Agent Context Use when writing Python code with `axllm` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents. python skills skill-agent-context packages/python/skills/ax-python-agent-context/SKILL.md skill Agent Context

AxAgent Context Selection For Python

Use when writing Python code with axllm for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.

Install

Install only this skill for Python:

Shell
npx skills add https://ax-llm.github.io/ax/python/ --skill 'ax-python-agent-context'

Published skill file: ax-python-agent-context/SKILL.md.

Source

Skill Instructions

This skill helps an agent write Python code with the generated Ax package axllm. Use the generated package API, examples, and manifests; do not import TypeScript-only APIs unless you are editing the TypeScript package.

When To Use

  • Choose between contextMap, contextPolicy, optimization, and recall for a task.
  • Avoid mixing persistent corpus orientation with within-run compaction.
  • Route long-context agent work to the right generated-package feature.

Package Facts

  • Language: Python.
  • Package: axllm.
  • Package API docs: API.md and axir-api.json.
  • Capability manifest: axir-capabilities.json.
  • Runnable examples: examples/.
  • Real network support: yes.
  • Scripted no-key transport support: yes.
  • Runtime profiles: javascript-quickjs, python-pyodide.

Core Pattern

Python
from axllm import agent

helper = agent("question:string -> answer:string")
out = helper.forward(llm, {"question": "How should I proceed?"})

Relevant API Surface

  • Agents And RLM: agent, AxAgent
  • Runtime Profiles: ProcessCodeRuntime, RuntimeCapabilities, RuntimeEnvelope, javascript-quickjs, python-pyodide
  • Optimizers: optimize, AxBootstrapFewShot, AxGEPA, OptimizerEngine, OptimizerEvaluator

Guardrails

  • Start from package examples for exact native syntax before inventing a new call shape.
  • Use provider-api examples only when the user explicitly has provider credentials available.
  • Use no-key examples for deterministic local checks and provider request mapping.
  • Treat AxIR as the source of generated package truth: if package docs disagree with source code, update the compiler and regenerate packages.
  • Do not copy repo-maintainer skills from tools/*/skills/ into user packages.
Docs