What problem does it solve? Writing process documentation for AI agents often produces skills that agents ignore or rationalize away under pressure. This Skill applies test-driven development (RED-GREEN-REFACTOR) to skill authoring, ensuring skills are verified against real agent behavior before deployment. ## Core Features & Use Cases - TDD-Based Skill Authoring: Run baseline pressure scenarios with subagents, document failures verbatim, then write skills that address those specific rationalizations. - Discovery Optimization: Guidance on Claude Search Optimization (CSO), including description writing, keyword coverage, naming conventions, and token efficiency targets. - Bulletproofing Against Rationalization: Build rationalization tables, red flags lists, and explicit loophole counters so discipline-enforcing skills hold up under time, sunk cost, and authority pressures. - Use Case: When creating a new skill that enforces a rule like TDD, run pressure scenarios without the skill first, capture how agents violate the rule, write the skill to counter those exact excuses, and re-test until agents comply under maximum pressure. ## Quick Start Ask the agent to help you create a new skill by first running a baseline pressure scenario, then drafting the SKILL.md with proper frontmatter and testing it with subagents.
