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

ax-go-agent-optimize

Optimize Ax agents and Go components with BootstrapFewShot or GEPA.

2.9k|186|Updated Feb 23, 2023
Search Tags:#go#agent optimization#ax#evaluators#gepa#bootstrap few shot#optimizer artifacts
One-click install
npx skills add https://github.com/ax-llm/ax --skill ax-go-agent-optimize
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ax-go-agent-optimize
Source: https://github.com/ax-llm/ax/tree/main/website/static/go/.well-known/agent-skills/ax-go-agent-optimize
Command: npx skills add https://github.com/ax-llm/ax --skill ax-go-agent-optimize

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you build and tune Ax agent optimization workflows in Go without guessing at the correct package API, evaluator shape, or optimizer configuration.

Core Features & Use Cases

  • Agent Optimization: Refine Ax agents and reusable program components with BootstrapFewShot or GEPA.
  • Evaluators and Judges: Create deterministic evaluator callbacks and scoring logic for optimization runs.
  • Artifacts and Budgets: Persist optimizer artifacts and keep runs bounded with explicit datasets, row limits, and execution budgets.
  • Use Case: A Go developer can use this Skill to turn a rough agent into a more reliable production workflow by validating prompts, comparing variants, and saving the best optimized result.

Quick Start

Ask the assistant to use the ax-go-agent-optimize skill to design a bounded Go optimization workflow for an Ax agent, including the evaluator, optimizer choice, and artifact persistence.

Frequently Asked Questions about ax-go-agent-optimize

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

FAQPage Schema
How do I optimize Go agents using BootstrapFewShot and GEPA?▼

To optimize Go agents, you apply BootstrapFewShot or GEPA to refine Ax agents and reusable program components. This process uses evaluator callbacks and scoring logic to validate prompts and compare variants for improved reliability.

What is the best way to create deterministic evaluator callbacks for Ax agent optimization in Go?▼

Deterministic evaluator callbacks for Ax agent optimization are created by defining judge logic and scoring rules within your generated Go API package. This ensures consistent evaluation across bounded optimization runs.

How do I persist optimizer artifacts and keep runs bounded in a Go workflow?▼

You persist optimizer artifacts and keep runs bounded by configuring explicit datasets, row limits, and execution budgets within your generated Ax Go API package. This ensures optimization runs remain controlled and reproducible.

Do I need an API key to run Ax agent optimization workflows in Go?▼

You do not always need an API key to run Ax agent optimization workflows in Go. The generated package supports safe no-key execution paths alongside provider-backed execution paths for validating prompts and comparing variants.

What are the limitations when applying GEPA to reusable Go program components?▼

When applying GEPA to reusable Go program components, limitations include the need for explicit datasets and execution budgets to keep runs bounded. You must also ensure your generated Ax Go API and capability manifests align correctly.

Related Skills

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

ax-go-agent-observability

Inspect Ax Go agent traces, usage, runtime envelopes, action logs, and replay state.

Official
Advanced
ax-llmax-llm
2.9k

ax-go-refine

Refine Go Ax generation workflows with evaluator feedback and optimizer APIs.

Official
Intermediate
ax-llmax-llm
2.9k

ax-python-agent-optimize

Generate evaluator-driven optimization workflows for Python Ax agents with axllm.

Official
Advanced
ax-llmax-llm
2.9k

ax-java-gepa

Write Java code for GEPA optimization with reflection clients and Pareto tradeoffs.

Official
Advanced