writing-skills

Apply test-driven development to create and validate SKILL.md files.

Updated Apr 29, 2026
One-click install
npx skills add https://github.com/pgm1980/stryker-netx --skill writing-skills-pgm1980
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/pgm1980/stryker-netx/tree/main/.claude/skills/writing-skills
Command: npx skills add https://github.com/pgm1980/stryker-netx --skill writing-skills-pgm1980

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Improves how teams create and validate agent Skills by applying test-driven development to process documentation, preventing unclear instructions and loopholes under pressure.

Core Features & Use Cases

  • TDD for documentation: RED (watch violations), GREEN (write minimal guidance), REFACTOR (close new rationalizations).
  • Claude Search Optimization (CSO): crafts a discovery-focused description using concrete triggers, symptoms, and searchable keywords.
  • Skill authoring structure: enforces consistent SKILL.md frontmatter, naming conventions, and progressive disclosure practices.

Quick Start

Use the skill when creating a new SKILL.md entry or editing an existing one, then verify it works under pressure before deployment.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I write process documentation that agents follow under pressure?

Writing Skills applies a test-driven development cycle to process documentation, forcing agents to follow rules under time, authority, or sunk-cost pressure rather than rationalizing loopholes. It uses a RED-GREEN-REFACTOR workflow to build loophole-resistant instructions.

What is test-driven development for SKILL.md authoring?

Test-driven development for SKILL.md authoring is a cycle where you watch for instruction violations (RED), write minimal guidance to fix them (GREEN), and refactor to close new rationalizations (REFACTOR). This ensures process documentation remains reliable and compliant under pressure.

How do I optimize Claude search discovery for agent skills?

To optimize Claude search discovery, craft a discovery-focused description using concrete triggers, symptoms, and searchable keywords. This satisfies CSO discovery constraints by treating the description as a when-to-use guide rather than a general summary.

Does this skill authoring workflow enforce YAML metadata compliance?

Yes, the skill authoring workflow enforces consistent SKILL.md frontmatter and YAML metadata requirements, including name and description fields. It validates these constraints alongside CSO discovery rules during the RED-GREEN-REFACTOR cycle.

What's the best way to validate that agent instructions resist rationalization?

The best way to validate rationalization resistance is running a RED-GREEN-REFACTOR cycle that watches for violations under simulated pressure, writes minimal guidance to close them, and refactors to prevent new loopholes. Verify the SKILL.md works under pressure before deployment.

Can I use this approach to edit existing process documentation?

Yes, you can use this test-driven approach when creating a new SKILL.md entry or editing an existing one. The workflow validates that existing instructions hold up under time, authority, or sunk-cost pressure before deployment.