writing-skills

Guide AI Skill creation using the RED-GREEN-REFACTOR test-driven cycle.

1|2|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/cinjoff/fhhs-skills --skill writing-skills-cinjoff
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/cinjoff/fhhs-skills/tree/main/skills/writing-skills
Command: npx skills add https://github.com/cinjoff/fhhs-skills --skill writing-skills-cinjoff

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 AI Skills, ensuring they are discoverable, effective, and resistant to manipulation.

Core Features & Use Cases

  • Test-Driven Skill Development: Apply the RED-GREEN-REFACTOR cycle to skill documentation.
  • Rationalization Countermeasures: Develop strategies to prevent agents from bypassing skill rules under pressure.
  • Use Case: When developing a new skill for code review, use this skill's methodology to write failing test scenarios first, then build the skill to pass those tests, and finally refactor to prevent common rationalizations for skipping reviews.

Quick Start

Follow the RED-GREEN-REFACTOR cycle to create or update a skill.

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 an AI agent skill?

To use TDD for AI agent skill creation, you apply the RED-GREEN-REFACTOR cycle: write failing test scenarios first, build the skill documentation to pass those tests, then refactor to prevent rationalizations. This ensures rigorous agent compliance.

Why does my AI agent bypass skill rules under pressure?

AI agents bypass skill rules under pressure due to rationalization. You prevent this by developing countermeasures through rigorous testing scenarios that force the agent to adhere to documented processes even when pressured to skip steps.

What is test-driven development for skill documentation?

Test-driven development for skill documentation is applying the RED-GREEN-REFACTOR cycle to skill creation. You write failing test scenarios first, build the skill to pass those tests, and refactor to prevent common rationalizations for skipping processes.

Can I apply this testing methodology to any type of AI skill?

Yes, you can apply this testing methodology to all skill types requiring agent adherence to documented processes. It is applicable to any AI skill development needing strict compliance and resistance to manipulation.

What is the best way to ensure agent compliance with documented processes?

The best way to ensure agent compliance is using a test-driven development methodology with rationalization countermeasures. You build rigorous testing scenarios that prevent agents from bypassing skill rules under pressure.

How do I prevent common rationalizations for skipping code reviews in AI?

To prevent rationalizations for skipping code reviews, use the RED-GREEN-REFACTOR cycle to build countermeasures into the skill. Write failing test scenarios first, then build and refactor the skill to enforce compliance.