verification-before-completion (obra/superpowers) vs xlsx (anthropics/skills)
verification-before-completion (obra/superpowers)
25.0 / 30
SituationalSafe
verification-before-completion: all 18 runs verify before claiming done, with or without the skill (5.0 / 5.0 / 5.0); the skill adds ~20% 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