prompt-engineering

SKILL.md

Advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

Teach the model by showing examples instead of explaining rules. Include 2-5 input-output pairs that demonstrate the desired behavior. Use when you need consistent formatting, specific reasoning patterns, or handling of edge cases. More examples improve accuracy but consume tokens—balance based on task complexity.

Request step-by-step reasoning before the final answer. Add "Let's think step by step" (zero-shot) or include example reasoning traces (few-shot). Use for complex problems requiring multi-step logic, mathematical reasoning, or when you need to verify the model's thought process. Improves accuracy on analytical tasks by 30-50%.

신속한 엔지니어링 패턴, 모범 사례 및 최적화 기술에 대한 전문가 가이드입니다. 사용자가 프롬프트를 개선하거나, 프롬프트 전략을 배우거나, 상담원 동작을 디버깅하려는 경우에 사용하세요. 출처: hainamchung/agent-assistant.

원본 보기