prototype (mattpocock/skills) vs verification-before-completion (obra/superpowers)
prototype (mattpocock/skills)
27.2 / 30
RecommendedSafe
Matt Pocock's prototype: follows its own UI-variant rules (4.95 vs 3.71 for control) at about the same cost as no skill
- SOTAPass
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