Agent Skills

All skills

pptx (anthropics/skills) vs setup-pre-commit (mattpocock/skills)

pptx (anthropics/skills)

24.0 / 30

SituationalSafe

anthropics pptx: all groups pass our deck checks (5.0 vs 4.99), the skill costs 1.4x the tokens; one one-sentence run produced a deck LibreOffice cannot open

  • SOTAPass

setup-pre-commit (mattpocock/skills)

29.0 / 30

RecommendedSafe

setup-pre-commit: for a vague 'add commit hooks' request plain Codex builds a different (native git hook) setup, even calling npm in a pnpm repo (seen in one run); the skill and a one-sentence prompt both give the Husky + lint-staged setup (5.0 vs 1.4)

  • SOTAPass