caveman-review (JuliusBrussee/caveman) vs prototype (mattpocock/skills)
caveman-review (JuliusBrussee/caveman)
25.1 / 30
SituationalSafe
caveman-review: shifts code reviews toward short per-finding lines (control 3.3, skill 4.2, one-liner 4.8) at the same tokens, but the skill's own L<line> line format was followed in only some runs; a one-sentence prompt of the format scores higher
- 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