Write C++ GEPA optimizer code for axllm projects.
npx skills add https://github.com/ax-llm/ax --skill ax-cpp-gepa
Please help me install this Agent Skill. Skill: ax-cpp-gepa Source: https://github.com/ax-llm/ax/tree/main/website/static/cpp/.well-known/agent-skills/ax-cpp-gepa Command: npx skills add https://github.com/ax-llm/ax --skill ax-cpp-gepa
This Skill helps you write Ax GEPA code in C++ without guessing the generated axllm API, package patterns, or optimizer workflow.
Create a C++ GEPA example with axllm that uses the generated package API, a reflection client, and an evaluator.
High-intent search queries and answers about installing and using this skill.
You implement a GEPA optimizer in C++ by generating optimization flows that handle Pareto tradeoffs, metric budgets, and optimizer state using the generated package API and AxIR-aligned optimizer calls.
You add reflection clients and evaluator hooks by generating GEPA optimization flows that integrate directly with the generated axllm package API and native example patterns in your C++ project.
Yes, you can use GEPA optimizers in C++ without an API key by safely selecting a no-key workflow configuration during the optimizer setup and execution process.
You bootstrap few-shot seeding and manage optimizer state by writing C++ GEPA code that utilizes checkpointing and artifact inspection to maintain and evaluate optimizer conditions throughout the optimization lifecycle.
The best way to port Ax optimization logic into native C++ is to use AxIR-aligned optimizer calls, native example patterns, and the generated package API to ensure correct GEPA integration and artifact inspection.
ax-llmRefine C++ Ax generation workflows with reward-scored optimizer feedback loops.
ax-llmWrite Java code for GEPA optimization with reflection clients and Pareto tradeoffs.
ax-llmRefine Rust generation outputs using AxGEPA and bootstrap few-shot optimizers.
ax-llmGenerate Python code for Ax GEPA optimization workflows in axllm.
