A permission-aware Agent Skill for reproducible, auditable batch episode collection across VLA, policy, world-model, and embodied benchmark workflows.
Latest release v0.2.0 — v0.2.0 - Informed and capability-faithful embodied evaluation · 3 Aug 2026
1 file for Codex and OpenCode: embodied-eval-automation AGENTS.md — 179 tokens loaded in every session.
AGENTS.md A 179 tok These files are Yinzhanqing/embodied-eval-automation's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.