skills.rest
ax-llm
ax-llmOFFICIAL
Explore all skills by this author →
GitHub

ax-python-agent

Build Python agents using the generated axllm package and its typed API.

2.9k|186|Updated Feb 23, 2023
Search Tags:#python#delegation#runtime#agents#mcp#tools#axllm
One-click install
npx skills add https://github.com/ax-llm/ax --skill ax-python-agent
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ax-python-agent
Source: https://github.com/ax-llm/ax/tree/main/website/static/python/.well-known/agent-skills/ax-python-agent
Command: npx skills add https://github.com/ax-llm/ax --skill ax-python-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you write Python code with the generated axllm package for building agents, delegating work to child agents, connecting tools and MCP clients, and managing runtime state without using TypeScript-only APIs.

Core Features & Use Cases

  • Agent construction: Create typed Python agents from concise signatures and call them with structured inputs and outputs.
  • Delegation and tools: Add child agents, tools, and MCP integrations for multi-step or multi-capability workflows.
  • Runtime control: Use clarification, discovery, recall, final, and respond envelopes, plus state save and restore for long-running tasks.
  • Example-driven implementation: Start from package examples and manifests to match the generated Python API exactly.
  • Use case: Build a support assistant that asks clarifying questions, calls tools, and returns a final typed response.

Quick Start

Ask the assistant to create a Python axllm agent for your task with the right tools, output schema, and runtime behavior.

Frequently Asked Questions about ax-python-agent

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

FAQPage Schema
How do I build a Python agent with axllm?▼

To build a Python agent with axllm, you create typed agents from concise signatures and call them with structured inputs and outputs, matching the generated package examples to ensure the API surface aligns exactly.

Can I use MCP clients and tools with Python agents?▼

Yes, you can add MCP clients and tools to Python agents for multi-step or multi-capability workflows, integrating child agents to handle complex delegation and multi-capability task execution within your generated package.

How does runtime state handling work for Python agents?▼

Runtime state handling for Python agents utilizes clarification, discovery, recall, final, and respond envelopes, plus state save and restore mechanisms to manage long-running tasks effectively across execution cycles.

Does axllm Python agent development support TypeScript-only APIs?▼

No, axllm Python agent development avoids TypeScript-only APIs unless you are editing the TypeScript package directly. You must follow generated package examples and manifests to match the typed Python API exactly.

What is the best way to add child delegation to a Python agent?▼

The best way to add child delegation to a Python agent is by attaching child agents and tools to the parent workflow, enabling multi-step task execution while following the generated package manifests for accurate typed API delegation.

Related Skills

Explore More Software Engineering Skills→
ax-llmax-llm
2.9k

ax-python-signature

Create typed Ax signatures for Python structured outputs with JSON Schema generation.

Official
Intermediate
ax-llmax-llm
2.9k

ax-cpp-agent

Write C++ Ax agent code with tools, child delegation, MCP clients, and typed envelopes.

Official
Advanced
lyq-linlyq-lin

mcp-builder

Build MCP servers with Python and TypeScript templates.

Community
Advanced
balkhaevbalkhaev

turborepo

Orchestrate JavaScript and TypeScript monorepo build pipelines with dependency graph analysis.

Community
Advanced