Skill: ai-sdk-core
SkillDocs & knowledgeThis skill gives your AI accurate reference knowledge of Vercel AI SDK v7, so it can build AI features in your backend without writing code from memory. Once added, your AI can implement text generation, streaming replies, and tool-based agents that work with the current v7 API. It also helps track down and fix errors in existing AI SDK code.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then ask your AI to build or debug a feature that uses Vercel AI SDK v7. It will work from the reference material rather than relying on memory.
Then ask your AI: use the Skill: ai-sdk-core skill
What your AI can do with it
- Write code that generates text with generateText
- Build responses that stream as they are produced using streamText
- Create ToolLoopAgent agents that work through tasks step by step
- Attach tools so the AI can take actions, not just answer
- Troubleshoot and fix errors in AI SDK code
- Follow the actual v7 API instead of guessing outdated patterns
What this skill tells your AI
The instructions your AI receives, as published by blockmatic/basilic in .agents/skills/ai-sdk-core-v7/SKILL.md and read by ahel’s review.
Scope
- Applies to: Backend AI with Vercel AI SDK v7 (
aipackage) - Does NOT cover: React chat UIs (see ai-sdk-ui)
Assumptions
- Folder major tracks the installed
aipackage inpackage.json, not a skill-file revision - Node.js 22+, ESM; Zod 4 for
inputSchema - Never write AI SDK from memory. Grep
node_modules/ai/docs/andnode_modules/ai/src/for the installed version. Else https://ai-sdk.dev/docs (append.md) or https://ai-sdk.dev/api/search-docs?q= - v6 leftovers: https://ai-sdk.dev/docs/migration-guides/migration-guide-7-0
Principles
generateText/streamTextfor request handlers and one-shot API routes;instructionsfor system-style prompt- Request-handler tool loops:
stopWhen: isStepCount(n)ongenerateText/streamText— notmaxSteps, notstepCountIs ToolLoopAgent+generate()/stream()for durable agents — not hand-rolled loops, notnew Agent()- UI streams:
createUIMessageStreamResponse+toUIMessageStream({ stream: result.stream })from'ai'. Use these for new handlers and for dedicated stream/SDK updates result.toUIMessageStreamResponse()still works in v7 (deprecated). Leave it only when the task is unrelated to streaming or the SDK- Tool results must be JSON-serializable (no
Date) - System prompt lives in
instructions. Clientmessagesmust not include{ role: 'system' }unless the server fully trusts the payload
Constraints
MUST
- Read bundled docs before writing calls
convertToModelMessageswhen the client sends UI messages- Reject untrusted
{ role: 'system' }inmessages. Do not setallowSystemInMessages: truefor client-supplied chat
AVOID
toDataStreamResponse/pipeDataStreamToResponsestepCountIs/maxSteps/result.fullStream/ top-levelsystem:(useisStepCount,result.stream,instructions)- Guessing model IDs
Interactions
- Complements ai-sdk-ui, fastify, next
- Upstream: vercel/ai use-ai-sdk
Templates
References
- Request handlers — tools +
isStepCount, Fastify SSE, system-message reject
Signals
- GitHub stars
- 89
- Forks
- 11
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
ai-sdk-core-v7- Source
- github.com/blockmatic/basilic