writing-skills

Create and refine AI Skills using a RED-GREEN-REFACTOR test-driven cycle.

Updated Dec 11, 2025
One-click install
npx skills add https://github.com/Fancu1/dotfile --skill writing-skills-fancu1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/Fancu1/dotfile/tree/main/skills/writing-skills
Command: npx skills add https://github.com/Fancu1/dotfile --skill writing-skills-fancu1

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 robust against common failure modes.

Core Features & Use Cases

  • TDD for Documentation: Applies the Red-Green-Refactor cycle to skill authoring.
  • Pressure Testing: Develops skills that remain compliant under simulated real-world pressures (time, sunk cost, authority).
  • Rationalization Countermeasures: Explicitly addresses and prevents common AI rationalizations for bypassing rules.
  • Use Case: When developing a new skill for code review, use this Skill's methodology to write test scenarios that simulate a developer trying to skip review under time pressure, then write the skill to ensure compliance.

Quick Start

Follow the RED-GREEN-REFACTOR process outlined in this skill's documentation to create a new 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 for AI skill development?

TDD for AI skill development applies a strict RED-GREEN-REFACTOR cycle: write baseline tests first, create minimal skill logic to pass, then refactor to close loopholes. This ensures skills remain compliant and robust against failure modes.

What is the best way to prevent AI rationalization in skill documentation?

Preventing AI rationalization requires pressure testing during skill creation. By simulating real-world pressures like time or sunk cost, you write skills that explicitly counter rationalizations for bypassing documented rules and processes.

How does pressure testing improve AI compliance with documented processes?

Pressure testing improves AI compliance by simulating real-world constraints like time, sunk cost, and authority. This verifies that the skill enforces documented processes and resists bypassing rules under simulated stress.

Can I apply the RED-GREEN-REFACTOR cycle to refactoring existing AI skills?

Yes, you can apply the RED-GREEN-REFACTOR cycle to refactoring existing AI skills. It involves establishing baseline tests, writing minimal updates, and refactoring to close loopholes, ensuring continued compliance under pressure.

Do I need baseline testing to ensure my AI skill is discoverable and effective?

Yes, baseline testing is required to ensure your AI skill is discoverable and effective. It provides the initial RED phase in the TDD cycle, validating requirements before minimal skill writing and refactoring begin.