Agent Skills

All skills

pptx (anthropics/skills) vs prototype (mattpocock/skills)

pptx (anthropics/skills)

24.0 / 30

SituationalSafe

anthropics pptx: all groups pass our deck checks (5.0 vs 4.99), the skill costs 1.4x the tokens; one one-sentence run produced a deck LibreOffice cannot open

  • SOTAPass

prototype (mattpocock/skills)

27.2 / 30

RecommendedSafe

Matt Pocock's prototype: follows its own UI-variant rules (4.95 vs 3.71 for control) at about the same cost as no skill

  • SOTAPass