ax-ai

Generate TypeScript provider setup and configuration code for @ax-llm/ax.

2.9k|186|Updated Feb 23, 2023
One-click install
npx skills add https://github.com/ax-llm/ax --skill ax-ai-ax-llm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ax-ai
Source: https://github.com/ax-llm/ax/tree/main/website/static/typescript/.well-known/agent-skills/ax-ai
Command: npx skills add https://github.com/ax-llm/ax --skill ax-ai-ax-llm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the guesswork from wiring up AI providers in @ax-llm/ax, helping you generate correct setup code instead of piecing together provider-specific details by hand.

Core Features & Use Cases

  • Provider Setup: Create clean initialization code for OpenAI, Anthropic, Google Gemini, Azure OpenAI, DeepSeek, Mistral, Cohere, Reka, Grok, and compatible endpoints.
  • Typed Model Workflows: Produce copyable patterns for chat, model presets, embeddings, audio transcription, text-to-speech, extended thinking, and context caching.
  • Practical Use Cases: Use it when you need a minimal provider bootstrap, a preset-based model selector, an embeddings example, or a safe configuration for provider-specific constraints like Azure deployment fields or Anthropic thinking rules.

Quick Start

Ask for a minimal TypeScript example that sets up your chosen provider with ai(), the right model config, and a chat call.

Frequently Asked Questions about ax-ai

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

FAQPage Schema
How do I set up an AI provider in TypeScript for @ax-llm/ax?

To set up an AI provider in TypeScript, initialize your chosen provider with the ai() function, configure the correct model presets, and execute a chat call using Ax-specific constraints.

How do I configure OpenAI and Anthropic providers with model presets in TypeScript?

Configuring OpenAI and Anthropic providers involves generating typed initialization code with model presets, ensuring runtime options respect provider-specific constraints like Anthropic thinking rules.

Can I use Azure OpenAI deployments with Ax for text-to-speech and audio transcription?

Yes, Azure OpenAI deployments are supported. You can generate copyable TypeScript examples for audio transcription, text-to-speech, and chat by applying Azure-specific deployment fields.

Does Ax support embeddings and context caching for Google Gemini and DeepSeek?

Yes, Ax supports typed workflows for embeddings and context caching across Google Gemini, DeepSeek, Mistral, Cohere, Reka, and Grok, providing copyable patterns for each provider.

What is the best way to handle provider-specific constraints like Anthropic extended thinking rules?

The best way to handle provider-specific constraints is to use generated configuration code that automatically respects limitations like Anthropic extended thinking rules and Azure deployment fields.

Why does my Ax provider initialization fail with incorrect model catalog lookups?

Ax provider initialization fails when model catalog lookups do not satisfy typed provider selection, requiring correct model presets and runtime options to generate safe, copyable TypeScript examples.