Loading...
Loading...
Found 3 Skills
A/B test agent variants measuring quality and total session token cost across simple and complex benchmarks. Use when creating compact agent versions, validating agent changes, comparing internal vs external agents, or deciding between variants for production. Use for "compare agents", "A/B test", "benchmark agents", or "test agent efficiency". Do NOT use for evaluating single agents, testing skills, or optimizing prompts without variant comparison.
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
Optimize anything through autonomous experimentation, against an evaluator you cannot grade yourself with. Use whenever the user wants to improve a number by iterating - raise accuracy, cut val loss, make training or inference faster, reduce latency or cost, beat a baseline, tune a pipeline or prompt, squeeze a kernel, run experiments overnight, or set up a benchmark for someone else to beat. Also use for any request to create, inspect, update or score against a hill, or when the user types /hills. Sets up a frozen evaluation, gets one human sign-off, then runs the experiment loop autonomously until the stopping criteria are met.