testing-skills-with-subagents

What problem does it solve?

Skills, like code, can have flaws or be misinterpreted, especially when agents are under pressure or tempted to rationalize. Untested skills lead to unreliable AI behavior. This skill applies the Test-Driven Development (TDD) cycle to process documentation, ensuring skills are robust, resist rationalization, and reliably guide AI behavior even in complex, high-stakes scenarios.

Core Features & Use Cases

• TDD for Documentation: Uses RED-GREEN-REFACTOR to test skill effectiveness on AI agents.
• Pressure Scenario Testing: Creates realistic scenarios with combined pressures (time, sunk cost, authority) to test compliance.
• Rationalization Prevention: Identifies and explicitly counters common AI rationalizations and loopholes.
• Use Case: When creating a new skill, use this skill to test it with subagents under various pressures, ensuring it's clear, effective, and prevents the AI from taking shortcuts.

Quick Start

Use the testing-skills-with-subagents skill to test the 'new-debugging-workflow' skill for robustness and compliance.