writing-skills

Apply Test-Driven Development cycles to create and refine AI skills.

Updated Dec 1, 2025
One-click install
npx skills add https://github.com/Come0520/L2C --skill writing-skills-come0520
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/Come0520/L2C/tree/main/.agent/skills/writing-skills
Command: npx skills add https://github.com/Come0520/L2C --skill writing-skills-come0520

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a rigorous, test-driven framework for creating and refining AI skills, ensuring they are discoverable, effective, and resistant to misuse.

Core Features & Use Cases

  • TDD for Documentation: Adapts the Test-Driven Development cycle (RED-GREEN-REFACTOR) to skill authoring.
  • Pressure Testing: Uses realistic scenarios with combined pressures (time, sunk cost, authority) to identify and fix loopholes.
  • Rationalization Countermeasures: Explicitly addresses common excuses agents use to bypass rules.
  • Use Case: When developing a new skill for code review, use this skill's methodology to write failing tests first, then the skill, and finally refactor to ensure agents always comply even under pressure.

Quick Start

Follow the TDD cycle: write a failing test scenario, then write the skill to make it pass, then refactor to close loopholes.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I use TDD to create AI skills that resist agent rationalization?

Test-driven development for AI skills applies the RED-GREEN-REFACTOR cycle to documentation, using pressure scenarios like sunk cost or authority to identify rule bypasses. It explicitly addresses rationalization countermeasures to guarantee agent compliance with procedures.

What is the best way to pressure test AI agent behavior for rule compliance?

Pressure testing AI agent behavior involves simulating realistic scenarios with combined pressures like time and authority to find documentation loopholes. Applying rationalization countermeasures ensures agents follow rules even under stress, yielding robust and effective skills.

How do I write documentation that prevents AI agents from bypassing rules?

Writing documentation to prevent rule bypasses requires rationalization tables and explicit countermeasures against common agent excuses. By testing documentation against pressure scenarios, you guarantee agents follow procedures and maintain robust compliance.

What are common limitations of using TDD for skill creation?

Limitations of TDD for skill creation include the difficulty of anticipating every agent rationalization and pressure scenario. Without continuous refactoring and comprehensive pressure testing, undiscovered loopholes may allow agents to bypass documented procedures.