skill-authoring

Name: skill-authoring
Availability: InStock
Author: mrwillist

Validate SKILL.md entries using a RED-GREEN-REFACTOR workflow against pressure scenarios.

7|2|Updated Apr 30, 2026

Search Tags:#tdd #quality assurance #prompt engineering #agent behavior #claude search optimization #process validation #skill documentation

Ready to run

npx skills add https://github.com/MRWillisT/PullNexus --skill skill-authoring-mrwillist

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-authoring
Source: https://github.com/MRWillisT/PullNexus/tree/main/skills/skill-authoring
Command: npx skills add https://github.com/MRWillisT/PullNexus --skill skill-authoring-mrwillist

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents agent-skill documentation from being shipped without proof that it enforces the intended behavior, reducing silent failures and loopholes in how agents follow process rules.

Core Features & Use Cases

Pressure-scenario TDD for skills: Converts skill writing into a RED → GREEN → REFACTOR cycle using baseline behavior checks.
Compliance-first documentation: Ensures the skill is written so agents actively follow the documented rules, not just interpret them.
Claude search-optimized descriptions: Uses a “When to Use” description that avoids tempting the agent to shortcut the full instructions.

Quick Start

Use the skill-authoring process to validate a new or updated SKILL.md by running a pressure scenario without the skill, then writing the skill to make the specific failure modes pass, and finally refactoring until no rationalizations remain.

Frequently Asked Questions about skill-authoring

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

FAQPage Schema

How do I validate agent behavior documentation before shipping?▼

To validate agent behavior documentation, apply a RED-GREEN-REFACTOR workflow that proves compliance against pressure scenarios, checking that baseline failure tests pass and loopholes are closed before shipping.

What is TDD for prompt engineering and agent skills?▼

TDD for prompt engineering converts skill writing into a RED-GREEN-REFACTOR cycle using baseline behavior checks, ensuring agents actively follow documented process rules rather than just interpreting them.

How do I write a Claude search-optimized description for agent skills?▼

Write a Claude search-optimized description using a "When to Use" format that avoids tempting the agent to shortcut full instructions, ensuring the skill is reliably triggered during relevant tasks.

Why does my agent bypass process rules in the documentation?▼

Agents bypass process rules when documentation lacks compliance proof against pressure scenarios. Iterative loophole closure through refactoring ensures rationalizations are eliminated and pass behavior is reliable.

Do I need baseline failure tests for SKILL.md entries?▼

Yes, a TDD-mapped baseline failure test is required for SKILL.md entries to verify that the documented technique, pattern, or process rule actively enforces intended agent behavior.

What's the best way to ensure quality assurance for reusable agent techniques?▼

The best way to ensure quality assurance for reusable agent techniques is running a pressure scenario without the skill, writing the skill to fix specific failure modes, and refactoring until no rationalizations remain.