All skills

emil-design-eng (emilkowalski/skills) vs pptx (anthropics/skills)

emil-design-eng (emilkowalski/skills)

26.2 / 30

RecommendedSafe

emil-design-eng: adds press feedback and custom easing that plain Codex never writes (0/6 to 6/6), but a one-sentence version gets nearly all of it

  • 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