writing-skills

Apply TDD methodology to author and refine AI skills.

3|Updated Dec 23, 2025
One-click install
npx skills add https://github.com/boazcstrike/opencode --skill writing-skills-boazcstrike
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/boazcstrike/opencode/tree/main/skills/writing-skills
Command: npx skills add https://github.com/boazcstrike/opencode --skill writing-skills-boazcstrike

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a rigorous, test-driven development (TDD) methodology specifically for creating and refining AI skills, ensuring they are effective, robust, and discoverable.

Core Features & Use Cases

  • TDD for Documentation: Adapts the RED-GREEN-REFACTOR cycle to skill creation, ensuring skills are written only after failing test cases (agent behaviors without the skill) are observed.
  • Bulletproofing Skills: Provides strategies to close loopholes and prevent agents from rationalizing around skill rules.
  • Use Case: When developing a new skill to enforce a specific coding standard, you would first write test scenarios where an AI agent fails to adhere to that standard. Then, you write the skill to correct that behavior, and finally, you refactor by testing against new rationalizations the AI might invent.

Quick Start

Use the writing-skills skill to create a new skill by first writing failing test scenarios for an agent.

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 AI skills?

Test-driven development for AI skills requires writing failing test scenarios for agent behaviors first, then writing the skill to correct that behavior, and finally refactoring to close rationalization loopholes.

What is the best way to prevent AI agents from rationalizing around skill rules?

Preventing AI agent rationalization involves applying a refactoring strategy that continuously tests skills against new loopholes the AI might invent, ensuring robust rule enforcement throughout the skill lifecycle.

How do I structure AI skill documentation for search optimization?

Structuring AI skill documentation for search optimization requires adhering to specific frontmatter, naming conventions, and content structure guidelines to maximize discoverability.

Can I apply the RED-GREEN-REFACTOR cycle to documentation and skill development?

Yes, you can apply the RED-GREEN-REFACTOR cycle to documentation by writing skills only after RED failing test cases are observed, GREEN by correcting the behavior, and REFACTOR by testing new rationalizations.

Why does my AI skill fail to enforce specific coding standards during testing?

AI skills fail to enforce coding standards when rationalization loopholes are not closed; you must test against agent behaviors without the skill first, then refactor the skill to prevent new rationalizations.

Do I need prior test scenarios before developing a new AI skill?

Yes, prior test scenarios are required; you must first write test scenarios where an AI agent fails to adhere to a specific standard before writing the skill to correct that behavior.