dspy-skills

DSPy Skills Collection is a Claude Code plugin containing 22 specialized skills for building and optimizing LLM applications using the DSPy framework. It covers the full lifecycle of LLM development: defining typed signatures and structured outputs, building RAG pipelines and multi-hop retrieval systems, creating ReAct agents with tool integration, and optimizing prompts and weights through multiple optimizer families. The collection includes skills for evaluation, debugging, production hardening, and deployment with caching, async support, and streaming. Teams can systematically design LLM systems, establish performance baselines, apply targeted optimizers like MIPROv2 or GEPA, and prepare applications for production use.

["Install DSPy and dependencies: `pip install dspy-ai pydantic`","Define your task requirements in the prompt template, including [TASK_DESCRIPTION] and [OPERATIONS_TEAM]","Connect to your Python workflow by replacing [PYTHON_WORKFLOW] with your module imports or API calls","Specify output format in [FORMAT] (e.g., JSON, CSV, or structured Python objects)","Test edge cases in [EDGE_CASES] (e.g., invalid queries, missing data) and verify logging in [LOGGING_SYSTEM]","Tip: Use DSPy's `teleprompt` module to fine-tune the pipeline with your organization's data patterns"]