What problem does it solve? Writing effective agent skills is hard because untested documentation often fails under real-world pressure—agents rationalize away rules, skip steps, or misinterpret guidance. This Skill applies test-driven development to skill authoring so you can verify skills actually change agent behavior before deployment. ## Core Features & Use Cases - TDD-Based Skill Authoring: Follows the RED-GREEN-REFACTOR cycle—run baseline pressure scenarios without the skill, document agent failures verbatim, then write minimal skills addressing those specific rationalizations. - Discovery Optimization (CSO): Provides concrete rules for writing descriptions, naming conventions, keyword coverage, and token efficiency so future agents can find your skill. - Bulletproofing Against Rationalization: Includes techniques like rationalization tables, red flags lists, and persuasion principles to close loopholes agents exploit under pressure. - Use Case: You want to create a new skill enforcing code review before commits. Run pressure scenarios (time pressure + sunk cost + authority) with a subagent lacking the skill, capture its excuses, write the skill countering those exact rationalizations, 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 with a subagent, then drafting the SKILL.md based on the observed failures.
