writing-skills

Apply RED-GREEN-REFACTOR cycles to author and validate AI skills.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/benjgrad/clawdbot --skill writing-skills-benjgrad
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/benjgrad/clawdbot/tree/main/skills/writing-skills
Command: npx skills add https://github.com/benjgrad/clawdbot --skill writing-skills-benjgrad

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a rigorous, test-driven development (TDD) framework for creating, editing, and verifying AI skills, ensuring they are robust, discoverable, and effective.

Core Features & Use Cases

  • TDD for Documentation: Adapts the RED-GREEN-REFACTOR cycle to skill authoring.
  • Pressure Testing: Develops scenarios to test skills under realistic constraints (time, sunk cost, authority).
  • Rationalization Countermeasures: Identifies and explicitly addresses common excuses agents use to bypass rules.
  • Use Case: When developing a new skill for code review, you'll use this skill to write failing test scenarios (e.g., an agent trying to skip review under time pressure), then write the skill to enforce the review, and finally refactor to close any loopholes the agent finds.

Quick Start

Use the writing-skills skill to create a new skill by following the RED-GREEN-REFACTOR process.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I use test-driven development for AI skill authoring?

Test-driven development for AI skill authoring uses a RED-GREEN-REFACTOR cycle to write failing pressure scenarios first, then builds the skill to pass them, and finally refactors to close loopholes. This ensures robust agent compliance and documentation.

What are pressure scenarios in skill testing?

Pressure scenarios in skill testing are constraints like time, sunk cost, and authority designed to test AI agents under realistic conditions. They verify that the agent adheres to skill rules instead of rationalizing its way out of compliance.

How do I prevent an AI agent from bypassing skill documentation rules?

To prevent an AI agent from bypassing skill documentation rules, you identify common rationalizations and explicitly address them during iterative refactoring. This countermeasure closes loopholes the agent uses to skip required processes.

What is the best way to validate agent compliance for a new skill?

The best way to validate agent compliance is through iterative refactoring and rationalization analysis. You develop pressure scenarios to test the skill, enforce rules, and refactor the documentation until the agent can no longer find loopholes.

Do I need any specific frameworks to start TDD skill development?

No specific external frameworks are required to start TDD skill development. The process relies on scripts and references to implement the RED-GREEN-REFACTOR cycle, focusing entirely on internal documentation and pressure testing logic.