Tools for prompt optimization, structured schema enforcement, response caching, and evaluation metrics.
Automatically optimize your agent skills using a multi-agent system built with Google ADK (Agent Development Kit) and Gemini. Upload a skill, let the agents generate test scenarios and evaluation criteria, then watch as three...
How this repo checks that its skills actually work — before they ship and on every change after. Layout: one folder per skill, evals/<skill-name>/.
Reduce LLM API costs by 30-60% using TOON (Token-Oriented Object Notation) format for structured data serialization. This app demonstrates how to use Toonify to dramatically reduce token usage when passing structured data to Large...
