dspy
Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineering
npx skills add majiayu000/claude-skill-registry --skill dspy-vamseeachanta-workspace-hub --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Compiles prompts into self-improving pipelines by combining signatures, modules, optimizers, and programmatic prompt engineering. It supports programmatic prompt construction, automated prompt optimization, few-shot learning, and multi-step reasoning through chain-of-thought capabilities, along with retrieval integration and metric evaluation.
How it works
The skill provides examples and scaffolding for:
- Defining input/output signatures (e.g., Python classes with InputField and OutputField) and using them directly with a predictor (dspy.Predict).
- Building module pipelines, including ChainOfThought reasoning, multi-stage processing, and RAG patterns (retrieval-augmented generation).
- Implementing ReAct-style tool use and multi-hop RAG workflows to answer complex questions.
- Employing optimizers (BootstrapFewShot, BootstrapFewShotWithRandomSearch, MIPRO) to automatically improve prompts using labeled data and metrics. The workflows show creating training data, a metric function, and compiling an optimized module or classifier, then executing it with new inputs.
- Integrating retrieval with a retriever (ChromadbRM) and configuring a retrieval-augmented generation pipeline that outputs an answer and source passages.
When to use it
USE when:
- You need to optimize prompts programmatically rather than manually
- Building pipelines where prompt quality is critical to success
- You want reproducible, testable prompt engineering
- Working with complex multi-step reasoning tasks
- You need to automatically find effective few-shot examples
- Building systems that improve with more training data
- You require systematic evaluation and comparison of prompt strategies
- You want to abstract away prompt engineering from application logic
DONT USE when:
- You have simple single-shot prompts that work as-is
- You need fine-grained control over exact prompt wording
- Building applications with minimal LLM interactions
- Prototyping where rapid iteration is more important than optimization
- Resource-constrained environments (optimization requires API calls)
What it can touch
The skill references tools such as:
- Read, Write, Bash, Grep
- Python-based platform with modules like dspy, ChromadbRM, and OpenAI integrations
- LLM providers via Python imports (e.g., OpenAI, anthropic)
- Pip-installable packages: dspy-ai, chromadb, faiss-cpu, pandas, scikit-learn
Caveats
- License: MIT
- Triggered manually and not auto-executed by default
- Requires API keys and external services for retrieval and LLM access
- Uses experimental DSPy constructs (Signatures, Modules, Optimizers) that depend on the DSPy framework conventions
# DSPy Skill > Compile prompts into self-improving pipelines with programmatic prompt engineering. ## Quick Start ```bash # Install DSPy pip install dspy-ai # Optional: For retrieval pip install chromadb faiss-cpu # Set API key export OPENAI_API_KEY="your-api-key" ``` ## When to Use This Skill **USE when:** - Need to optimize prompts programmatically rather than manually - Building pipelines where prompt quality is critical to success - Want reproducible, testable prompt engineering - Working with complex multi-step reasoning tasks - Need to automatically find effective few-shot examples - Building systems that improve with more training data - Require systematic evaluation and comparison of prompt strategies - Want to abstract away prompt engineering from application logic **DON'T USE when:** - Simple single-shot prompts that work well as-is - Need fine-grained control over exact prompt wording - Building applications with minimal LLM interactions - Prototyping where rapid iteration is more important than optimization - Resource-constrained environments (optimization requires API calls) ## Prerequisites ```bash # Core installation pip install dspy-ai>=2.4.0 # For vector retrieval
- Quick Start
- When to Use This Skill
- Prerequisites
- Core Concepts
- DSPy Philosophy
- Core Capabilities
- 1. Signatures
- 2. Modules
- 3. Retrieval-Augmented Generation
- 4. Optimizers
- 5. Evaluation and Metrics
- 6. Saving and Loading
- Complete Examples
- Example 1: Engineering Report Analysis Pipeline
Install DSPy pip install dspy-ai pip install chromadb faiss-cpu Set API key export OPENAI_API_KEY="your-api-key" Core installation pip install dspy-ai>=2.4.0 For vector retrieval pip install chromadb>=0.4.0 faiss-cpu>=1.7.0 For different LLM providers
What does the dspy skill do?
Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineering
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill dspy-vamseeachanta-workspace-hub --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.