Prompt Optimizer

소개

The Prompt Optimizer skill empowers developers to refine and enhance agent behaviors by applying proven prompt engineering techniques. It follows a systematic 'Understand, Plan, Propose, Integrate' methodology to ensure every modification is grounded in research and documented impact. Whether you are dealing with simple tool instructions or complex multi-agent orchestration, this skill helps eliminate ambiguity, manage token constraints, and address specific failure modes through an interactive, visual approval process that keeps the human in control.

주요 기능

• Conditional logic for complex multi-agent orchestration and shared context
• Visual 'Card' layout for scannable, side-by-side change proposals
• Phase-based optimization workflow (Understand, Plan, Propose, Integrate)
• 226 GitHub stars
• Anti-pattern detection to identify hedging language and conflicting rules
• Research-backed pattern attribution from single and multi-turn references

사용 사례

• Standardizing prompt structures across a multi-agent hierarchy for better consistency
• Decomposing complex, multi-step agent workflows into clear, systematic instructions
• Refining a system prompt for a tool-use agent that is hallucinating or ignoring constraints