testing-skills-with-subagents

Run baseline failure scenarios to validate skill behavior with RED-GREEN-REFACTOR workflows.

205|26|Updated Oct 30, 2025

Search Tags:#testing #documentation #TDD #AI agents #skills #compliance #rationalization

Ready to run

npx skills add https://github.com/LerianStudio/ring --skill testing-skills-with-subagents-lerianstudio

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: testing-skills-with-subagents
Source: https://github.com/LerianStudio/ring/tree/main/skills/testing-skills-with-subagents
Command: npx skills add https://github.com/LerianStudio/ring --skill testing-skills-with-subagents-lerianstudio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Skills, especially those enforcing discipline, can be rationalized away by AI agents under pressure. This skill applies Test-Driven Development (TDD) to process documentation to ensure skills are robust and followed.

Core Features & Use Cases

TDD for Documentation: Maps the RED-GREEN-REFACTOR cycle to skill creation, starting with baseline tests (agents failing without the skill).
Pressure Scenarios: Guides the creation of realistic scenarios combining time, sunk cost, authority, and other pressures to test agent compliance.
Rationalization Capture: Mandates documenting exact agent rationalizations verbatim to identify and plug loopholes in the skill.

Quick Start

I'm creating a new skill. Use the testing-skills-with-subagents skill to ensure it's robust and followed.

Frequently Asked Questions about testing-skills-with-subagents

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

FAQPage Schema

How do I test AI agent skills to prevent them from being rationalized away under pressure?▼

Test-driven development for documentation ensures skills are robust by running baseline scenarios without the skill to observe failures, then validating the skill prevents those failures. Document agent rationalizations verbatim to identify and plug compliance loopholes before deployment.

What's the best way to validate that an AI agent will actually follow a skill in high-pressure scenarios?▼

Create pressure scenarios combining time, sunk cost, and authority constraints, then run RED-GREEN-REFACTOR cycles: document exact failures without the skill, verify the skill fixes them, and iteratively tighten rules to ensure compliance across multiple pressures.

How do I document agent rationalization to improve skill compliance?▼

Capture agent rationalizations verbatim during pressure testing to expose where skills fail or get circumvented. Use these exact rationalization tables to identify gaps and strengthen skill rules before production deployment.

Can I use TDD principles to ensure my AI agent skills are followed reliably?▼

Yes. TDD for documentation maps RED-GREEN-REFACTOR to skill creation: start with baseline tests showing agents fail without the skill, validate the skill prevents failures, then refactor rules to close loopholes and ensure compliance.

What's the difference between testing skills with pressure scenarios versus standard validation?▼

Pressure-based evaluation tests agent compliance under realistic constraints—time pressure, sunk cost, and authority—rather than isolated conditions. This reveals rationalization patterns and ensures skills hold when agents face competing priorities.

Do I need to document exact agent failures before creating a skill?▼

Yes. Baseline failure documentation is the first step in the RED-GREEN-REFACTOR cycle. Observe and record how agents fail without the skill, then design the skill to prevent those specific failures and achieve compliance.