Skip to content

qredence/gepa-omni

v0.2.1MIT

Optimize scorable prompts, code, configs, schemas, SQL, regexes, and agent instructions with GEPA's Omni portfolio and fresh continuation workflow.

gepa-omni-skill

Automatically improve any scorable text artifact—prompts, programs, configs, specs, regex/SQL/schemas, agent scaffolds, or encoded search solutions—with the engine-pluggable optimize_anything API. Use when tuning a candidate from objective metrics, execution feedback, or LLM-as-judge scores, when designing an evaluator, or when running the default Omni portfolio across GEPA, AutoResearch, and Meta-Harness.

Read SKILL.md at the source

Pinned to revision 16ff1e54a06a, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.