Agent Skills

Install the Ax skills for Python into your coding agent workspace.

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

The URL publishes a well-known agent-skills index for this language:

https://ax-llm.github.io/ax/python/.well-known/agent-skills/index.json

Published Skills

• Quick Reference - ax-python-llm: Use when writing Python code with axllm for using the generated Ax package, factory functions, package docs, examples, and API reference. Source: packages/python/skills/ax-python-llm/SKILL.md.
• AI - ax-python-ai: Use when writing Python code with axllm for provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers. Source: packages/python/skills/ax-python-ai/SKILL.md.
• Audio - ax-python-audio: Use when writing Python code with axllm for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples. Source: packages/python/skills/ax-python-audio/SKILL.md.
• Signatures - ax-python-signature: Use when writing Python code with axllm for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes. Source: packages/python/skills/ax-python-signature/SKILL.md.
• Generation - ax-python-gen: Use when writing Python code with axllm for AxGen programs, forward calls, streaming, tools, assertions, traces, usage, and output parsing. Source: packages/python/skills/ax-python-gen/SKILL.md.
• Flow - ax-python-flow: Use when writing Python code with axllm for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components. Source: packages/python/skills/ax-python-flow/SKILL.md.
• Agent - ax-python-agent: Use when writing Python code with axllm for agents, child delegation, tools, MCP, clarification, runtime state, and final typed responses. Source: packages/python/skills/ax-python-agent/SKILL.md.
• Agent RLM - ax-python-agent-rlm: Use when writing Python code with axllm for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles. Source: packages/python/skills/ax-python-agent-rlm/SKILL.md.
• Memory & Skills - ax-python-agent-memory-skills: Use when writing Python code with axllm for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking. Source: packages/python/skills/ax-python-agent-memory-skills/SKILL.md.
• Observability - ax-python-agent-observability: Use when writing Python code with axllm for agent tracing, usage accounting, action logs, runtime diagnostics, replay, and production debugging. Source: packages/python/skills/ax-python-agent-observability/SKILL.md.
• Agent Optimize - ax-python-agent-optimize: Use when writing Python code with axllm for agent optimization, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA. Source: packages/python/skills/ax-python-agent-optimize/SKILL.md.
• GEPA - ax-python-gepa: Use when writing Python code with axllm for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts. Source: packages/python/skills/ax-python-gepa/SKILL.md.
• Refinement - ax-python-refine: Use when writing Python code with axllm for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns. Source: packages/python/skills/ax-python-refine/SKILL.md.

Source

packages/python/skills/**/SKILL.md, generated by the AxIR package compiler.

Generated language package skills are emitted by the AxIR compiler together with README.md, API.md, axir-api.json, examples, and capability manifests. The website reads those generated package skill files and publishes installable well-known artifacts.

Pages

• Quick Reference Use when writing Python code with `axllm` for using the generated Ax package, factory functions, package docs, examples, and API reference.
• AI Use when writing Python code with `axllm` for provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.
• Audio Use when writing Python code with `axllm` for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.
• Signatures Use when writing Python code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.
• Generation Use when writing Python code with `axllm` for AxGen programs, forward calls, streaming, tools, assertions, traces, usage, and output parsing.
• Flow Use when writing Python code with `axllm` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.
• Agent Use when writing Python code with `axllm` for agents, child delegation, tools, MCP, clarification, runtime state, and final typed responses.
• Agent RLM Use when writing Python code with `axllm` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.
• Memory & Skills Use when writing Python code with `axllm` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
• Observability Use when writing Python code with `axllm` for agent tracing, usage accounting, action logs, runtime diagnostics, replay, and production debugging.
• Agent Optimize Use when writing Python code with `axllm` for agent optimization, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.
• GEPA Use when writing Python code with `axllm` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.
• Refinement Use when writing Python code with `axllm` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.