prompt-optimization_skill

Overview

This skill provides expert prompt optimization for large language models and AI systems. It helps design concise, high-performing prompts, implement few-shot patterns, and set constraints to produce reliable outputs. Use it to improve agent behavior, response quality, and task-specific performance.

How this skill works

The skill inspects prompt structure, clarity, examples, and output formatting, then suggests revisions that reduce ambiguity and guide model reasoning. It applies patterns like role definitions, few-shot examples, chain-of-thought scaffolding, and explicit constraints to boost consistency and efficiency. Recommendations include concrete prompt rewrites, example pairs, and evaluation criteria.

When to use it

• Building AI features or conversational agents
• Improving LLM response relevance and reliability
• Crafting system or initializer prompts
• Implementing few-shot learning for niche tasks
• Optimizing agent performance and cost-efficiency

Best practices

• Define a clear role and task upfront to set model context
• Include 2–3 curated examples showing input-output style and edge cases
• Specify exact output format (JSON, bullet list, tables) and validation rules
• Break complex tasks into step-by-step reasoning or chain-of-thought prompts
• Iterate: test prompts, collect failure cases, and refine examples

Example use cases

• Create a system prompt for a code review agent with explicit checklists and output schema
• Design few-shot examples to teach a model domain-specific classification labels
• Rewrite user-facing prompts to reduce hallucinations and improve factuality
• Set constraints and safety filters for content moderation agents
• Optimize prompts to reduce token usage while retaining output quality