What problem does it solve? Writing documentation-style skills for AI agents often produces untested instructions that agents ignore or rationalize away under pressure. This Skill applies test-driven development 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 (RED), write the skill addressing observed failures (GREEN), then close rationalization loopholes (REFACTOR). - Discovery optimization guidance: Rules for writing name and description frontmatter, keyword coverage, token efficiency, and Claude Search Optimization so agents actually find the skill. - Testing methodology: Detailed guidance for pressure scenarios, rationalization tables, red-flag lists, and meta-testing, plus persuasion principles research for bulletproofing discipline-enforcing skills. - Use Case: You want to create a new skill that enforces a code-review rule. Use this Skill to first run a subagent scenario without the rule, capture the agent's excuses verbatim, write the skill countering those exact excuses, and re-test until the agent complies under time, sunk-cost, and authority pressure. ## Quick Start Ask the agent to help you create a new skill using test-driven development, starting with a baseline pressure scenario before writing any documentation.
