Agent Skills

All skills

algorithmic-art (Anthropic) vs emil-design-eng (emilkowalski/skills)

algorithmic-art (Anthropic)

22.5 / 30

SituationalSafe

algorithmic-art: every arm passes the rule checks (4.5 / 4.8 / 5.0), but only the skill and a one-sentence prompt write a real philosophy document; the skill costs 2x the tokens

  • SOTAPass

emil-design-eng (emilkowalski/skills)

26.2 / 30

RecommendedSafe

emil-design-eng: adds press feedback and custom easing that plain Codex never writes (0/6 to 6/6), but a one-sentence version gets nearly all of it

  • SOTAPass