Deep Learning to Create StepMania SM FIles
12 files for Claude Code, Cursor, Codex and OpenCode: agent-brain-refresh, agent-self-improvement, ar-tide-autoresearch, autoresearch and 8 more — 1,611 tokens loaded in every session.
AGENTS.md A 1,611 tok .cursor/skills/agent-brain-refresh/SKILL.md A 53 tok .cursor/skills/agent-self-improvement/SKILL.md A 36 tok .cursor/skills/ar-tide-autoresearch/SKILL.md A 22 tok .cursor/skills/autoresearch/SKILL.md A 78 tok .cursor/skills/onset-event-eval-matching/SKILL.md A 66 tok .cursor/skills/research-session-workflow/SKILL.md A 44 tok .cursor/skills/steering-correction-promotion/SKILL.md A 61 tok .cursor/skills/tide-ablations/SKILL.md A 53 tok .cursor/skills/tide-overfit-protocol/SKILL.md A 60 tok .cursor/skills/whats-next/SKILL.md A 66 tok .cursor/skills/wsl-gpu-stepcovnet/SKILL.md A 58 tok These files are cpuguy96/StepCOVNet's own configuration — they tell Claude Code, Cursor, 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.