ax-rust-agent

Build Rust axllm agents with tools, delegation, and stateful workflows.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you write correct Rust code for Ax-based agents without guessing the native API shape, especially when you need tools, child delegation, MCP clients, clarification flows, or saved runtime state.

Core Features & Use Cases

  • Agent Construction: Create axllm agents from a typed signature and call them with the generated Rust API.
  • Tooling and Delegation: Build agents that use tools, child agents, or MCP transports for multi-step workflows.
  • Runtime Control: Use clarification, discovery, recall, final, and respond envelopes, including direct-response skipping when no tools are needed.
  • Stateful Workflows: Save and restore agent runtime state for long-running or interruptible tasks.
  • Use Case: An assistant can generate Rust code for a customer-support agent that collects missing details, calls tools, and returns a typed final answer.

Quick Start

Ask the assistant to use this Skill to generate a Rust axllm agent with tools, MCP support, and a direct-response envelope for a no-tool task.

Frequently Asked Questions about ax-rust-agent

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

FAQPage Schema
How do I build stateful Rust AI agents with tool-using capabilities?

Build stateful Rust AI agents by generating axllm agents from typed signatures, enabling them to use tools, delegate to child agents, and persist runtime state. The Skill provides typed responses and guardrails for provider credentials.

How do I implement clarification and discovery flows in a Rust LLM agent?

Implement clarification and discovery flows in a Rust LLM agent by applying clarification, discovery, recall, and final envelopes. This allows the agent to collect missing details before returning a typed final answer.

Can I use MCP clients with Rust agents for multi-step workflows?

Yes, you can use MCP clients with Rust agents. The Skill supports building agents that utilize MCP transports and child delegation to execute complex, multi-step workflows with no-key transports.

What is the best way to save and restore runtime state for long-running Rust agents?

The best way to save and restore runtime state for long-running Rust agents is using the Skill's stateful workflow features. It supports runtime state persistence for long-running or interruptible tasks via generated package APIs.

Does the ax-rust-agent Skill require generated package APIs for validation?

Yes, the ax-rust-agent Skill requires generated package APIs. It relies on AxIR-aligned examples, runtime profile support, and package truth validation to ensure correct Rust code generation for Ax-based agents.

When should I use direct-response skipping in a Rust LLM agent?

Use direct-response skipping in a Rust LLM agent when no tools are needed for the task. The Skill optimizes workflows by allowing direct-response envelopes, bypassing unnecessary tool-calling overhead.