writing-skills

Apply RED-GREEN-REFACTOR workflow to craft SKILL.md documentation with baselining and compliance checks.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/JasonVene/CC_MainDev --skill writing-skills-jasonvene
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/JasonVene/CC_MainDev/tree/main/_archive/imports/downloads/superpowers-main/skills/writing-skills
Command: npx skills add https://github.com/JasonVene/CC_MainDev --skill writing-skills-jasonvene

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Writing Skills apply test-driven development principles to process documentation to prevent rationalizations and ensure consistent, reusable skill definitions.

Core Features & Use Cases

  • RED-GREEN-REFACTOR workflow applied to documentation to catch and close loopholes.
  • Structured baselining: observe agent behavior without the skill, capture rationalizations, then iterate to bulletproof compliance.
  • Cross-cutting guidance for crafting concise, discoverable SKILL.md entries that are easy to load in Claude with progressive disclosure.

Quick Start

Run baseline failure scenarios, draft a minimal skill to address them, then retest for full compliance.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I use test-driven development to write better agent documentation?

Test-driven development for documentation applies a RED-GREEN-REFACTOR workflow to catch rationalizations and close loopholes. You observe baseline agent failures, draft a minimal skill to address them, then retest for full compliance.

What is the best way to stop AI agents from finding rationalizations in my instructions?

To stop rationalizations, you capture baseline failure scenarios where the agent deviates from intent, then iterate on the documentation to close those specific loopholes. This structured baselining ensures bulletproof compliance.

How do I create a SKILL.md file that follows progressive disclosure principles?

Creating a SKILL.md with progressive disclosure involves structuring concise, discoverable entries that define trigger contexts and usage conditions. This makes the skill easy to load in Claude without overwhelming the context window.

Do I need YAML frontmatter to define when an agent should use a specific skill?

Yes, YAML frontmatter is required to define when to use the skill and the contexts in which it should trigger. This structured metadata ensures the agent loads the correct instructions at the appropriate time.

How does the RED-GREEN-REFACTOR workflow apply to documentation quality assurance?

The RED-GREEN-REFACTOR workflow applies to documentation quality assurance by first capturing baseline failures, drafting minimal guidance to make tests pass, then refactoring gaps to achieve consistent, reusable skill definitions.

Why does my agent ignore documentation instructions and how can I fix it?

Agents ignore documentation when rationalizations exploit gaps in the instructions. Fix this by running baseline failure scenarios, observing the exact deviations, and iterating on the skill definition until full compliance is achieved.