code-review (Matt Pocock) vs prototype (mattpocock/skills)
code-review (Matt Pocock)
23.5 / 30
SituationalSafe
Matt Pocock's code-review: same recall as plain Codex on 3 review tasks, 1.5x the tokens
- SOTAPass
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