senior-prompt-engineer

Prompt optimization refines existing LLM prompts to improve clarity, conciseness, and token efficiency. This Skill analyzes your prompt text to identify areas for refinement, ensuring optimal performance and accuracy in AI interactions.

Evaluating LLM outputs involves assessing the quality, faithfulness, and relevance of AI-generated responses. This Skill provides capabilities to evaluate RAG systems, helping you validate that responses are accurate and contextually appropriate.

Designing agentic systems involves building and validating complex AI workflows using patterns like ReAct and Plan-Execute. This Skill supports agent workflow visualization using Python scripts to structure and test your AI development.

Yes, you can analyze prompts stored in text files like 'customer_service_prompt.txt'. The Skill processes these files to evaluate and optimize the prompts driving your chatbot, leading to more helpful and concise customer interactions.

Irrelevant or verbose LLM responses often stem from unoptimized prompts. This Skill analyzes and refines the prompts driving your chatbot, addressing these specific issues to produce more helpful, concise, and accurate customer interactions.

Yes, visualizing agent workflows and evaluating prompts requires Python scripts and dependencies like pypdf, pdfplumber, and pdf2image. These libraries support the internal processing logic for analyzing your prompt files.