test-driven-development (obra/superpowers) vs xlsx (anthropics/skills)
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
xlsx (anthropics/skills)
20.3 / 30
SituationalSafe
anthropics xlsx: its recalculation script never ran on a Mac, and the skill scored slightly lower than no skill
- SOTAPass