Agent Skills

All skills

algorithmic-art (Anthropic) vs caveman (JuliusBrussee/caveman, SKILL.md only)

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

caveman (JuliusBrussee/caveman, SKILL.md only)

21.7 / 30

SituationalSafe

caveman: with 'be brief' already in the prompt, the skill saved no words and cost 2.2x the tokens

  • SOTAPass