cxcscmu/simpo-loss
SimPO (Simple Preference Optimization) loss computation for LLM alignment without a reference model.
npx skills add https://github.com/cxcscmu/SkillLearnBench --skill simpo-loss
Take cxcscmu/simpo-loss from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.