skills.rest
achatt89
achatt89COMMUNITY
Explore all skills by this author →
WebsiteGitHub

ax

Build type-safe LLM applications with streaming and multi-provider support.

1|Updated Feb 25, 2026
Search Tags:#llm#workflows#type-safe#signatures#generators#streams#ax
One-click install
npx skills add https://github.com/achatt89/sylva --skill ax
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ax
Source: https://github.com/achatt89/sylva/tree/main/.claude/skills/ax
Command: npx skills add https://github.com/achatt89/sylva --skill ax

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ax helps developers build LLM-powered applications with type-safe signatures, streaming support, and multi-provider compatibility.

Core Features & Use Cases

  • Type-safe signatures with f() fluent builder
  • Streaming support for real-time outputs
  • Multi-provider compatibility across OpenAI, Anthropic, Gemini, and others
  • Agents, flows, and tools (AxGen, AxAgent, AxFlow) for complex workflows
  • Examples and ready-to-use generators to accelerate development

Quick Start

Install the Ax library, import ax and f, then create a typed generator and forward to an LLM.

Frequently Asked Questions about ax

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

FAQPage Schema
How do I build type-safe LLM applications with streaming support?▼

You can build type-safe LLM applications by using fluent builder signatures to define typed generators, enabling structured inputs and real-time streaming outputs across multiple LLM providers.

What is the best way to orchestrate complex LLM workflows across different providers?▼

Orchestrate complex LLM workflows across providers like OpenAI and Anthropic by composing agents, flows, and generators, ensuring multi-provider compatibility and structured execution.

How do I create typed generators for LLM processing?▼

Create typed generators by importing the core library modules, using a fluent builder function to define type-safe signatures, and forwarding the structured output directly to an LLM.

Can I use this approach to integrate OpenAI, Anthropic, and Gemini models in one application?▼

Yes, the framework supports multi-provider compatibility, allowing developers to integrate OpenAI, Anthropic, and Gemini models within a single type-safe application architecture.

What are type-safe signatures in LLM app development?▼

Type-safe signatures in LLM app development define strict input and output contracts for generators and agents, preventing runtime type errors and ensuring robust structured data processing.

When should I use agents and flows instead of standalone generators for LLM tasks?▼

Use agents and flows instead of standalone generators when your LLM tasks require complex, multi-step orchestration, tool integration, and chained workflows to process dynamic inputs.

Related Skills

Explore More Software Engineering Skills→
PostHogPostHog
58

llm-analytics-setup

Wrap LLM SDKs with PostHog instrumentation to emit generation and trace events.

Official
Intermediate
ax-llmax-llm
2.9k

ax-llm

Build typed LLM applications with Ax in TypeScript.

Official
Advanced
bugrabilgebugrabilge
10

rag-implementation

Integrate vector databases and semantic search to build RAG pipelines for LLM applications.

Community
Advanced
nimeshgurungnimeshgurung

senior-prompt-engineer

Design and optimize LLM prompts with RAG and agent workflows.

Community
Advanced