llm-provider

Name: llm-provider
Availability: InStock
Author: Caliber

Implement LLMProvider interfaces and wire new providers into config, factory, and tests.

1.2k|119|Updated Mar 10, 2026

Search Tags:#testing #api #validation #llm #streaming #provider

Ready to run

npx skills add https://github.com/caliber-ai-org/ai-setup --skill llm-provider

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: llm-provider
Source: https://github.com/caliber-ai-org/ai-setup/tree/main/.cursor/skills/llm-provider
Command: npx skills add https://github.com/caliber-ai-org/ai-setup --skill llm-provider

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Streamlines adding new LLM providers to a unified interface.

Core Features & Use Cases

Implement the LLMProvider interface in a new provider under src/llm, ensuring both call() and stream() are implemented.
Wire the provider through config, factory, and tests to enable seamless integration and validation across environments.
Use cases include adding support for a new backend, integrating a new model API, or extending provider coverage.

Quick Start

Create a new provider file at src/llm/{provider-name}.ts and wire it into the config, factory, and tests.

Frequently Asked Questions about llm-provider

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

FAQPage Schema

How do I add a new LLM provider with streaming support to my application?▼

To add a new LLM provider, you implement the LLMProvider interface in a new file under src/llm, ensuring both call() and stream() methods are wired through the config, factory, and tests for seamless integration.

What is the standard structure for integrating a new model API backend?▼

The standard structure for integrating a new model API backend involves creating a provider file at src/llm/{provider-name}.ts that implements the LLMProvider interface, then routing it through a unified config and factory system.

How do I validate LLM provider behavior across development and production environments?▼

You validate LLM provider behavior across environments by wiring the new provider through config, factory, and tests that enforce standard API, model validation, and streaming semantics following the described interface.

Can I extend model support to a unified interface without breaking existing provider routing?▼

Yes, you can extend model support by creating a new provider file and wiring it through the factory routing system, which maintains a unified interface and enables seamless integration without breaking existing providers.

What's the best way to implement streaming responses for a new LLM API?▼

The best way to implement streaming responses for a new LLM API is to implement the stream() method within the LLMProvider interface, ensuring the provider config and factory routing support streaming semantics.