Agent Skills

All skills

pptx (anthropics/skills) vs review-animations (emilkowalski/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

review-animations (emilkowalski/skills)

24.9 / 30

RecommendedSafe

review-animations: makes a pull-request motion review find the planted problems and give exact fixes (control 2.9, skill 4.4, one-liner 4.9) at 1.2x the tokens; a one-sentence prompt of the checklist does better

  • SOTAPass