What problem does it solve? Untested skill documentation often fails in practice because authors never observe how agents actually behave 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. - Rationalization Bulletproofing: Provides rationalization tables, red flag lists, and explicit loophole counters so discipline-enforcing skills resist agent workarounds. - Discovery Optimization (CSO): Defines naming, description, and keyword rules so future agents can find the skill via search, plus token-efficiency targets for frequently loaded skills. - Use Case: When creating a new skill like a code-review checklist, run pressure scenarios (time pressure, sunk cost, authority) against a subagent without the skill, document its exact excuses, then write the minimal skill that counters those specific failures and re-test until compliant. ## Quick Start Ask the agent to help you create a new skill by first running baseline pressure scenarios with subagents, then writing the SKILL.md that addresses the observed failures.
