All skills

docx (anthropics/skills) vs theme-factory (Anthropic)

docx (anthropics/skills)

21.4 / 30

SituationalSafe

anthropics docx: same results as no skill on three Word tasks, plus working files left behind

  • SOTAPass

theme-factory (Anthropic)

27.7 / 30

RecommendedSafe

theme-factory: Codex already knows two named themes by heart (5.0 without the skill), but only the skill can 'pick a preset': 5.0 vs 0.0 on that task, and it is cheaper (0.66x tokens)

  • SOTAPass