What problem does it solve? Writing documentation-style skills for AI agents often produces untested instructions that agents ignore or misinterpret under pressure, leading to unreliable behavior in production workflows. ## Core Features & Use Cases - TDD-Based Skill Authoring: Applies the RED-GREEN-REFACTOR cycle to skill creation, requiring baseline failure tests with subagents before writing any skill content. - Rationalization Bulletproofing: Provides pressure-scenario testing methods, rationalization tables, and red-flag lists to close loopholes agents exploit. - Discovery Optimization: Guides Claude Search Optimization (CSO) with rules for descriptions, naming, keyword coverage, and token efficiency. - Use Case: When creating a new discipline-enforcing skill like TDD or verification-before-completion, run baseline pressure scenarios with subagents, document their exact rationalizations, then write a minimal skill that counters those specific failures. ## Quick Start Ask the agent to help you create a new skill by first running baseline pressure scenarios without the skill, then writing the SKILL.md to address the observed failures.