Vibe Index
🎯

dspy

🎯Skill

from zpankz/mcp-skillset

VibeIndex|
What it does

Enables declarative programming of AI systems, automatically optimizing prompts and creating modular RAG pipelines using Stanford NLP's DSPy framework.

πŸ“¦

Part of

zpankz/mcp-skillset(137 items)

dspy

Installation

pip installInstall Python package
pip install dspy
πŸ“– Extracted from docs: zpankz/mcp-skillset
Need more details? View full documentation on GitHub β†’
3Installs
-
AddedFeb 4, 2026
View on GitHubBack to Skills

Skill Details

SKILL.md

"Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming. Use when you need to build complex AI systems, program LMs declaratively, optimize prompts automatically, create modular AI pipelines, or build RAG systems and agents."

Overview

# DSPy: Declarative Language Model Programming

Stanford NLP's framework for programmingβ€”not promptingβ€”language models.

Quick Start

```python

import dspy

# 1. Configure

dspy.settings.configure(lm=dspy.OpenAI(model='gpt-4o-mini'))

# 2. Define Module

qa = dspy.ChainOfThought("question -> answer")

# 3. Run

response = qa(question="What is the capital of France?")

print(response.answer)

```

Learning Path (DAG)

The DSPy framework follows a natural progression from core concepts through optimization to advanced applications. Use this directed acyclic graph to understand dependencies and navigate the skill components.

Foundation Layer (Start Here)

  1. [Configuring Language Models](./core/configuring-language-models.md)

- Prerequisites: None

- Next: Signatures, Modules, Datasets

  1. [Designing Signatures](./core/designing-signatures.md)

- Prerequisites: LM Configuration

- Next: Modules, Optimization

  1. [Building Modules](./core/building-modules.md)

- Prerequisites: Signatures

- Next: Optimization, Applications

  1. [Creating Datasets](./core/creating-datasets.md)

- Prerequisites: None

- Next: Optimization

Optimization Layer

  1. [Few-Shot Learning](./optimization/few-shot-learning.md)

- Prerequisites: Modules, Datasets

- Techniques: LabeledFewShot, BootstrapFewShot, KNNFewShot

- Next: Applications

  1. [Instruction Optimization](./optimization/instruction-optimization.md)

- Prerequisites: Modules, Datasets

- Techniques: COPRO, MIPROv2, GEPA

- Next: Applications

  1. [Finetuning Models](./optimization/finetuning-models.md)

- Prerequisites: Modules, Datasets

- Techniques: BootstrapFinetune

- Next: Applications

  1. [Ensemble Strategies](./optimization/ensemble-strategies.md)

- Prerequisites: Multiple trained modules

- Next: Applications

Application Layer

  1. [Building RAG Pipelines](./applications/building-rag-pipelines.md)

- Prerequisites: Modules, Optimization (recommended)

  1. [Evaluating Programs](./applications/evaluating-programs.md)

- Prerequisites: Modules, Datasets

  1. [Integrating Haystack](./applications/integrating-haystack.md)

- Prerequisites: Modules, Haystack knowledge

Advanced Features (Cross-Cutting)

  1. [Assertions & Validation](./advanced/assertions-validation.md)

- Prerequisites: Modules

  1. [Typed Outputs](./advanced/typed-outputs.md)

- Prerequisites: Signatures

  1. [Multi-Chain Comparison](./advanced/multi-chain-comparison.md)

- Prerequisites: ChainOfThought module

Reference Documentation

  • [Modules Reference](./references/modules-reference.md) - Complete module catalog
  • [Optimizers Reference](./references/optimizers-reference.md) - All optimization techniques
  • [Examples Reference](./references/examples-reference.md) - Real-world implementations

Common Workflows

Workflow 1: Basic QA System

  1. Configure LM β†’ Design Signature β†’ Build Module
  2. Path: configuring-language-models.md β†’ designing-signatures.md β†’ building-modules.md

Workflow 2: Optimized RAG System

  1. Configure LM β†’ Build RAG Module β†’ Optimize with Few-Shot β†’ Evaluate
  2. Path: configuring-language-models.md β†’ building-rag-pipelines.md β†’ few-shot-learning.md β†’ evaluating-programs.md

Workflow 3: Production Agent

  1. Configure LM β†’ Design Signature β†’ Build ReAct Module β†’ Add Assertions β†’ Optimize Instructions β†’ Evaluate
  2. Path: configuring-language-models.md β†’ designing-signatures.md β†’ building-modules.md β†’ assertions-validation.md β†’ instruction-optimization.md β†’ evaluating-programs.md

Installation

```bash

pip install dspy

# Or with specific providers

pip install dspy[anthropic] # Claude

pip install dspy[openai] # GPT

pip install dspy[all] # All providers

```

Additional Resources

  • Official Docs: dspy.ai
  • GitHub: github.com/stanfordnlp/dspy

More from this repository10

🎯
software-architecture🎯Skill

Provides expert guidance for designing high-quality, clean software architectures using domain-driven design principles and best practices.

🎯
csv-analysis🎯Skill

csv-analysis skill from zpankz/mcp-skillset

🎯
code refactoring🎯Skill

Skill

🎯
claude-docs-consultant🎯Skill

claude-docs-consultant skill from zpankz/mcp-skillset

🎯
cursor-skills🎯Skill

cursor-skills skill from zpankz/mcp-skillset

🎯
infranodus-orchestrator🎯Skill

Orchestrates complex knowledge graph analysis by integrating InfraNodus cloud tools with local reasoning and documentation skills for advanced research and content optimization.

🎯
refactor🎯Skill

Automatically analyzes and optimizes Claude's code architecture, identifying redundancies and improving system efficiency through meta-cognitive techniques.

🎯
code-refactor🎯Skill

Performs systematic code refactoring by finding and replacing patterns, identifiers, and API calls across multiple files while preserving code functionality.

🎯
agent-evaluation🎯Skill

Evaluates and improves Claude Code commands, skills, and agents by testing prompt effectiveness and validating context engineering choices.

🎯
network-meta-analysis-appraisal🎯Skill

network-meta-analysis-appraisal skill from zpankz/mcp-skillset