Agent Skills

All skills

algorithmic-art (Anthropic) vs code-review (Matt Pocock)

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

code-review (Matt Pocock)

23.5 / 30

SituationalSafe

Matt Pocock's code-review: same recall as plain Codex on 3 review tasks, 1.5x the tokens

  • SOTAPass