prompt-engineering

Write, optimize, and debug LLM prompts — system prompts, task prompts, and prompt templates. Trigger when: the user wants to write or improve a system prompt; asks "how do I prompt Claude/GPT/Gemini to [X]"; a prompt keeps giving bad or inconsistent outputs; wants to build a prompt template; asks about few-shot, chain-of-thought, or role-based prompting; wants to reduce hallucinations or improve AI output quality; or asks to evaluate or critique a prompt. Key capabilities: role assignment, output format specification, few-shot examples with 2–3 input→output pairs, chain-of-thought reasoning, XML tag structure, positive over negative framing, and a 7-field system prompt template (Role/Goal/Context/Instructions/Output Format/Constraints). Also for: rewriting vague requests as structured prompts, debugging prompt output problems with a 5-step checklist, generating prompt templates for recurring tasks, and evaluating prompt clarity with a 5-dimension rubric (clarity, specificity, example quality, constraint completeness, format spec). Does NOT trigger for general code writing or non-AI tasks.