Skill UI

This tool allows users to systematically evaluate and rank the outputs of multiple agents within an AgentHub session. It supports metric-based evaluation (running custom commands for measurable metrics like speed or resource usage), or an advanced LLM Judge Mode. The LLM Judge compares results based on criteria like correctness, simplicity, and overall quality, helping users determine the best-performing agent for the task.

This skill provides expert capabilities for training and fine-tuning transformer language models using the TRL (Transformers Reinforcement Learning) library. It supports state-of-the-art post-training methods, including Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), Group Relative Policy Optimization (GRPO), and Reward Model training. Use this skill to align and customize foundation models for advanced tasks via CLI commands.