All skills

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

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

xlsx (anthropics/skills)

20.3 / 30

SituationalSafe

anthropics xlsx: its recalculation script never ran on a Mac, and the skill scored slightly lower than no skill

  • SOTAPass