video (smixs/visual-skills) vs vercel-react-best-practices (vercel-labs/agent-skills)
video (smixs/visual-skills)
20.8 / 30
SituationalSafe
smixs video skill: richer, more directed prompts, but keyword checks score it lower and it costs 2.8x the tokens; no video was generated
- SOTAPass
vercel-react-best-practices (vercel-labs/agent-skills)
24.3 / 30
SituationalSafe
Vercel's React best practices: lifts a Next.js optimisation from 2.3 to 3.6/5, but the one-sentence version reaches 4.6 for 75% of the tokens
- SOTAPass