dspy-gepa-reflective

Community

Reflectively optimize agentic DSPy workflows.

AuthorOmidZamani
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill introduces GEPA, the newest DSPy optimizer that uses LLM reflection on full execution traces to search for Pareto-optimal improvements in agentic systems.

Core Features & Use Cases

  • Feedback-driven optimization: Metrics return (score, feedback) to guide improvements.
  • Phase-based workflow: Define a metric, configure a reflection LM, and compile an optimized program.
  • Production-ready: Apply GEPA to complex agents with tool use to improve reliability and performance.

Quick Start

Define a metric that returns a (score, feedback) pair, configure the reflection LM, set the auto mode, and compile the agent with GEPA.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: dspy-gepa-reflective
Download link: https://github.com/OmidZamani/dspy-skills/archive/main.zip#dspy-gepa-reflective

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.