code-review (Matt Pocock) vs react-native-skills (vercel-labs/agent-skills)
code-review (Matt Pocock)
23.5 / 30
SituationalSafe
Matt Pocock's code-review: same recall as plain Codex on 3 review tasks, 1.5x the tokens
- 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