cxcscmu/implement_simpo_loss
Implements the SimPO (Simple Preference Optimization) loss function with length normalization and reward margin as specified in the research paper.
npx skills add https://github.com/cxcscmu/SkillLearnBench --skill implement_simpo_loss
Take cxcscmu/implement_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.