caveman-review (JuliusBrussee/caveman) vs setup-pre-commit (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
setup-pre-commit (mattpocock/skills)
29.0 / 30
RecommendedSafe
setup-pre-commit: for a vague 'add commit hooks' request plain Codex builds a different (native git hook) setup, even calling npm in a pnpm repo (seen in one run); the skill and a one-sentence prompt both give the Husky + lint-staged setup (5.0 vs 1.4)
- SOTAPass