Build 3 evaluations and a no-Skill baseline BEFORE writing the Skill (evaluation-driven Skill development)

Claude Docs·medium signal

Anthropic recommends running Claude on representative tasks without a Skill first, documenting the specific failures, then writing three eval scenarios and a baseline measurement — and only then authoring the minimal instructions needed to beat that baseline. This stops you from documenting imagined problems and keeps Skills lean. The companion workflow uses two Claude instances: 'Claude A' to author/refine and a fresh 'Claude B' to test, feeding observed gaps back to A.