add-provider-package

Create @ai-sdk/<provider> workspace modules with provider and model adapters.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/stellarone/evaluate --skill add-provider-package-stellarone
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-provider-package
Source: https://github.com/stellarone/evaluate/tree/main/.agents/skills/add-provider-package
Command: npx skills add https://github.com/stellarone/evaluate --skill add-provider-package-stellarone

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you add a brand-new AI provider package to the AI SDK so your AI service can plug into the same model and generation abstractions used by existing providers.

Core Features & Use Cases

  • Package scaffolding: Creates the expected directory, build, and test structure for a new @ai-sdk/<provider> package.
  • Provider + model implementation guidance: Implements the adapter-pattern provider and the required model classes (language, embeddings, images, etc.).
  • Validation, safety, and maintainability: Recommends schema practices, API key loading, deterministic testing, and changeset-based versioning.

Quick Start

Create a new @ai-sdk/<provider> package by following the Skill’s steps to scaffold src/, implement the provider and model classes, add tests and examples, and write the provider documentation in the content directory.

Frequently Asked Questions about add-provider-package

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I integrate a new AI provider into the AI SDK?▼

You integrate a new AI provider into the AI SDK by scaffolding a new @ai-sdk/<provider> workspace module, implementing adapter-pattern provider and model classes, and configuring build and test setups.

What's the best way to structure an AI SDK provider package?▼

The best way to structure an AI SDK provider package is to scaffold the expected directory, build, and test structure, implement required model classes in src/, and write provider documentation in the content directory.

How do you handle API key loading and schema validation for AI SDK adapters?▼

API key loading and schema validation for AI SDK adapters are handled securely via provider-utils, using schema practices to parse responses and validate the provider implementation.

Does the AI SDK require an adapter pattern for model implementation?▼

Yes, the AI SDK requires an adapter pattern for model implementation, demanding model classes conform to @ai-sdk/provider interfaces to support generate, stream, and object workflows.

How do I set up tests and examples for a new AI provider integration?▼

You set up tests and examples for a new AI provider integration by adding deterministic testing and writing examples for generate, stream, and object workflows within the package structure.

Do I need a changeset-driven release workflow for AI SDK provider packages?▼

Yes, you need a changeset-driven release workflow for AI SDK provider packages to manage versioning, validation, safety, and maintainability throughout the provider integration lifecycle.