rl-evaluator

This skill should be used when the user wants to "activate the rl evaluator", "invoke the evaluator agent", "evaluate the RL policy", "run evaluation tests", "diagnose training failures", "test robustness", "create visualization plots", "analyze saliency maps", or says "I need the evaluator to review the project". Orchestrates all evaluation, testing, and analysis tasks for a trained reinforcement learning policy.