writing-skills

Apply the RED-GREEN-REFACTOR cycle to create and refine documentation skills.

2|1|Updated Jun 21, 2025
One-click install
npx skills add https://github.com/MeechYourGoals/Chravel --skill writing-skills-meechyourgoals
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/MeechYourGoals/Chravel/tree/main/.claude/plugins/superpowers/skills/writing-skills
Command: npx skills add https://github.com/MeechYourGoals/Chravel --skill writing-skills-meechyourgoals

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 documentation skills, ensuring they are discoverable, effective, and robust against misuse.

Core Features & Use Cases

  • TDD for Documentation: Applies the RED-GREEN-REFACTOR cycle to skill development, starting with failing tests (baseline agent behavior) before writing the skill.
  • Bulletproofing Skills: Offers strategies to close loopholes and prevent rationalizations that lead to skill misuse.
  • Use Case: When developing a new skill for code review, you would first run scenarios where an agent fails to perform a proper review without the skill. Then, you write the skill to address those specific failures, and finally, test again to ensure compliance under pressure.

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
How do I use TDD to create AI documentation skills?

To use TDD for AI documentation skills, establish a failing test baseline of agent behavior before authoring the skill, then apply the RED-GREEN-REFACTOR cycle to continuously refine it.

What is the best way to prevent agent rationalization in skill development?

Preventing agent rationalization in skill development requires continuous refactoring against baseline agent behaviors to close loopholes and ensure adherence to specific YAML frontmatter and token efficiency guidelines.

How does the RED-GREEN-REFACTOR cycle apply to skill authoring?

The RED-GREEN-REFACTOR cycle applies to skill authoring by first running scenarios where an agent fails without the skill, writing the skill to fix those failures, and testing again to ensure compliance under pressure.

Do I need specific YAML frontmatter for Claude Search Optimization?

Yes, achieving Claude Search Optimization requires adherence to specific YAML frontmatter, naming conventions, and token efficiency guidelines to ensure your documentation skills are discoverable and effective.

Why does my AI agent misuse documentation skills under pressure?

AI agents misuse documentation skills under pressure due to loopholes in the skill design that allow rationalizations, which can be addressed by establishing a failing test baseline and continuously refactoring against agent behavior.