DSPy Skills Collection

A Claude Code plugin containing 22 focused skills for programming, optimizing, evaluating, and deploying LLM applications with DSPy.

Stable DSPy baseline: 3.2.1, released May 5, 2026. Install the stable series with:

pip install -U "dspy>=3.2.1,<3.3"

DSPy 3.3.0b1 is a prerelease published May 28, 2026. See prerelease notes before opting in.

Skills Index

Start Here

Skill Use it for
dspy-signature-designer Typed signatures and structured outputs
dspy-custom-module-design Reusable dspy.Module architecture
dspy-evaluation-suite Metrics, baselines, and comparisons
dspy-optimizer-selection Choosing among DSPy's optimizer families

Retrieval and Data

Skill Use it for
dspy-rag-pipeline RAG and multi-hop retrieval pipelines
dspy-embedding-retrieval Embedder, Embeddings, FAISS, and local corpora
dspy-haystack-integration Optimizing Haystack-backed pipelines

Agents and Reasoning

Skill Use it for
dspy-react-agent-builder ReAct tool agents
dspy-mcp-tool-integration MCP tools in DSPy agents
dspy-reasoning-modules RLM, ProgramOfThought, CodeAct, and Parallel
dspy-advanced-module-composition Ensembles and composed modules

Optimizers

Skill Use it for
dspy-bootstrap-fewshot Fast demo bootstrapping
dspy-miprov2-optimizer Instruction and demo search
dspy-gepa-reflective Reflective instruction optimization
dspy-simba-optimizer Mini-batch introspective optimization
dspy-finetune-bootstrap Weight optimization and distillation
dspy-better-together Sequencing prompt and weight optimizers
dspy-optimize-anything GEPA optimization for text artifacts outside DSPy

Production and Interfaces

Skill Use it for
dspy-output-refinement-constraints Refine and BestOfN constraints
dspy-adapters-multimodal Adapters, native tools, image, audio, and file inputs
dspy-production-deployment Cache hardening, save/load, usage tracking, async, and streaming
dspy-debugging-observability Inspection, callbacks, and MLflow tracing

Typical Workflow

  1. Define typed inputs and outputs with dspy-signature-designer.
  2. Build a module, RAG pipeline, or agent.
  3. Establish a baseline with dspy-evaluation-suite.
  4. Choose an optimizer with dspy-optimizer-selection.
  5. Harden the runtime with dspy-production-deployment.

Optional Dependencies

# Bayesian search for MIPROv2
pip install -U "dspy[optuna]>=3.2.1,<3.3"

# MCP tool integration
pip install -U "dspy[mcp]>=3.2.1,<3.3"

# Large local embedding corpora
pip install faiss-cpu

# optimize_anything
pip install -U "gepa>=0.1.1,<0.2"

Install as a Claude Code Plugin

/plugin marketplace add OmidZamani/dspy-skills
/plugin install dspy-skills@dspy-skills-marketplace

Documentation

Validate Changes

python3 scripts/validate_repo.py
python3 -m compileall -q examples skills/dspy-haystack-integration/examples

License

MIT License. See LICENSE.