skills.rest
Qredence
QredenceOFFICIAL
Explore all skills by this author →
Website𝕏@agenticfleetGitHub

optimization

Automate iterative DSPy prompt and RLM skill bundle optimization with GEPA and MLflow tracking.

51|6|Updated Feb 7, 2026
Search Tags:#optimization#evaluation#pipeline#prompts#mlflow#rlm#gepa
One-click install
npx skills add https://github.com/Qredence/fleet-rlm --skill optimization-qredence
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: optimization
Source: https://github.com/Qredence/fleet-rlm/tree/main/src/fleet_rlm/scaffold/skills/optimization
Command: npx skills add https://github.com/Qredence/fleet-rlm --skill optimization-qredence

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

GEPA-driven optimization automates the iterative refinement of DSPy prompts and RLM skill bundles, enabling systematic performance improvements through verbal feedback and offline traces.

Core Features & Use Cases

  • GEPA-based prompt evolution for markdown skill prompts and module pipelines.
  • Integrated MLflow tracking of optimization runs, including before/after prompts, metrics, traces, and artifacts.
  • Supports dataset preparation and trace-driven evaluation to compare candidate prompts.

Quick Start

Run a GEPA optimization on a bundled skill to iteratively rewrite prompts and evaluate improvements.

Frequently Asked Questions about optimization

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

FAQPage Schema
How do I optimize DSPy prompts automatically using trace data?▼

DSPy prompt optimization can be automated using GEPA-driven iterative refinement, which leverages verbal feedback and offline trace bundles to systematically rewrite and evaluate candidate prompts for performance improvements.

Can I track DSPy prompt optimization runs with MLflow?▼

Yes, MLflow integration tracks optimization runs by logging before and after prompts, evaluation metrics, traces, and artifacts, enabling systematic comparison of candidate prompts across datasets.

What is GEPA-based prompt evolution for machine learning pipelines?▼

GEPA-based prompt evolution is an iterative optimization technique that refines markdown skill prompts and module pipelines using verbal feedback and offline traces to achieve systematic performance gains.

Do I need offline trace bundles to run prompt optimization?▼

Yes, the optimization process requires support for offline trace bundles alongside MLflow integration to evaluate candidate prompts and track provenance metadata without overwriting source skills.

How do I compare optimization runs across different prompt versions?▼

MLflow tracking enables comparison of optimization runs by recording before and after prompts, evaluation metrics, and trace artifacts, allowing you to evaluate candidate prompts against training datasets.

Related Skills

Explore More Software Engineering Skills→
itsadijmbtitsadijmbt
1

skill-test

Evaluate and optimize Databricks agent skills against ground truth YAML test cases.

Community
Advanced
o2alexanderfedino2alexanderfedin
15

create-meta-prompts

Create optimized prompts for Claude-to-Claude pipelines with XML metadata.

Community
Advanced
cabeznocabezno

dspy

Define declarative LM programs and optimize prompts with DSPy.

Community
Advanced
OmidZamaniOmidZamani
120

dspy-haystack-integration

Optimize Haystack pipeline prompts with DSPy and custom metrics.

Community
Advanced