caveman (JuliusBrussee/caveman, SKILL.md only) vs verification-before-completion (obra/superpowers)
caveman (JuliusBrussee/caveman, SKILL.md only)
21.7 / 30
SituationalSafe
caveman: with 'be brief' already in the prompt, the skill saved no words and cost 2.2x the tokens
- 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