writing-skills

Author AI agent skills using the RED-GREEN-REFACTOR cycle.

Updated Nov 22, 2025
One-click install
npx skills add https://github.com/tom-xs/nixos-dotfiles --skill writing-skills-tom-xs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/tom-xs/nixos-dotfiles/tree/main/ai/kimi-skills/skills/writing-skills
Command: npx skills add https://github.com/tom-xs/nixos-dotfiles --skill writing-skills-tom-xs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill solves the problem of inconsistent or ineffective agent documentation by applying Test-Driven Development (TDD) principles to the creation of process guides, ensuring agents actually follow instructions under pressure.

Core Features & Use Cases

  • TDD for Documentation: Provides a structured RED-GREEN-REFACTOR cycle for writing and verifying skills.
  • Pressure-Testing Framework: Includes methodologies for creating scenarios that test agent compliance under time, authority, and sunk-cost pressures.
  • Use Case: Use this when you need to create a new skill for your agent and want to ensure it is bulletproof against rationalization and failure before deployment.

Quick Start

Use the writing-skills framework to create a new skill by first running a baseline pressure scenario to document how the agent fails without the 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 write process guides for AI agents?

TDD for agent documentation applies a structured RED-GREEN-REFACTOR cycle to author and verify skills, ensuring process guides remain compliant and bulletproof against rationalization before deployment.

How do I pressure-test agent skills against rationalization under high-pressure scenarios?

Pressure-testing agent skills involves running systematic scenarios with subagents that apply time, authority, and sunk-cost pressures to verify the agent resists rationalization and instruction failure.

What is the best way to ensure AI agents follow instructions under pressure?

Using a TDD-based documentation framework ensures agents follow instructions by first documenting a baseline failure scenario, then writing and verifying the skill against high-pressure rationalization attempts.

Do I need subagents to test compliance for discipline-enforcing AI skills?

Yes, the framework requires systematic pressure-testing with subagents to verify that discipline-enforcing, technique, and reference skills remain compliant under high-pressure scenarios.

When should I use a TDD framework for AI agent skill creation?

Use a TDD framework for agent skill creation when you need to build discipline-enforcing skills that must remain compliant under pressure and want to prevent rationalization failures before deployment.