What problem does it solve? Writing agent skills without testing them against real agent behavior leads to documentation that agents ignore, misinterpret, or rationalize away under pressure, resulting in unreliable process guidance. ## Core Features & Use Cases - TDD-Based Skill Authoring: Applies the RED-GREEN-REFACTOR cycle to skill creation by running baseline pressure scenarios with subagents before writing any documentation. - Rationalization Bulletproofing: Provides techniques to close loopholes, build rationalization tables, and create red flag lists so discipline-enforcing skills resist agent workarounds. - Discovery Optimization: Guides writing effective YAML frontmatter descriptions, keyword coverage, and token-efficient content so future agents can find and load the skill. - Use Case: When creating a new skill that enforces a rule like test-driven development, run pressure scenarios (time pressure, sunk cost, authority) with subagents first, document their exact rationalizations, then write the skill to counter those specific excuses. ## Quick Start Ask the agent to create a new skill for a specific technique, starting with baseline pressure scenarios tested on subagents before writing the SKILL.md file.
