creating-skills

Name: creating-skills
Availability: InStock
Author: otherCode

Guide creating, testing, and refining AI skills with Test-Driven Development.

Updated Feb 12, 2026

Search Tags:#tdd #documentation #refactoring #prompt engineering #skill creation #agent testing

Ready to run

npx skills add https://github.com/othercode/profiles --skill creating-skills-othercode

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: creating-skills
Source: https://github.com/othercode/profiles/tree/main/plugins/prompt-engineering/skills/creating-skills
Command: npx skills add https://github.com/othercode/profiles --skill creating-skills-othercode

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a comprehensive guide to creating, testing, and refining AI skills, ensuring they are discoverable, effective, and robust against common pitfalls.

Core Features & Use Cases

Skill Authoring Methodology: Learn the Test-Driven Development (TDD) approach for skills, focusing on writing failing tests before documentation.
Testing Under Pressure: Understand how to create scenarios that test skills against combined pressures like time constraints, sunk costs, and authority.
Bulletproofing Skills: Discover techniques to close loopholes, address rationalizations, and make skills resistant to bypass.
Use Case: You're tasked with creating a new skill for code review. This guide will walk you through writing the skill, testing it with subagents under pressure, and ensuring it's adopted correctly.

Quick Start

Follow the RED-GREEN-REFACTOR cycle to create a new skill for your project.

Frequently Asked Questions about creating-skills

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

FAQPage Schema

How do I create AI agent skills using a Test-Driven Development approach?▼

To create AI agent skills using Test-Driven Development, follow the RED-GREEN-REFACTOR cycle by writing failing pressure tests first, then authoring the skill documentation to pass them, and finally refining the prompts. This methodology ensures your skills are effective and robust against rationalization.

What is skill pressure testing and how does it prevent AI bypass?▼

Skill pressure testing evaluates AI behavior under combined constraints like time limits, sunk costs, and authority figures to close loopholes. By creating these scenarios, you bulletproof skills against rationalization and ensure agents resist bypassing your defined instructions.

How should I name AI skills for optimal agent discovery?▼

Naming AI skills for optimal agent discovery requires following specific conventions outlined in skill authoring best practices. Proper naming ensures your created skills are easily discoverable by AI agents, facilitating correct adoption and iterative development within your project.

Can I test created skills with subagents before final deployment?▼

Yes, you can test created skills with subagents before final deployment by placing them in simulated pressure scenarios. This iterative development process allows you to evaluate agent behavior, address rationalizations, and refine the skill documentation against combined constraints.

What is the best way to bulletproof AI prompts against rationalization?▼

The best way to bulletproof AI prompts against rationalization is to use a Test-Driven Development methodology that creates specific pressure scenarios. This approach closes loopholes by actively testing skills against sunk costs, authority figures, and time constraints before finalizing documentation.

Why does my AI skill bypass instructions under authority pressure?▼

AI skills bypass instructions under authority pressure because they are not adequately bulletproofed against rationalizations. To fix this, you must implement pressure scenario testing using TDD, explicitly targeting combined constraints like authority and sunk costs to close logical loopholes.