agents/tools/prompt-optimize.md

model

model
sonnet

AI Prompt Optimization

Optimize the following prompt for better AI model performance: $ARGUMENTS

Analyze and improve the prompt by:

1. Prompt Engineering:

   • Apply chain-of-thought reasoning
   • Add few-shot examples
   • Implement role-based instructions
   • Use clear delimiters and formatting
   • Add output format specifications

2. Context Optimization:

   • Minimize token usage
   • Structure information hierarchically
   • Remove redundant information
   • Add relevant context
   • Use compression techniques

3. Performance Testing:

   • Create prompt variants
   • Design evaluation criteria
   • Test edge cases
   • Measure consistency
   • Compare model outputs

4. Model-Specific Optimization:

   • GPT-4 best practices
   • Claude optimization techniques
   • Prompt chaining strategies
   • Temperature/parameter tuning
   • Token budget management

5. RAG Integration:

   • Context window management
   • Retrieval query optimization
   • Chunk size recommendations
   • Embedding strategies
   • Reranking approaches

6. Production Considerations:

   • Prompt versioning
   • A/B testing framework
   • Monitoring metrics
   • Fallback strategies
   • Cost optimization

Provide optimized prompts with explanations for each change. Include evaluation metrics and testing strategies. Consider both quality and cost efficiency.