writing-skills

Guide AI skill creation using a RED-GREEN-REFACTOR test-driven cycle.

34|5|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/weiping/pi-superpowers --skill writing-skills-weiping
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/weiping/pi-superpowers/tree/main/skills/writing-skills
Command: npx skills add https://github.com/weiping/pi-superpowers --skill writing-skills-weiping

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 improving AI skills, ensuring they are effective, reliable, and adhere to best practices.

Core Features & Use Cases

  • Test-Driven Skill Development: Enforces the RED-GREEN-REFACTOR cycle for skill creation and modification.
  • Rationalization Countermeasures: Provides methods to identify and block common excuses agents use to bypass skill rules.
  • Use Case: When developing a new skill for code review, use this skill to ensure the review process is always followed, even under pressure, by first defining failure scenarios and then writing the skill to prevent them.

Quick Start

Use the writing skills skill to create a new skill for summarizing meeting transcripts.

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 uses a RED-GREEN-REFACTOR cycle to write verifiable skills. You first define failure scenarios and pressure tests, then author the skill to pass them, ensuring robust and reliable agent behaviors.

How do I stop AI agents from bypassing skill rules under pressure?

To stop AI agents from bypassing skill rules under pressure, apply explicit counter-rationalization techniques. This identifies and blocks common excuses agents use to skip required workflows during task execution.

What is the best way to document AI skills?

The best way to document AI skills is to enforce concise descriptions and clear workflows during the refactoring phase. This test-driven refinement ensures the skill's metadata accurately represents its processing logic.

Do I need testing frameworks to refactor AI skills?

You need testing frameworks to refactor AI skills safely because the process enforces a RED-GREEN-REFACTOR cycle. Defining explicit tests first ensures that refactoring improves the skill without breaking existing verifiable behaviors.

Why does my AI skill fail during complex code review tasks?

AI skills fail during complex code review tasks due to missing pressure testing and rationalization countermeasures. Without defining failure scenarios first, agents bypass the required review process when encountering execution pressure.