ai-sdk

por openai

Orientação especializada do Vercel AI SDK. Use ao criar funcionalidades baseadas em IA — interfaces de chat, geração de texto, saída estruturada, chamada de ferramentas, agentes, MCP…

npx skills add https://github.com/openai/plugins --skill ai-sdk

Prerequisites

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Everything you know about the AI SDK is outdated or wrong.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:

  1. Ensure ai package is installed (see Prerequisites)
  2. Search node_modules/ai/docs/ and node_modules/ai/src/ for current APIs
  3. If not found locally, search ai-sdk.dev documentation (instructions below)
  4. Never rely on memory - always verify against source code or docs
  5. useChat has changed significantly - check Common Errors before writing client code
  6. 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.
  7. 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 | .[]' (replacing provider with the relevant provider like anthropic, openai, or google) to get the full list with newest models first. Use the model with the highest version number (e.g., claude-sonnet-4-5 over claude-sonnet-4 over claude-3-5-sonnet).
  8. Run typecheck after changes to ensure code is correct
  9. 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

  1. Search: https://ai-sdk.dev/api/search-docs?q=your_query
  2. Fetch .md URLs 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:

  1. Search node_modules/ai/src/ and node_modules/ai/docs/
  2. 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:

  1. Check package.json to detect the project's framework/stack
  2. Search documentation for the framework's quickstart guide
  3. Follow the framework-specific patterns for streaming, API routes, and client integration

References

Related Skills in This Plugin

  • AI Elements component library for AI interfaces (Message, Conversation, Tool components) → ⤳ skill: ai-elements
  • Manual rendering patterns for custom generative UIs → ⤳ skill: json-render

Mais skills de openai

release
openai
Crie um release da Symphony atualizando a versão commitada, fazendo o merge, criando a tag no commit mesclado e verificando o workflow de release do Burrito. Use quando for solicitado a...
signing-entitlements
openai
Inspecione problemas de assinatura, entitlements, runtime protegido e Gatekeeper em aplicativos macOS. Use quando solicitado a diagnosticar falhas de assinatura de código, entitlements ausentes,…
building-ai-agent-on-cloudflare
openai
Constrói agentes de IA na Cloudflare usando o Agents SDK com gerenciamento de estado, WebSockets em tempo real, tarefas agendadas, integração de ferramentas e chat…
epigraphdb-skill
openai
Envie requisições compactas da API EpiGraphDB para ontologia, literatura, MR, gene-droga e evidências de suporte a caminhos. Use quando um usuário desejar resumos concisos do EpiGraphDB.
runtime-behavior-probe
openai
Planeje e execute investigações de comportamento em tempo de execução com scripts de sonda temporários, matrizes de validação, controles de estado e relatórios focados em descobertas. Use apenas quando…
deep-security-scan
openai
Use quando o usuário solicitar uma varredura de segurança Codex Security scan profunda, exaustiva, de múltiplas passagens ou com redução de variância, em todo o repositório ou em caminho específico. Execute repetidas verificações independentes…
define-security-policy
openai
Defina, revise ou atualize as orientações do SECURITY.md para um repositório ou componente. Use quando o usuário quiser esclarecer o que o Codex Security deve revisar, o que está fora…
validation
openai
Use quando o Codex já está na fase de validação de uma varredura de segurança ou quando o usuário pede explicitamente para determinar se uma ou mais descobertas de segurança candidatas…