Agent Skills

All skills

algorithmic-art (Anthropic) vs domain-modeling (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

domain-modeling (mattpocock/skills)

28.2 / 30

RecommendedSafe

domain-modeling: turns plain 'set up a glossary / record this decision' requests into the short GLOSSARY.md + ADR format (control 2.8, skill 5.0), a one-sentence prompt gets 4.6; no token overhead

  • SOTAPass