writing-skills

Apply test-driven RED-GREEN-REFACTOR verification to author SKILL.md files under pressure scenarios.

Updated Mar 3, 2026
One-click install
npx skills add https://github.com/jacexh/skills --skill writing-skills-jacexh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/jacexh/skills/tree/main/skills/writing-skills
Command: npx skills add https://github.com/jacexh/skills --skill writing-skills-jacexh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ensures AI skill authors produce discoverable, concise, and testable SKILL.md documentation that agents reliably follow under real-world pressures and temptations to bypass rules.

Core Features & Use Cases

  • Test-Driven Skill Authoring: Maps RED-GREEN-REFACTOR to skill creation so authors write failing baseline scenarios, create minimal skills, and iteratively close loopholes.
  • Pressure Testing & Verification: Provides templates and scenarios to simulate time, sunk-cost, and authority pressures so skills enforce discipline when compliance is hardest.
  • Discovery & CSO Guidance: Prescribes frontmatter, description design, keyword coverage, and token-efficient authoring to help agents find and load the right skill when needed.

Quick Start

Run a RED-GREEN-REFACTOR check: execute a realistic pressure scenario without the skill, document exact failures, write or update SKILL.md to address those failures, and re-run the scenario until the agent complies.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
What is test-driven documentation for agent skills?

Test-driven documentation applies RED-GREEN-REFACTOR cycles to skill authoring, writing failing baseline scenarios first, then creating minimal SKILL.md files to address exact agent failures under pressure.

How do I verify AI agent skills comply with rules under pressure?

Verify agent skills by running pressure testing scenarios that simulate time constraints, sunk-cost pressures, and authority-driven decisions, documenting rationalizations until the agent reliably follows process rules.

How do I create a SKILL.md file that agents reliably follow?

Create reliable SKILL.md files by executing a realistic pressure scenario without the skill, documenting exact failures, writing minimal content to address them, and re-running until full agent compliance.

Does skill authoring require specific frontmatter for agent discovery?

Skill authoring requires concise SKILL.md frontmatter, description design, keyword coverage, and token-efficient content to ensure agents discover and load the correct skill when needed.

What are the limitations of test-driven skill authoring?

Test-driven skill authoring focuses specifically on pressure scenarios involving time, sunk-cost, and authority pressures, requiring iterative verification loops to close loopholes rather than one-time validation.

Can I use test-driven development for editing existing AI agent skills?

Test-driven development applies to creating, editing, and verifying AI agent skills by mapping RED-GREEN-REFACTOR checks to update existing SKILL.md documentation and close compliance loopholes.