skills.rest
robkisk
robkiskCOMMUNITY
Explore all skills by this author →
GitHub

writing-skills

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

Updated Mar 10, 2026
Search Tags:#tdd#documentation#refactoring#skill creation#rationalization#agent testing
One-click install
npx skills add https://github.com/robkisk/coding-agents-databricks-app --skill writing-skills-robkisk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/robkisk/coding-agents-databricks-app/tree/main/.claude/skills/writing-skills
Command: npx skills add https://github.com/robkisk/coding-agents-databricks-app --skill writing-skills-robkisk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

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

Core Features & Use Cases

  • TDD for Documentation: Adapts the RED-GREEN-REFACTOR cycle to skill authoring.
  • Pressure Testing: Develops skills that remain compliant under realistic agent pressures (time, sunk cost, authority).
  • Rationalization Countermeasures: Identifies and explicitly blocks common agent excuses for bypassing rules.
  • Use Case: When developing a new skill to enforce code review before deployment, use this skill's methodology to write test scenarios that simulate an agent wanting to skip the review due to time pressure, then refine the skill until it consistently enforces the rule.

Quick Start

Follow the RED-GREEN-REFACTOR cycle to create a new skill, starting with writing failing test scenarios.

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 methodology to create AI agent documentation skills?▼

Test-driven development for documentation adapts the RED-GREEN-REFACTOR cycle to skill authoring by writing failing test scenarios first, then refining the skill until it passes. This ensures AI agent documentation remains robust.

Why do AI agents bypass rules under pressure and how can I prevent it?▼

Agents bypass rules through rationalization when facing time constraints, sunk costs, or authority pressure. You prevent rationalization by identifying common agent excuses and explicitly blocking them during skill creation.

What is the best way to test AI agent compliance with documentation rules?▼

The best way to test agent compliance is using subagent testing to simulate realistic pressures. You write test scenarios where an agent wants to skip a rule, then refine the skill until it enforces compliance consistently.

Can I apply refactoring techniques to improve existing skill documentation?▼

Yes, you apply the refactoring phase of the TDD cycle to improve existing documentation skills. This involves restructuring the skill to enhance discoverability and effectiveness while maintaining passing test scenarios.

Does skill creation with TDD require specific testing frameworks?▼

Skill creation with TDD uses subagent testing cycles rather than specific external testing frameworks. The methodology focuses on writing scenarios that simulate agent behavior to verify compliance without external dependencies.

Related Skills

Explore More Software Engineering Skills→
pv-udpvpv-udpv
4

Testing Skills With Subagents

Run RED-GREEN-REFACTOR tests to harden skill documentation and close loopholes.

Community
Advanced
KanuToCLKanuToCL

testing-skills-with-subagents

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

Community
Advanced
seanGSISGseanGSISG
3

testing-skills-with-subagents

Test skills with subagents to verify resistance to rationalization under pressure.

Community
Basic
GamezarGamezar

customaize-agent-test-skill

Test custom AI skills using TDD cycles against bypass attempts.

Community
Advanced