Skip to content

laguagu/claude-code-nextjs-skills / skills/ai-sdk-6

ai-sdk-6

Verified

Vercel AI SDK v6 development, for projects already on ai@6. Use when building or maintaining AI agents, chatbots, tool integrations, streaming apps, or structured output in a v6 codebase. New projects and ai@7 code use ai-sdk-7; an unknown version goes through ai-sdk. Covers ToolLoopAgent, useChat, generateText, streamText, tool approval, provider tools, MCP integration, and Output patterns.

FileKindSize
SKILL.mdskill md5.1 KB
references/agents.mdmarkdown1.0 KB
references/core-functions.mdmarkdown1.1 KB
references/examples.mdmarkdown787 B
references/mcp.mdmarkdown1009 B
references/middleware.mdmarkdown1.0 KB
references/tools.mdmarkdown1.9 KB
references/ui-hooks.mdmarkdown1.9 KB
references/workflows.mdmarkdown831 B

references/core-functions.md

View on GitHub
# AI SDK 6 generation and output

Use `generateText` or `streamText` with the provider package already used by
the app. V6 uses `system`, `stopWhen` and `stepCountIs`; do not substitute
v7 names or assume they exist in this major.

For schema output, use `Output.object`, `array`, `choice` or another supported
output specification. Prefer validated output to parsing text that merely
looks like JSON. Schema validity does not prove semantic correctness.

A `useChat` response needs UI-message streaming; a plain text stream is a
different protocol. V6 exposes result helpers such as
`toUIMessageStreamResponse`, `fullStream` and `consumeStream`. Streaming
completion is `onFinish`; final result properties may be promises.

Multi-step `usage`, tool calls and outputs on the result have final-step
semantics; `totalUsage` and `steps` provide aggregates/history. Match the field
to the app's accounting or persistence requirement.

Resolve provider options, callbacks and structured-stream behavior from the
installed docs/types or the
[v6 Core guide](https://github.com/vercel/ai/blob/ai%406.0.297/content/docs/03-ai-sdk-core/01-overview.mdx).
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall