writing-skills

Guide AI skill creation with a RED-GREEN-REFACTOR testing cycle.

Updated Feb 18, 2026
One-click install
npx skills add https://github.com/riddopic/cc-tools --skill writing-skills-riddopic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/riddopic/cc-tools/tree/main/.claude/skills/writing-skills
Command: npx skills add https://github.com/riddopic/cc-tools --skill writing-skills-riddopic

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a rigorous framework for creating and refining AI skills, ensuring they are effective, robust, and adhere to best practices by applying Test-Driven Development (TDD) principles to documentation.

Core Features & Use Cases

  • TDD for Skills: Enforces the "Red-Green-Refactor" cycle for skill development, ensuring skills are built to address specific failures.
  • Pressure Testing: Guides the creation of realistic scenarios with multiple pressures (time, sunk cost, authority) to test skill compliance.
  • Rationalization Countermeasures: Provides methods to identify and close loopholes where AI agents might rationalize bypassing skill instructions.
  • Use Case: When developing a new skill for code review, you would first create scenarios where an AI fails to follow best practices without the skill (RED), then write the skill to address those failures (GREEN), and finally test against new rationalizations to ensure continued compliance (REFACTOR).

Quick Start

Use the writing-skills skill to create a new skill by following the TDD 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 agent skills?

To use TDD for AI agent skills, you create failure scenarios without the skill (RED), write documentation to pass them (GREEN), and refactor to close loopholes (REFACTOR).

Why does my AI agent bypass skill documentation?

AI agents bypass skill documentation by rationalizing instructions under pressures like time, sunk cost, or authority. You can fix this by applying pressure testing and explicit counter-measures to close those loopholes.

What is the Red-Green-Refactor cycle for skill development?

The Red-Green-Refactor cycle for skill development is a TDD methodology where you document failure scenarios (RED), write instructions to address them (GREEN), and test against new rationalizations to ensure compliance (REFACTOR).

How do I pressure test an AI agent for instruction compliance?

You pressure test an AI agent by creating realistic scenarios with multiple pressures like time constraints, sunk costs, and authority figures to evaluate if the agent rationalizes bypassing its skill instructions.

What are rationalization countermeasures in AI skills?

Rationalization countermeasures in AI skills are methods to identify and close loopholes where agents might justify bypassing instructions, enforced through iterative refactoring and explicit documentation rules.

Can I apply Test-Driven Development to AI documentation?

Yes, you can apply Test-Driven Development to AI documentation by treating instructions as code, writing tests for agent failures first, and refining the text through a Red-Green-Refactor cycle to ensure robust compliance.