Verified:GitHub

mlops/dspy

Assemble and optimize AI systems with modular declarative components.

2|1|Updated May 10, 2026

Search Tags:#prompt engineering #prompt optimization #declarative programming #modular AI #automated tuning #self-improving systems

Ready to run

npx skills add https://github.com/zli5460/hermes-agent-X-Phoenix-Architecture --skill mlops-dspy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: mlops/dspy
Source: https://github.com/zli5460/hermes-agent-X-Phoenix-Architecture/tree/main/skills/mlops/research/dspy
Command: npx skills add https://github.com/zli5460/hermes-agent-X-Phoenix-Architecture --skill mlops-dspy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references/optimizers.md (resource) and references/modules.md (resource) components.

What problem does it solve?

It streamlines the development of complex AI workflows by providing declarative modules and optimization techniques for prompt engineering.

Core Features & Use Cases

Declarative Programming: Create modular AI pipelines with clear input-output signatures.
Prompt Optimization: Automate prompt design and refinement via data-driven optimizers.
Use Case: Automate question-answering systems that self-improve over time with minimal manual tuning.

Quick Start

Use DSPy to define a question-answer module and improve its accuracy by running an optimizer over training examples.

Frequently Asked Questions about mlops/dspy

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

FAQPage Schema

How do I use declarative programming to build modular AI pipelines?▼

Declarative programming builds modular AI pipelines by defining clear input-output signatures for each component. You assemble these modules to structure complex workflows without manually writing imperative control flow logic for every step.

What is automated prompt optimization and how does it work?▼

Automated prompt optimization refines prompt designs using data-driven optimizers rather than manual tuning. It analyzes training examples to iteratively adjust and improve prompt instructions, enhancing AI accuracy and reducing manual engineering effort.

How do I create self-improving AI systems with minimal manual tuning?▼

Self-improving AI systems automate refinement by running data-driven optimizers over training examples. This process iteratively adjusts declarative prompt modules to increase accuracy over time without requiring continuous manual prompt adjustments.

Can I automate question-answering systems to improve accuracy over time?▼

Automating question-answering systems involves defining a declarative module and running an optimizer over training examples. This data-driven approach automatically refines prompts, allowing the system to self-improve its accuracy over time.

Does prompt optimization work without dependencies?▼

Prompt optimization can work without external dependencies by using internal scripts and references. The system provides built-in modules and optimizers to assemble and tune AI pipelines independently without requiring external libraries.

What are the limitations of declarative prompt modules?▼

Declarative prompt modules require structured input-output signatures and sufficient training examples for optimizers. Systems may struggle with highly ambiguous tasks lacking clear definitions or when insufficient data exists to drive automated tuning effectively.