Skills for eval-driven agent optimization

OptimizeSpec helps you make your agent better in a measured way, even if you have never built an eval suite or optimization loop before.

You start with a plain-language goal, such as "make support-triage answers more complete."

OptimizeSpec guides your coding agent through a spec-driven development workflow to turn your request into an eval spec, scoring criteria, and optimization code.

Even if you haven’t collected evals yet, this exercise will give you an understanding of what your evals should look like and what you need to collect.

Under the hood, it builds on GEPA, a powerful optimization system. The spec-driven development workflow was inspired by

OpenSpec.

The spec-driven development workflow makes it easy for your coding agents to build the complex optimization system while aligning you with you at a higher level on the goals and design of the system.

I built this because there's no one-size-fits-all with agents and the optimization system often needs to be customized for the agent harness.

If you try it, let me know if it helped and if you have any suggestions!

Repo (Please give it a ⭐️ if it's useful!)