Agent Skills

All skills

algorithmic-art (Anthropic) vs prototype (mattpocock/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

prototype (mattpocock/skills)

27.2 / 30

RecommendedSafe

Matt Pocock's prototype: follows its own UI-variant rules (4.95 vs 3.71 for control) at about the same cost as no skill

  • SOTAPass