Evaluates and optimizes agent skills using a DSPy-powered GEPA (Generate/Evaluate/Propose/Apply) loop. Loads scenario YAML files as DSPy datasets, scores outputs with pattern-matching metrics, and optimizes prompts via BootstrapFewShot or MIPROv2 teleprompters. Also generates new scenario YAML files from skill descriptions.
Quickly install dspy-gepa AI skill to your development environment via command line
Source: qredence/skills.
GEPA is a DSPy-powered tool for evaluating, optimizing, and generating skill scenarios.
Point GEPA at an existing skill to generate new test scenarios:
See references/gepa-architecture.md for the full GEPA loop design and DSPy mapping.
Evaluates and optimizes agent skills using a DSPy-powered GEPA (Generate/Evaluate/Propose/Apply) loop. Loads scenario YAML files as DSPy datasets, scores outputs with pattern-matching metrics, and optimizes prompts via BootstrapFewShot or MIPROv2 teleprompters. Also generates new scenario YAML files from skill descriptions. Source: qredence/skills.
Stable fields and commands for AI/search citations.
npx skills add https://github.com/qredence/skills --skill dspy-gepaEvaluates and optimizes agent skills using a DSPy-powered GEPA (Generate/Evaluate/Propose/Apply) loop. Loads scenario YAML files as DSPy datasets, scores outputs with pattern-matching metrics, and optimizes prompts via BootstrapFewShot or MIPROv2 teleprompters. Also generates new scenario YAML files from skill descriptions. Source: qredence/skills.
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/qredence/skills --skill dspy-gepa Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw
https://github.com/qredence/skills