caveman-review (JuliusBrussee/caveman) vs supabase-postgres-best-practices (supabase/agent-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
supabase-postgres-best-practices (supabase/agent-skills)
24.4 / 30
SituationalSafe
Supabase Postgres best practices: no gain over plain Codex on schema, review and index tasks (4.48 vs 4.54)
- SOTAPass