prompt-engineering

This skill provides comprehensive frameworks for creating, optimizing, and implementing advanced prompt patterns that significantly improve LLM performance across various tasks and models. It covers few-shot learning, chain-of-thought reasoning, prompt optimization workflows, template systems, and system prompt design for production-ready AI applications.

Select examples using semantic similarity and diversity sampling to maximize learning within context window constraints.

Elicit step-by-step reasoning for complex problem-solving through structured thinking patterns.

在創建、優化或實現高級提示模式時應使用此技能，包括少量學習、思維鏈推理、提示優化工作流程、模板系統和系統提示設計。它提供了全面的框架，用於建立可用於生產的提示，並具有可衡量的性能改進。 來源：giuseppe-trisciuoglio/developer-kit。