writing-skills

Apply the RED-GREEN-REFACTOR cycle to author and refine AI skills.

1|Updated Feb 24, 2026
One-click install
npx skills add https://github.com/FacuM/yolo-agent --skill writing-skills-facum
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/FacuM/yolo-agent/tree/main/.claude/skills/writing-skills
Command: npx skills add https://github.com/FacuM/yolo-agent --skill writing-skills-facum

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a rigorous, test-driven development (TDD) framework for creating and refining AI Skills, ensuring they are robust, discoverable, and effective. It prevents common pitfalls in skill authoring by adapting the RED-GREEN-REFACTOR cycle to documentation.

Core Features & Use Cases

  • TDD for Skills: Apply the RED-GREEN-REFACTOR cycle to skill creation and editing.
  • Pressure Testing: Design scenarios to test skills under realistic constraints (time, sunk cost, authority).
  • Rationalization Countermeasures: Identify and explicitly address common excuses agents use to bypass rules.
  • Use Case: You're developing a new skill to enforce coding standards. Use this skill's methodology to write test scenarios where an agent might be tempted to skip standards under time pressure, then refine the skill until it's bulletproof.

Quick Start

Follow the RED-GREEN-REFACTOR cycle outlined in this skill's documentation to create or update any skill.

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 adapts the RED-GREEN-REFACTOR cycle to documentation, ensuring robustness by creating pressure scenarios to baseline agent behavior before writing minimal skills to address observed failures.

How do I create pressure scenarios to test AI agent behavior?

To create pressure scenarios for AI skills, design tests using realistic constraints like time pressure, sunk cost, or authority, then observe agent failures to establish a baseline before refining the skill documentation.

Can I use TDD methodology to refine existing skill documentation?

Yes, you can apply TDD methodology to refine existing skill documentation by identifying loopholes through pressure testing, refactoring to close gaps, and implementing rationalization countermeasures to prevent agents from bypassing rules.

Why does my AI skill fail to enforce rules under time pressure?

AI skills fail under time pressure when they lack rationalization countermeasures. Applying the TDD cycle helps identify these loopholes by testing skills against realistic constraints and explicitly addressing common excuses agents use to bypass rules.

What's the best way to prevent AI agents from rationalizing rule bypasses?

The best way to prevent rationalization is using the TDD REFACTOR phase to close loopholes in skill documentation, explicitly addressing common excuses agents use to bypass rules under pressure scenarios involving time or sunk cost constraints.

Do I need any dependencies to apply TDD for skill authoring?

No dependencies are required to apply TDD for skill authoring. The methodology is self-contained, guiding you through the RED-GREEN-REFACTOR cycle using pressure scenarios and refactoring techniques to ensure skill robustness and discoverability.