skills.rest
subham007ai
subham007aiCOMMUNITY
Explore all skills by this author →
GitHub

writing-skills

Create and refine AI Skills using a Test-Driven Development methodology.

Updated Aug 23, 2026
Search Tags:#testing#tdd#documentation#refactoring#skill creation#agent behavior
One-click install
npx skills add https://github.com/subham007ai/share-room --skill writing-skills-subham007ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/subham007ai/share-room/tree/main/.agent/skills/writing-skills
Command: npx skills add https://github.com/subham007ai/share-room --skill writing-skills-subham007ai

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 Skills: Apply the RED-GREEN-REFACTOR cycle to skill documentation.
  • Pressure Testing: Design scenarios that test skill compliance under realistic constraints (time, sunk cost, authority).
  • Rationalization Countermeasures: Identify and explicitly block common excuses agents use to bypass rules.
  • Use Case: When developing a new skill for enforcing coding standards, use this Skill to write failing tests first, then build the skill to pass those tests, and finally, refactor to close loopholes agents might exploit.

Quick Start

Use the writing-skills skill to create a new skill document following TDD principles.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I apply test-driven development to AI skill creation?▼

TDD for AI skills applies the RED-GREEN-REFACTOR cycle to skill documentation. You write failing pressure scenarios first, build the skill to pass those tests, then refactor to close loopholes and ensure compliance.

What are rationalization countermeasures in agent behavior testing?▼

Rationalization countermeasures identify and explicitly block common excuses agents use to bypass rules. They are implemented during skill refinement to ensure strict compliance under realistic constraints like time or sunk cost.

How do I design pressure scenarios to test agent compliance?▼

Designing pressure scenarios involves creating realistic constraints such as time, sunk cost, or authority pressure. These scenarios test whether the AI skill enforces discipline and maintains compliance when the agent attempts to bypass established rules.

Can I use this TDD methodology for refactoring existing reference skills?▼

Yes, the TDD methodology is applicable to developing and refining discipline-enforcing, technique, pattern, and reference skills. You refactor existing skills to close loopholes and improve discoverability while maintaining compliance.

Why does my AI skill fail under realistic constraints during testing?▼

Skills fail under realistic constraints when rationalization countermeasures are missing. The TDD framework helps identify these failures by testing agent behavior under pressure scenarios like time limits and sunk cost before finalizing the skill documentation.

Related Skills

Explore More Software Engineering Skills→
caobingshengcaobingsheng
1

tdd-workflows-tdd-red

Generate failing tests to define expected behavior in the TDD red phase.

Community
Advanced
KanuToCLKanuToCL

testing-skills-with-subagents

Test AI agent skills using Red-Green-Refactor and pressure simulations.

Community
Advanced
flosrnflosrn

writing-skills

Create and refine documentation skills using the RED-GREEN-REFACTOR test-driven cycle.

Community
Advanced
jmdueajmduea

writing-skills

Create, edit, and validate Claude skills with TDD-style guidelines and pressure-scenario templates.

Community
Advanced