writing-skills

Enforce RED-GREEN-REFACTOR cycles with pressure scenario testing for AI skills.

Updated Mar 3, 2026
One-click install
npx skills add https://github.com/zhou533/UnVault --skill writing-skills-zhou533
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/zhou533/UnVault/tree/main/.claude/skills/writing-skills
Command: npx skills add https://github.com/zhou533/UnVault --skill writing-skills-zhou533

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a rigorous, test-driven framework for creating and refining AI Skills, ensuring they are effective, compliant, and resistant to manipulation.

Core Features & Use Cases

  • Test-Driven Skill Development: Enforces the RED-GREEN-REFACTOR cycle for documentation.
  • Pressure Scenario Testing: Simulates real-world agent behavior under stress to identify failure points.
  • Rationalization Countermeasures: Develops explicit strategies to prevent agents from bypassing rules.
  • Use Case: Before deploying a new skill that enforces coding standards, you would use this skill's methodology to write pressure scenarios that test an agent's adherence to those standards, document any rationalizations they use to bypass them, and then refine the skill to explicitly counter those rationalizations.

Quick Start

Use the writing-skills skill to create a new skill by following the RED-GREEN-REFACTOR process.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
What is test-driven development for AI skills?

Test-driven development for AI skills is a framework enforcing RED-GREEN-REFACTOR cycles for documentation. It ensures created skills are robust, compliant, and resistant to manipulation by simulating real-world agent behavior under stress.

How do I prevent AI agents from bypassing rules under pressure?

To prevent AI agents from bypassing rules under pressure, you implement rationalization countermeasures. This involves simulating stress scenarios, documenting the excuses agents use to bypass rules, and refining the skill to explicitly counter those rationalizations.

How to create robust AI skills using the RED-GREEN-REFACTOR cycle?

To create robust AI skills using the RED-GREEN-REFACTOR cycle, you write failing pressure scenarios first (RED), refine the skill documentation to make them pass (GREEN), and then optimize the skill while maintaining compliance (REFACTOR).

Does test-driven skill development work for enforcing coding standards?

Yes, test-driven skill development works for enforcing coding standards. You write pressure scenarios that test an agent's adherence to the standards, document any rationalizations used to bypass them, and refine the skill to explicitly counter those rationalizations.

What are the limitations of standard skill development without pressure scenario testing?

Without pressure scenario testing, standard skill development leaves AI skills vulnerable to agent rationalization and non-compliance under stress. It fails to identify failure points where agents bypass rules, resulting in less robust and easily manipulated skills.