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/workflows.md

View on GitHub
# Orchestration choices

Use the simplest execution model that meets the product contract. Fixed steps
can be ordinary application code; independent work can run concurrently. Use a
tool loop when the model must choose the next action.

A routing, worker or evaluator stage earns its place through a task requirement
or measured improvement. It adds model calls, latency and failure paths; an
LLM judge needs a bounded stopping rule and criteria the supplied evidence can
establish.

These v6 application patterns do not provide the durable `WorkflowAgent`
runtime added through a separate package in v7. Do not silently upgrade the
SDK to introduce it.

Use the installed agent docs or
[v6 workflow patterns](https://github.com/vercel/ai/blob/ai%406.0.297/content/docs/03-agents/03-workflows.mdx) for a
matching official example.
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: 471kUpdated 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