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. - Pressure Scenario Testing: Provides a methodology for testing skills against combined pressures (time, sunk cost, authority, exhaustion) and closing rationalization loopholes. - Discovery Optimization: Guides writing descriptions, keywords, and naming for Claude Search Optimization so agents find the right skill at the right time. - Use Case: When creating a new discipline-enforcing skill like TDD or verification-before-completion, run baseline scenarios without the skill, document agent rationalizations verbatim, write the minimal skill addressing those failures, then refactor until bulletproof. ## Quick Start Ask the agent to help you create a new skill by first running a baseline pressure scenario without the skill, then writing the SKILL.md based on the observed failures.