What problem does it solve? Writing effective agent skills without verification leads to documentation that agents ignore or misinterpret under pressure. This Skill applies test-driven development to skill authoring, ensuring skills actually change agent behavior before deployment. ## Core Features & Use Cases - TDD-Based Skill Authoring: Follows the RED-GREEN-REFACTOR cycle where baseline pressure scenarios are run without the skill first, then the skill is written to address observed failures, then loopholes are closed iteratively. - Subagent Pressure Testing: Provides a methodology for testing skills with realistic scenarios combining time pressure, sunk cost, authority, and exhaustion to verify compliance. - Discovery Optimization: Covers Claude Search Optimization techniques including description writing, keyword coverage, naming conventions, and token efficiency. - Use Case: When creating a new discipline-enforcing skill like a TDD requirement, run baseline scenarios with subagents to capture their rationalizations verbatim, write the skill addressing those specific excuses, then refactor until agents comply under maximum pressure. ## Quick Start Ask the agent to create a new skill for a specific technique using the writing-skills methodology, starting with baseline pressure scenario testing before writing any documentation.
