testing-skills-with-subagents

What problem does it solve?

This Skill applies Test-Driven Development (TDD) to process documentation, ensuring that new or edited Claude Skills are robust, resist rationalization, and work effectively under pressure, preventing agents from bypassing critical rules.

Core Features & Use Cases

• TDD for Documentation: Guides through the RED-GREEN-REFACTOR cycle for skill writing, using subagents for testing compliance.
• Pressure Scenario Testing: Creates realistic scenarios with combined pressures (time, sunk cost, authority) to test agent compliance under stress.
• Rationalization Countering: Identifies and explicitly plugs loopholes and common excuses agents use to bypass rules, ensuring disciplined adherence.
• Use Case: When creating a new skill that enforces discipline (e.g., a TDD skill), use this to test it with subagents, ensuring it prevents agents from rationalizing their way out of following the rules, making your skills truly effective.

Quick Start

TDD Mapping for Skill Testing

RED: Baseline test (Run scenario WITHOUT skill, watch agent fail)

Verify RED: Capture rationalizations (Document exact failures verbatim)

GREEN: Write skill (Address specific baseline failures)

Verify GREEN: Pressure test (Run scenario WITH skill, verify compliance)

REFACTOR: Plug holes (Find new rationalizations, add counters)

Stay GREEN: Re-verify (Test again, ensure still compliant)