Generate Python code for Ax GEPA optimization workflows in axllm.
npx skills add https://github.com/ax-llm/ax --skill ax-python-gepa
Please help me install this Agent Skill. Skill: ax-python-gepa Source: https://github.com/ax-llm/ax/tree/main/website/static/python/.well-known/agent-skills/ax-python-gepa Command: npx skills add https://github.com/ax-llm/ax --skill ax-python-gepa
This Skill helps you write and reason about Python code for Ax GEPA optimization workflows in the generated axllm package, especially when you need reliable syntax and package-specific behavior instead of guessing at the API.
Ask for Python code that uses axllm AxGEPA with a reflection client and evaluator to optimize my request and explain the result.
High-intent search queries and answers about installing and using this skill.
To optimize Python workflows using GEPA, you generate AxGEPA code with reflection clients and evaluators to refine prompts or programs. This process produces optimization artifacts and candidate states that you can inspect and apply within your Python project.
The best way to seed Ax GEPA optimization is to run BootstrapFewShot before the GEPA process. This provides initial demonstrations that seed the optimizer, allowing the AxGEPA engine to start from refined candidate states when evaluating Pareto tradeoffs.
Pareto tradeoffs and metric budgets in Ax optimization work by evaluating multiple competing metrics simultaneously within set constraints. The GEPA optimizer generates candidates and artifacts that balance these tradeoffs, allowing you to inspect and apply the best performing candidate state.
Yes, you can use axllm AxGEPA without an API key by leveraging its no-key runtime profiles. The generated Python package supports both no-key and provider-backed runtime profiles, ensuring syntax alignment for optimization workflows across different execution environments.
To inspect GEPA artifacts and optimizer state in Python, you generate AxGEPA code that outputs optimization artifacts during the workflow. You can then examine these artifacts and the resulting candidate state to understand Pareto tradeoffs and metric budget performance.
ax-llmGenerate Python AxGen code for typed structured generation workflows.
ax-llmImplement Rust code for Ax GEPA optimization with axllm.
ax-llmWrite C++ GEPA optimizer code for axllm projects.
ax-llmGenerate evaluator-driven optimization workflows for Python Ax agents with axllm.
