docx (anthropics/skills) vs test-driven-development (obra/superpowers)
docx (anthropics/skills)
21.4 / 30
SituationalSafe
anthropics docx: same results as no skill on three Word tasks, plus working files left behind
- SOTAPass
test-driven-development (obra/superpowers)
24.0 / 30
RecommendedSafe
superpowers test-driven-development: makes the agent write the test first, and costs about 1.6x the tokens
- SOTAPass