writing-skills

Standardize agent skill creation and verification with a RED-GREEN-REFACTOR cycle.

2|Updated Mar 29, 2026
One-click install
npx skills add https://github.com/NagyVikt/codex-plugins --skill writing-skills-nagyvikt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/NagyVikt/codex-plugins/tree/main/plugins/superpowers/skills/writing-skills
Command: npx skills add https://github.com/NagyVikt/codex-plugins --skill writing-skills-nagyvikt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the problem of inconsistent, unreliable, or poorly understood agent documentation by applying Test-Driven Development (TDD) principles to the creation of skills themselves.

Core Features & Use Cases

  • TDD for Documentation: Provides a structured RED-GREEN-REFACTOR cycle for writing and verifying skills.
  • Rationalization Countering: Includes patterns to identify and block agent rationalizations that lead to rule-breaking.
  • Use Case: Use this when you need to create a new skill or update an existing one to ensure it is bulletproof, verifiable, and resistant to being ignored by the agent under pressure.

Quick Start

Use the writing-skills framework to create a new skill by first defining a failing pressure scenario and then documenting the agent's baseline behavior.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I apply TDD to process documentation for AI agents?

Testing agent documentation with TDD involves defining a failing pressure scenario first, then documenting baseline behavior to verify compliance. This structured RED-GREEN-REFACTOR cycle ensures your skills remain bulletproof under high-pressure scenarios.

What is the best way to stop agents from breaking rules under high pressure?

To stop agents from breaking rules under high pressure, use TDD patterns that identify and block rationalizations leading to rule-breaking. This counters agent rationalizations by enforcing strict documentation verification during the development cycle.

How do I create verifiable agent skills that resist being ignored?

Creating verifiable agent skills requires standardizing creation through a RED-GREEN-REFACTOR cycle. You define a failing pressure scenario, document the baseline behavior, and iteratively refine the skill to ensure it is bulletproof and resistant to being ignored.

Does TDD for agent skills work with reference and technique workflows?

Yes, TDD for agent skills applies directly to the development of discipline-enforcing, technique, and reference skills within agent-based workflows. It standardizes their creation and verification to ensure documentation compliance across these specific workflow types.

Why does my agent ignore process documentation during complex tasks?

Agents ignore process documentation during complex tasks due to rationalizations that lead to rule-breaking under high-pressure scenarios. Implementing a TDD verification cycle identifies and blocks these rationalizations, ensuring strict compliance with the defined documentation.