in building AI-powered features such as agents, chatbots, RAG systems, and text generation. It covers APIs like generateText, streamText, ToolLoopAgent, embed, and tools, as well as provider choices, streaming, tool calling, structured output, embeddings, and React hooks like useChat and useCompletion.
How This Skill Works
When users ask about the AI SDK, this skill guides them to current APIs by checking local docs under node_modules/ai/docs and node_modules/ai/src, installing only the ai package first, and validating model IDs via the AI Gateway. It emphasizes using the ToolLoopAgent pattern for agents, evaluating provider options (defaulting to Vercel AI Gateway), and performing typechecking after changes, while avoiding reliance on outdated internal knowledge.
When to Use It
- When developers ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools
- When building AI-powered features such as agents, chatbots, RAG systems, or text generation
- When questions arise about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings
- When using React hooks like useChat or useCompletion
- When guidance is needed on prerequisites, installation steps, and best practices for the ai package
Quick Start
- Step 1: Ensure node_modules/ai/docs exists; if not, install only the ai package (pnpm add ai)
- Step 2: Inspect node_modules/ai/docs and node_modules/ai/src for current APIs; consult ai-sdk.dev if needed
- Step 3: For agents, implement using the ToolLoopAgent pattern and run typecheck after changes
Best Practices
- Verify APIs locally by inspecting node_modules/ai/docs and node_modules/ai/src before coding
- Install only the ai package initially (pnpm add ai) and defer provider/client packages until required
- Prefer the Vercel AI Gateway provider by default for model/provider decisions unless the user specifies otherwise
- Always fetch current model IDs with the curl command provided before using a model
- Use the ToolLoopAgent pattern for creating agents and run typecheck after changes
Example Use Cases
- A developer asks how to use generateText and streamText to power a chat feature in their app
- A team builds an AI agent with ToolLoopAgent to orchestrate multiple tools for a workflow
- They compare providers and default to Vercel AI Gateway, then fetch the latest models via curl
- They integrate useChat or useCompletion in React components and ensure type safety
- They verify docs in node_modules/ai/docs before implementing any API calls