What problem does it solve? Writing documentation-style skills for AI agents often produces instructions that agents ignore or rationalize away under pressure. This Skill applies test-driven development to skill authoring: you run baseline pressure scenarios without the skill, observe exact failure rationalizations, write the minimal skill to address them, and iterate until compliance holds. ## Core Features & Use Cases - TDD-based skill authoring: Red-green-refactor cycle adapted to documentation, with baseline testing, minimal skill writing, and loophole closing. - Skill Discovery Optimization (SDO): Guidance on writing trigger-focused descriptions, keyword coverage, naming conventions, and token-efficient structure. - Pressure testing methodology: Reference docs cover multi-pressure subagent scenarios, rationalization tables, red-line lists, and persuasion principles grounded in published research. - Use Case: When creating a new discipline-enforcement skill (e.g., mandatory TDD), run a scenario combining time pressure, sunk cost, and fatigue without the skill, record the agent's excuses verbatim, then write targeted rebuttals and re-test until the agent complies. ## Quick Start Ask the agent to help you create a new skill by first running a baseline pressure scenario without it, then drafting the SKILL.md and iterating until the agent complies under pressure.
