design-taste-frontend (Leonxlnx/taste-skill) vs systematic-debugging (obra/superpowers)
design-taste-frontend (Leonxlnx/taste-skill)
16.2 / 30
SituationalCaution
design-taste-frontend: removes the 'AI slop' tells (uppercase eyebrows, 01/02 markers) and wins the redesign task, but averages below control (3.6 vs 4.0) because one landing page came out broken, at 3.7x the tokens
- SOTAPass
systematic-debugging (obra/superpowers)
22.4 / 30
SituationalSafe
superpowers systematic-debugging: no measurable gain on three small bugs, about 1.3x the tokens
- SOTAPass