All skills

tdd (Matt Pocock) vs xlsx (anthropics/skills)

tdd (Matt Pocock)

22.7 / 30

SituationalSafe

mattpocock tdd: no lift once the prompt already asks for test-first, and about 1.7x the tokens

  • 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