Agent Skills

All skills

caveman-review (JuliusBrussee/caveman) vs react-native-skills (vercel-labs/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

react-native-skills (vercel-labs/agent-skills)

24.3 / 30

RecommendedSafe

react-native-skills: lifts a double-tap animation from 'JS-thread Animated' to Reanimated + Gesture Handler (0.7 to 5.0), but on review and optimise tasks it is no better than control and below a one-sentence checklist (4.6 vs 5.0)

  • SOTAPass