Agent Skills

All skills

algorithmic-art (Anthropic) vs pptx (anthropics/skills)

algorithmic-art (Anthropic)

22.5 / 30

SituationalSafe

algorithmic-art: every arm passes the rule checks (4.5 / 4.8 / 5.0), but only the skill and a one-sentence prompt write a real philosophy document; the skill costs 2x the tokens

  • SOTAPass

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