caveman (JuliusBrussee/caveman, SKILL.md only) vs composition-patterns (vercel-labs/agent-skills)
caveman (JuliusBrussee/caveman, SKILL.md only)
21.7 / 30
SituationalSafe
caveman: with 'be brief' already in the prompt, the skill saved no words and cost 2.2x the tokens
- SOTAPass
composition-patterns (vercel-labs/agent-skills)
25.1 / 30
SituationalSafe
vercel-composition-patterns: moves a boolean-prop React component to a compound-component API (control 3.7, skill 4.4), at no extra tokens, but a one-sentence prompt of the same advice scores 4.7
- SOTAPass