skill-test

Enforce TDD cycles with pressure scenarios and rationalization analysis for AI Skills.

2|Updated Feb 27, 2026
One-click install
npx skills add https://github.com/onejaejae/skills --skill skill-test-onejaejae
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-test
Source: https://github.com/onejaejae/skills/tree/main/plugins/ai-registry/common/skill-test/skills/skill-test
Command: npx skills add https://github.com/onejaejae/skills --skill skill-test-onejaejae

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enforces a rigorous Test-Driven Development (TDD) approach for AI Skills, ensuring they are robust, compliant, and resistant to manipulation by proactively identifying and fixing weaknesses before deployment.

Core Features & Use Cases

  • TDD Cycle Enforcement: Guides the development through RED (baseline failure), GREEN (compliance verification), and REFACTOR (loophole fixing) phases.
  • Pressure Scenario Testing: Utilizes defined pressure scenarios (time, sunk cost, authority, etc.) to stress-test Skill responses.
  • Rationalization Analysis: Captures and analyzes agent justifications for non-compliant behavior to identify skill gaps.
  • Use Case: Before releasing a new "code-standards" Skill, use this Skill to run it against simulated stressful coding scenarios. If the Skill fails to enforce standards under pressure, the TDD cycle will guide its refinement until it consistently passes.

Quick Start

Use the skill-test skill to run the TDD cycle for the new 'code-standards' skill.

Frequently Asked Questions about skill-test

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I test AI skills for vulnerabilities and compliance before deployment?

You test AI skills for vulnerabilities by applying a Test-Driven Development methodology using RED, GREEN, and REFACTOR cycles to proactively identify weaknesses and verify compliance before deployment.

What is the TDD cycle for AI skill development?

The TDD cycle for AI skill development consists of three phases: RED to establish baseline failure, GREEN to verify compliance, and REFACTOR to fix loopholes and refine robustness against manipulation.

How do I stress-test AI agent responses against manipulation and edge cases?

You stress-test AI agent responses by applying pressure scenarios involving time, sunk cost, and authority constraints, then capturing and analyzing rationalizations for non-compliant behavior to identify skill gaps.

Can I use TDD methodology to ensure new code-standards skills enforce rules under pressure?

Yes, you can use TDD methodology to run new code-standards skills against simulated stressful coding scenarios, guiding refinement until the skill consistently passes and enforces standards under pressure.

Why do AI agents fail to enforce compliance rules in high-pressure situations?

AI agents fail to enforce compliance rules in high-pressure situations due to unhandled edge cases and rationalization gaps, which structured pressure scenario testing and rationalization analysis can proactively identify and fix.