writing-skills

Create and maintain AI agent skills using Test-Driven Development cycles.

2|Updated Apr 15, 2026

Search Tags:#testing #tdd #documentation #refactoring #process #agent-skills

Ready to run

npx skills add https://github.com/getspur/spur --skill writing-skills-getspur

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/getspur/spur/tree/main/.spur/skills/writing-skills
Command: npx skills add https://github.com/getspur/spur --skill writing-skills-getspur

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

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

Core Features & Use Cases

TDD-Based Authoring: Ensures documentation is validated through a RED-GREEN-REFACTOR cycle using agent pressure scenarios.
Rationalization Prevention: Provides frameworks to identify and block agent loopholes, ensuring compliance under stress.
Use Case: Use this when you need to create a new skill or update an existing one to ensure that the resulting documentation is robust, testable, and effectively followed by AI agents.

Quick Start

Use the writing-skills framework to define a new skill by first running a baseline pressure scenario to document agent failures.

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 methodology to write AI agent process documentation?▼

To apply TDD methodology to process documentation, you standardize skill creation using the RED-GREEN-REFACTOR cycle. This cycle runs baseline agent pressure scenarios to validate documentation reliability and ensure AI compliance before deployment.

Why does my AI agent fail to follow process documentation under stress?▼

AI agents fail to follow process documentation under stress due to rationalization loopholes. You can prevent this by applying explicit loophole-closing frameworks during the documentation authoring process to ensure strict compliance.

What is the best way to create reliable and testable reference guides for AI agents?▼

The best way to create reliable reference guides for AI agents is using a TDD-based authoring framework. This approach validates your reusable techniques through agent pressure scenarios, ensuring the documentation is robust and effectively followed.

How do I start the RED-GREEN-REFACTOR cycle when creating a new agent skill?▼

To start the RED-GREEN-REFACTOR cycle for a new agent skill, you first run a baseline pressure scenario to document initial AI agent failures. You then iteratively refactor the documentation to close rationalization loopholes and pass the tests.

Can I use this TDD framework to update existing process documentation?▼

Yes, you can use this TDD framework to update existing process documentation. It applies the RED-GREEN-REFACTOR cycle and loophole-closing strategies to mature your current reference guides, ensuring they remain robust and testable for agent compliance.