caveman-review (JuliusBrussee/caveman) vs writing-skills (obra/superpowers)
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
writing-skills (obra/superpowers)
17.6 / 30
SituationalSafe
writing-skills: gets the description rule right ('Use when...' 4.9 vs 4.4 without the skill), but a one-sentence rule gets 4.7 for a third of the tokens (2.5x)
- SOTAPass