senior-prompt-engineer

Prompt optimization applies patterns like few-shot learning, chain-of-thought reasoning, and structured output formatting to improve response quality. The prompt_optimizer.py script provides a CLI entry point for running optimization workflows against input data.

RAG evaluation measures retrieval relevance and generation quality using structured frameworks. The rag_evaluator.py script and the llm_evaluation_frameworks.md reference describe evaluation workflows, metrics, and troubleshooting procedures.

Production systems benefit from chain-of-thought for reasoning tasks, few-shot examples for format consistency, and explicit output schemas for parsing. The prompt_engineering_patterns.md reference covers implementation strategies and scalability considerations.

Yes, the skill's documented tech stack includes LangChain, LlamaIndex, and DSPy as LLM frameworks. The guidance covers agent design and RAG patterns applicable to these frameworks, though the bundled scripts use only Python standard library.

The scripts prompt_optimizer.py, rag_evaluator.py, and agent_orchestrator.py are scaffolding templates with placeholder execution logic. They provide CLI structure, logging, and config validation but require custom implementation in the _execute method for real processing.