writing-skills

Apply RED-GREEN-REFACTOR cycles to create and verify AI skills.

1|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/Devattom/.claude --skill writing-skills-devattom
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/Devattom/.claude/tree/main/skills/writing-skills
Command: npx skills add https://github.com/Devattom/.claude --skill writing-skills-devattom

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, editing, and verifying AI skills, ensuring they are robust, effective, and resistant to loopholes.

Core Features & Use Cases

  • TDD for Skills: Apply the RED-GREEN-REFACTOR cycle to skill documentation.
  • Pressure Scenario Testing: Design tests that simulate real-world stress to uncover weaknesses.
  • Rationalization Countermeasures: Identify and explicitly block common excuses agents use to bypass rules.
  • Use Case: When developing a new skill for code review, use this Skill's methodology to write failing tests (e.g., simulate a time crunch), then write the skill to enforce review steps, and finally refactor to prevent agents from skipping reviews under pressure.

Quick Start

Follow the TDD cycle to create a new skill, starting with writing a failing test scenario.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I use TDD to create and refine AI skills?

To use TDD for AI skill development, apply the RED-GREEN-REFACTOR cycle to skill documentation. You write failing pressure scenario tests first, then create the skill logic to pass them, and finally refactor to close loopholes and ensure compliance.

What is pressure scenario testing for AI skill development?

Pressure scenario testing for AI skills involves designing tests that simulate real-world stress, like a time crunch, to uncover weaknesses. It ensures skill effectiveness by preventing rationalization and enforcing strict adherence to process rules under pressure.

How can I stop AI agents from rationalizing and bypassing documentation rules?

To stop AI agents from rationalizing and bypassing documentation rules, implement rationalization countermeasures during skill refactoring. This involves explicitly identifying and blocking common excuses agents use to skip required steps under pressure.

Does test-driven development work for AI compliance documentation?

Yes, test-driven development works for AI compliance documentation by enforcing strict adherence to the RED-GREEN-REFACTOR cycle. This methodology ensures documentation is robust, compliant, and explicitly closes loopholes during the refactoring phase.

What is the best way to prevent AI agents from skipping code reviews under pressure?

The best way to prevent AI agents from skipping code reviews under pressure is to write failing test scenarios simulating a time crunch. Then, develop the skill to enforce review steps and refactor the documentation to explicitly block rationalization loopholes.