OSU-NLP-Group

Use this skill whenever the user asks to generate, collect, inspect, or prepare early-experience training data (Implicit World Modeling or Self-Reflection, in the sense of arXiv:2510.08558) for an agent environment. Trigger phrases include "rollout", "collect expert trajectories", "generate reflection", "smoke test the pipeline", "set up a new env for early experience", or any work that produces expert / IWM / reflection SFT JSONL files. Do NOT trigger for model training, evaluation, or unrelated work.