skills.rest
vrazdalovschi
vrazdalovschiCOMMUNITY
Explore all skills by this author →
GitHub

writing-skills

Apply RED-GREEN-REFACTOR cycles to author and test AI skills.

Updated Jan 10, 2026
Search Tags:#testing#tdd#documentation#refactoring#skill creation#agent behavior
One-click install
npx skills add https://github.com/vrazdalovschi/dotfiles --skill writing-skills-vrazdalovschi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/vrazdalovschi/dotfiles/tree/main/agents/skills/shared/writing-skills
Command: npx skills add https://github.com/vrazdalovschi/dotfiles --skill writing-skills-vrazdalovschi

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: Applies the RED-GREEN-REFACTOR cycle to skill authoring.
  • Pressure Testing: Develops skills that remain compliant under simulated real-world pressures (time, sunk cost, authority).
  • Rationalization Countermeasures: Identifies and explicitly addresses common excuses agents use to bypass rules.
  • Use Case: When developing a new skill for code review, use this framework to write failing tests first, then build the skill, and finally, test it against scenarios where an agent might be tempted to skip steps due to time pressure.

Quick Start

Use the writing-skills skill to create a new skill for validating API responses.

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 for AI agent skill creation?▼

Test-driven development for skill creation applies the RED-GREEN-REFACTOR cycle to documentation, writing failing tests first, then building the skill, and refactoring to ensure compliance and robustness.

What is the best way to prevent AI agents from rationalizing and bypassing rules?▼

To prevent rationalization and bypassing rules, implement pressure testing with countermeasures that explicitly address common excuses agents use under simulated real-world pressures like time or sunk cost.

How do I pressure test AI skills before deployment to ensure consistent agent behavior?▼

Pressure test AI skills before deployment by verifying their operational integrity through structured testing cycles that simulate real-world pressures, ensuring consistent agent behavior and rule compliance.

Can I apply TDD methodology to edit and refine existing AI skills?▼

Yes, you can apply TDD methodology to edit existing AI skills by running structured testing and refactoring cycles that verify operational integrity and enforce adherence to specific documentation protocols.

What documentation protocols are needed when authoring AI skills with TDD?▼

Authoring AI skills with TDD requires strict adherence to specific documentation and testing protocols designed to prevent rationalization and ensure discoverable, effective, and misuse-resistant agent behavior.

Related Skills

Explore More Software Engineering Skills→
kk20300113-pngkk20300113-png

writing-skills

Apply test-driven development cycles to author and validate agent skills.

Community
Advanced
VeraticusVeraticus

writing-skills

Create and modify gambit skills through evaluation-driven RED, GREEN, and REFACTOR testing phases.

Community
Advanced
outfitter-devoutfitter-dev
28

Scenario Testing

Run end-to-end scenario tests against real dependencies without mocks.

Official
Advanced
arthurgailesarthurgailes
19

writing-r-skills

Guide R skill creation through Test-Driven Development cycles.

Community
Advanced