SkillLift paper reports 40–70% lower token cost for evolving agent skills
DAIR.AI highlighted a SkillLift paper that trains a learned rubric to rank agent skill-prompt candidates instead of scoring every revision with a full rollout. It reports beating SkillOpt and CoEvoSkills on SkillsBench and WildClawBench, reaching target performance with 40 to 70% fewer tokens.