What problem does it solve? Untested skill documentation often fails in practice because authors never observe how agents actually misbehave without it, leading to instructions that agents ignore, misinterpret, or rationalize away under pressure. ## Core Features & Use Cases - TDD-based skill authoring: Applies the RED-GREEN-REFACTOR cycle to documentation by running baseline pressure scenarios with subagents before writing any skill content. - Skill Discovery Optimization (SDO): Provides rules for writing description fields, keyword coverage, naming conventions, and token-efficient SKILL.md structure. - Rationalization bulletproofing: Supplies rationalization tables, red flag lists, and persuasion-principle guidance to close loopholes agents exploit under time, sunk-cost, or authority pressure. - Use Case: Before deploying a new discipline-enforcing skill, run pressure scenarios without it, document the agent's verbatim excuses, write the minimal skill addressing those failures, then iterate until the agent complies under maximum pressure. ## Quick Start Ask the agent to create a new skill following the TDD process: first run a baseline pressure scenario without the skill, then write the SKILL.md addressing the observed failures.
