testing-skills-with-subagents
Testing Skills With Subagents
Overview
Testing skills is just TDD applied to process documentation.
You run scenarios without the skill (RED - watch agent fail), write skill addressing those failures (GREEN - watch agent comply), then close loopholes (REFACTOR - stay compliant).
Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill prevents the right failures.
REQUIRED BACKGROUND: This skill applies a RED-GREEN-REFACTOR cycle to process documentation: run a baseline that the skill currently fails (RED), write the skill to address that failure (GREEN), then iterate to close loopholes (REFACTOR). On top of that cycle it adds skill-specific test formats (pressure scenarios, rationalization tables).
Complete worked example: See examples/CLAUDE_MD_TESTING.md for a full test campaign testing CLAUDE.md documentation variants.