ax-agent-memory-skills

Generate AxAgent memory retrieval and dynamic skill-loading 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-agent-memory-skills
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ax-agent-memory-skills
Source: https://github.com/ax-llm/ax/tree/main/website/static/typescript/.well-known/agent-skills/ax-agent-memory-skills
Command: npx skills add https://github.com/ax-llm/ax --skill ax-agent-memory-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you generate correct Ax agent code for persistent context maps, memory retrieval, and dynamic skill loading without breaking the framework's runtime rules.

Core Features & Use Cases

It covers contextMap setup, memory recall flows, skillsCatalog and discover based loading, loaded and used tracking, and safe persistence across forward calls. Use it when building agents that need to remember prior decisions, pull task-relevant notes from a store, or load runbook style guidance only when needed.

Quick Start

Ask the assistant to produce an Ax agent example that uses recall for memories, discover for skills, and follows the loading and tracking rules from this skill.

Frequently Asked Questions about ax-agent-memory-skills

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

FAQPage Schema
How do I implement dynamic skill loading and memory retrieval for Ax agents?

To implement dynamic skill loading and memory retrieval for Ax agents, generate code that sets up context maps, uses recall for memories, and applies discover for skills while adhering to callback contracts and deduplication rules.

What is a context map and how does it manage persistent memory in TypeScript agents?

A context map is a structure that manages persistent memory in TypeScript agents by tracking loaded and used skills across forward calls, ensuring safe state persistence and correct prompt-stage separation for memories and skills.

How do I load task-relevant runbooks on demand without breaking agent runtime rules?

Load task-relevant runbooks on demand by using a skillsCatalog with discover-based loading, which pulls runbook style guidance only when needed while enforcing preload rules and tracking loaded and used states.

Does @ax-llm/ax support separate prompt stages for memories and skills?

Yes, @ax-llm/ax supports separate prompt stages for memories and skills, requiring strict adherence to Ax callback contracts and prompt-stage separation to prevent runtime conflicts during memory recall and skill execution.

Why does my Ax agent load duplicate skills or memories during recall?

Your Ax agent loads duplicate skills or memories during recall when deduplication behavior is not correctly applied, which requires following specific loading rules and tracking loaded states across forward calls.