Agent Skills

All skills

codebase-design (mattpocock/skills) vs pptx (anthropics/skills)

codebase-design (mattpocock/skills)

23.6 / 30

SituationalSafe

codebase-design: gives architecture reviews the depth vocabulary and clearer structure (control 3.2, skill 3.9, one-liner 4.5) for 1.1x the tokens, but it did not find more of the planted problems than the one-liner prompt

  • 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