skills.rest
eugene-belkovich
eugene-belkovichCOMMUNITY
Explore all skills by this author →
GitHub

dspy-optimization

Automate DSPy MIPROv2 prompt optimization experiments for LLM classification tasks.

Updated Aug 27, 2026
Search Tags:#reproducibility#benchmarks#prompt-optimization#dspy#llm-classification#experiment-automation#mipro-v2
One-click install
npx skills add https://github.com/eugene-belkovich/ai-setup --skill dspy-optimization-eugene-belkovich
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dspy-optimization
Source: https://github.com/eugene-belkovich/ai-setup/tree/main/claude/profiles/work/skills/evals/dspy-optimization
Command: npx skills add https://github.com/eugene-belkovich/ai-setup --skill dspy-optimization-eugene-belkovich

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Runs DSPy MIPROv2 prompt optimization experiments to improve LLM classification prompts, enabling reproducible improvements and faster iteration.

Core Features & Use Cases

  • Experiment scaffolding: structure and run DSPy experiments from a centralized blueprint.
  • Metric-driven optimization: configure and evaluate MIPROv2 prompts with weighted metrics.
  • Reproducible workflows: capture results, prompts, and demos for audit and reuse.

Quick Start

Run the DSPy optimization workflow to generate an optimized controller for a follow-up classification task.

Frequently Asked Questions about dspy-optimization

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

FAQPage Schema
How do I automate DSPy MIPROv2 prompt optimization for LLM classification?▼

Automate DSPy MIPROv2 prompt optimization by defining a DSPy Signature, a Module, a weighted metric, and an experiment scaffold to generate optimized controllers for classification tasks.

What is needed to set up reproducible DSPy prompt optimization experiments?▼

Reproducible DSPy prompt optimization requires defining a DSPy Signature, a Module, a weighted metric, and an experiment scaffold to capture results, prompts, and demos for audit and reuse.

How do I structure end-to-end DSPy experiments for prompt optimization?▼

Structure end-to-end DSPy experiments using a centralized blueprint that handles data preparation, prompt design, evaluation, reporting, and integration of optimized prompts.

Does DSPy MIPROv2 support weighted metrics for evaluating LLM classification prompts?▼

Yes, DSPy MIPROv2 supports metric-driven optimization by allowing you to configure and evaluate prompts with weighted metrics for LLM classification tasks.

Can I capture and reuse optimized prompts from DSPy MIPROv2 experiments?▼

Yes, reproducible workflows capture optimized prompts, results, and demos during DSPy MIPROv2 experiments, preserving traceability for audit and reuse.

What's the best way to improve LLM classification prompts with DSPy?▼

Use DSPy MIPROv2 prompt optimization to apply metric-driven evaluation and experiment scaffolding, enabling faster iteration and reproducible improvements for LLM classification prompts.

Related Skills

Explore More Data & Analytics Skills→
bobmatnycbobmatnyc
3

dspy-framework

Automate prompt optimization with a declarative DSL for LLM workflows.

Community
Advanced
yogi100xyogi100x
1

Evaluation Pipeline

Automate end-to-end LLM evaluation pipelines with benchmarks, human evaluation, and automated scoring.

Community
Advanced
DrLuggelsDrLuggels
3

llm-evaluation

Evaluate LLM applications with automated metrics, human feedback, and benchmarking.

Community
Advanced
8b-is8b-is

dspy-ruby

Build type-safe DSPy.rb workflows with signatures, modules, and provider configurations.

Official
Intermediate