What problem does it solve? Writing documentation-style skills for AI agents often produces untested instructions that agents ignore or misinterpret under pressure. This Skill applies test-driven development (RED-GREEN-REFACTOR) to skill authoring so every skill is verified against real agent behavior before deployment. ## Core Features & Use Cases - TDD-based skill authoring: Run baseline pressure scenarios with subagents, document failures, write the skill, then verify compliance and close loopholes. - Skill Discovery Optimization (SDO): Guidelines for writing trigger-focused descriptions, keyword coverage, naming conventions, and token-efficient content so agents actually find and load the skill. - Failure-matched guidance forms: Choose prohibitions, recipes, structural templates, or conditionals based on the type of baseline failure observed. - Use Case: You want to create a new skill enforcing code review discipline. You first run pressure scenarios without the skill to capture agent rationalizations, then write the skill targeting those exact excuses, and re-test until agents comply under time, sunk-cost, and exhaustion pressure. ## Quick Start Ask the agent to help you create a new skill by first running a baseline pressure scenario with a subagent, then drafting the SKILL.md and verifying compliance.
