Agent Skills

All skills

pptx (anthropics/skills) vs verification-before-completion (obra/superpowers)

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

verification-before-completion (obra/superpowers)

25.0 / 30

SituationalSafe

verification-before-completion: all 18 runs verify before claiming done, with or without the skill (5.0 / 5.0 / 5.0); the skill adds ~20% tokens

  • SOTAPass