Ax For TypeScript

Build or debug TypeScript LLM applications with @ax-llm/ax. Use for Ax providers, structured generation, signatures, agents and tools, memory, MCP, workflows, audio, and optimization.

Install

Install only this skill for TypeScript:

Shell

npx skills add https://ax-llm.github.io/ax/typescript/ --skill 'ax-llm'

Published skill file: ax-llm/SKILL.md.

Source

Source: src/ax/skills/ax-llm.md
Version: 25.4.8

Skill Instructions

Use this entry point for @ax-llm/ax. Read the guides relevant to the task before writing code; the linked guides are bundled locally and need no extra skill installation. Load additional guides when the task crosses into another area.

Choose A Guide

Task	Read
Start a program, choose factories, or find basic examples	Quick reference
Configure providers, models, reasoning, embeddings, routing, or balancing	AI providers
Make typed decisions, use Jev, or retain probabilities and scores	Typesafe / Jev
Define signatures, field types, schemas, or validation	Signatures
Generate structured output, stream results, or attach tools	Generation
Build agents, use tools, or delegate to child agents	Agents
Configure code execution, RLM loops, sessions, or runtime state	Agent runtime
Choose context maps, trajectory policy, optimization, or recall	Agent context
Add persistent memory, recall, or dynamic skill discovery	Memory and skills
Inspect tracing, callbacks, logs, usage, or replay	Agent observability
Evaluate or tune agents and their playbooks	Agent optimization
Compose workflow graphs, branches, or parallel steps	Workflows
Connect MCP servers, transports, authentication, or catalogs	MCP
Ingest events, schedule wakeups, resume runs, or use stores and sinks	Event runtime
Transcribe, synthesize, or exchange conversational audio	Audio
Optimize prompts with BootstrapFewShot or GEPA	Optimization
Evolve reusable context or learn from run-end feedback	Playbooks
Improve candidates using reward scores and evaluator feedback	Refinement

Essential Conventions

Prefer ai(...), ax(...), agent(...), flow(...), optimize(...), s(...), and fn(...). Use string signatures or fluent f() field builders.
Check the installed package’s types and version before borrowing an example from another release. These guides ship with the package version above.
Use provider credentials from the application’s environment.

TypeScript

import { ai, ax } from '@ax-llm/ax';

const llm = ai({ name: 'openai', apiKey: process.env.OPENAI_APIKEY });
const answer = ax('question:string -> answer:string');
const result = await answer.forward(llm, { question: 'What is a signature?' });

For example, an agent with persistent recall needs the agent and memory guides; a provider-backed workflow needs the provider, generation, and workflow guides. Specialist skills remain optional for users who want separate skill entries.