tdd (Matt Pocock) vs mcp-builder (anthropics/skills)

tdd (Matt Pocock)

22.7 / 30

SituationalSafe

mattpocock tdd: no lift once the prompt already asks for test-first, and about 1.7x the tokens

SOTAPass

mcp-builder (anthropics/skills)

21.6 / 30

SituationalSafe

mcp-builder: lifts MCP servers from 3.6 to 4.6/5 by adding naming, annotations and async, but a one-sentence checklist scores 4.9 for 68% of the tokens

SOTAPass