skills.rest
mortenbroesby
mortenbroesbyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

writing-skills

Codify and validate Skills using a RED-GREEN-REFACTOR workflow.

1|Updated Apr 5, 2026
Search Tags:#tdd#documentation#red-green-refactor#skill-writing#testing-skills
One-click install
npx skills add https://github.com/mortenbroesby/playground --skill writing-skills-mortenbroesby
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/mortenbroesby/playground/tree/main/.skills/writing-skills
Command: npx skills add https://github.com/mortenbroesby/playground --skill writing-skills-mortenbroesby

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a disciplined framework for documenting, testing, and validating Skills (via a RED-GREEN-REFACTOR cycle) to ensure reliable agent behavior and prevent rationalizations from creeping into production.

Core Features & Use Cases

  • Test-driven skill creation: apply RED-GREEN-REFACTOR to writing and updating SKILL.md content.
  • Rationalization control: build and maintain a rationalization table and red flags to prevent edge-case loopholes.
  • Deployment-readiness: enforce pre-deployment verification and documented guidelines to ensure consistent Skill quality.

Quick Start

Draft a Skill by first capturing a failing baseline test (RED), then implement the Skill (GREEN), and finally close loopholes (REFACTOR) in a single iterative cycle.

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 and validate agent skills?▼

TDD-guided skill writing uses a RED-GREEN-REFACTOR cycle to validate SKILL.md content, capturing a failing test first, implementing the Skill, then closing loopholes to ensure predictable agent behavior.

What is the RED-GREEN-REFACTOR workflow for skill documentation?▼

The RED-GREEN-REFACTOR workflow for skill documentation captures a failing baseline test, implements the Skill, and refines it to close edge-case loopholes in a single iterative cycle.

How do I prevent rationalizations from creeping into production agent skills?▼

Prevent rationalizations in production agent skills by building a rationalization table with red flags, enforcing structured testing and pre-deployment verification to block edge-case loopholes.

What format does a SKILL.md file need for Claude discovery?▼

A SKILL.md file requires YAML frontmatter with name and description fields, plus a compact, token-conscious structure to optimize Claude discovery and deployment readiness.

Can I edit existing skills using test-driven validation, or is it only for new ones?▼

Test-driven validation applies to creating new Skills, editing existing ones, and verifying readiness before deployment, ensuring consistent quality and rationalization control across updates.

Related Skills

Explore More Content & Communication Skills→
beyondwenbeyondwen

writing-skills

Draft YAML-based SKILL.md units with standardized frontmatter for Claude-like agents.

Community
Advanced
mkurmanmkurman
321

writing-skills

Apply test-driven development to Skill documentation with RED, GREEN, and REFACTOR phases.

Community
Advanced
dsifrydsifry
60

testing-skills-with-subagents

Run RED-GREEN-REFACTOR testing cycles on documentation-based skills.

Community
Advanced
quangphu1912quangphu1912
1

writing-skills

Develop and maintain AI agent skills with test-driven documentation.

Community
Advanced