arc-writing-skills

Enforce a test-driven RED-GREEN-REFACTOR cycle for creating AI skills.

6|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/GregoryHo/arcforge --skill arc-writing-skills
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: arc-writing-skills
Source: https://github.com/GregoryHo/arcforge/tree/main/skills/arc-writing-skills
Command: npx skills add https://github.com/GregoryHo/arcforge --skill arc-writing-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and 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 discoverable, effective, and resistant to common AI rationalizations.

Core Features & Use Cases

  • Skill Development Workflow: Guides users through the RED-GREEN-REFACTOR cycle for skill creation.
  • Testing Methodology: Outlines how to test skills with subagents under pressure scenarios.
  • Rationalization Prevention: Provides techniques to close loopholes and prevent AI agents from bypassing skill rules.
  • Use Case: When developing a new skill for code review, use this skill to ensure it's clear, enforceable, and tested against common AI shortcuts.

Quick Start

Follow the RED-GREEN-REFACTOR cycle to write a new skill for your AI agent.

Frequently Asked Questions about arc-writing-skills

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

FAQPage Schema
How do I use test-driven development for AI prompt engineering?

Test-driven development for AI prompt engineering applies the RED-GREEN-REFACTOR cycle to skill creation, ensuring AI agents comply with rules before deployment. This methodology tests skills under pressure scenarios to prevent rationalization and enforce documentation standards.

Why does my AI agent bypass rules and rationalize outputs under pressure?

AI agents rationalize outputs under pressure when skills lack rigorous testing and loophole closures. Preventing AI rationalization requires applying specific testing protocols with subagents to ensure compliance and enforce skill rules during edge cases.

What is the best way to structure AI documentation for skill discoverability?

Structuring AI documentation for discoverability requires following specific documentation standards that outline use cases, testing methodologies, and core features. Adhering to these standards ensures skills remain effective, clear, and easily found by agents across the lifecycle.

How do I test AI skills against common shortcuts and rationalizations?

Testing AI skills against common shortcuts involves evaluating them with subagents under pressure scenarios. This approach closes loopholes and prevents AI agents from bypassing skill rules, ensuring the skill remains enforceable during deployment.

Do I need prior testing experience to create effective AI skills?

Prior testing experience is not explicitly required, but adherence to the RED-GREEN-REFACTOR cycle is mandatory. The skill development workflow guides users through testing protocols and documentation standards to ensure created skills are clear and enforceable.