dspy

Develop AI systems with declarative programming and automatic prompt optimization.

1|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/informatico-madrid/Architect-Expert-Gap-Forge --skill dspy-informatico-madrid
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dspy
Source: https://github.com/informatico-madrid/Architect-Expert-Gap-Forge/tree/main/.github/skills/dspy
Command: npx skills add https://github.com/informatico-madrid/Architect-Expert-Gap-Forge --skill dspy-informatico-madrid

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill simplifies the creation of complex AI systems by enabling declarative programming, automatic prompt optimization, and modular RAG systems and agents.

Core Features & Use Cases

  • Declarative LM Programming: Define AI tasks using signatures (input → output) instead of manual prompt engineering.
  • Automatic Prompt Optimization: Improve LM performance systematically using data-driven methods.
  • Modular AI Pipelines: Build maintainable and portable AI systems with reusable components.
  • Use Case: Develop a customer support bot that can understand user intent, retrieve relevant information, and generate helpful responses, all while automatically optimizing its prompts for better accuracy and efficiency.

Quick Start

Use the dspy skill to build a basic question answering system with a Claude language model.

Frequently Asked Questions about dspy

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

FAQPage Schema
How do I stop manually writing prompts and start automatic prompt optimization for LLMs?

Automatic prompt optimization replaces manual prompt engineering by using declarative signatures to define input and output tasks, allowing data-driven methods to systematically improve LM performance.

What is declarative LM programming and how does it help build AI pipelines?

Declarative LM programming defines AI tasks using signatures for input and output instead of manual prompts, facilitating the creation of modular, maintainable, and portable AI pipelines with reusable components.

Can I build modular RAG systems and agents without manual prompt engineering?

Yes, you can build modular RAG systems and agents by defining tasks declaratively, which enables automatic prompt optimization and systematic LM programming for robust and maintainable pipelines.

Does dspy support structured output and assertion-driven optimization for agents?

Yes, dspy supports advanced patterns like structured output and assertion-driven optimization, enabling systematic LM programming and the development of complex, robust AI agents and pipelines.

What is the best way to develop complex AI systems with various LM providers?

The best way to develop complex AI systems is using declarative programming and modular design, which supports various LM providers and facilitates systematic LM programming with automatic prompt optimization.

Why use declarative signatures instead of manual prompt engineering for customer support bots?

Declarative signatures allow customer support bots to understand intent and retrieve information automatically, while automatic prompt optimization improves response accuracy and efficiency without manual prompt tuning.