writing-skills

Create and validate agent Skills using a test-driven RED-GREEN-REFACTOR workflow.

1|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/danilonovaisv/PROMPT-APP --skill writing-skills-danilonovaisv
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/danilonovaisv/PROMPT-APP/tree/main/.agent/skills/writing-skills
Command: npx skills add https://github.com/danilonovaisv/PROMPT-APP --skill writing-skills-danilonovaisv

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a disciplined, test-driven approach to creating, editing, and validating Skills as reusable documentation patterns, reducing ambiguity and preventing rationalizations before deployment.

Core Features & Use Cases

  • TDD-based Skill creation workflow (RED-GREEN-REFACTOR) applied to documentation
  • Structured frontmatter, progressive disclosure, and targeted references to keep context focused
  • Guidance on testing skills with subagents and capturing exact rationalizations for improvement

Quick Start

Draft a new SKILL.md for a target capability and run a RED-GREEN-REFACTOR test cycle.

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 to writing agent skills and documentation?

Applying TDD to skill-writing involves running a RED-GREEN-REFACTOR test cycle against a drafted SKILL.md, validating frontmatter discipline and capturing rationalizations to ensure documentation is tested and reusable.

What is the best way to prevent rationalizations when creating agent skills?

Preventing rationalizations requires a structured, test-driven template that captures exact rationalizations during subagent testing, enforcing disciplined development practices before deployment.

How do I keep context lean when developing reusable agent skills?

Keeping context lean requires enforcing structured frontmatter, progressive disclosure, and controlled references in your SKILL.md, ensuring discoverability and safety across tasks without overloading the agent.

Do I need any dependencies to start testing skills with subagents?

No dependencies are required to start testing skills with subagents. You only need to draft a new SKILL.md for a target capability and execute the structured RED-GREEN-REFACTOR test cycle.

Why does my agent skill documentation fail during deployment validation?

Skill documentation fails validation due to poor frontmatter discipline, uncontrolled references expanding context, or unchecked rationalizations that a test-driven development workflow is designed to catch.