testing-skills-with-subagents

Apply RED-GREEN-REFACTOR testing to subagent-based skills with pressure scenarios.

4|1|Updated Oct 29, 2025

Search Tags:#automation #TDD #AI development #compliance #meta-skill #rationalization #skill testing

Ready to run

npx skills add https://github.com/samjhecht/wrangler --skill testing-skills-with-subagents-samjhecht

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Untested AI skills can fail under pressure, be rationalized away by agents, or contain loopholes, leading to unreliable automation and inconsistent agent behavior.

Core Features & Use Cases

TDD for Documentation: Applies the RED-GREEN-REFACTOR cycle to process documentation, ensuring skills are tested against real agent behavior.
Pressure Scenarios: Creates realistic test scenarios combining pressures like time, sunk cost, authority, and exhaustion to expose skill weaknesses.
Rationalization Loopholes: Identifies and explicitly plugs agent rationalizations, making skills bulletproof against attempts to bypass rules.
Use Case: When creating or editing any AI skill, this skill ensures it works reliably, resists agent rationalization, and enforces desired behaviors even under maximum stress, guaranteeing consistent automation.

Quick Start

I've written a new skill for 'test-driven-development'. Guide me through testing it with subagents to ensure it's bulletproof.

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 skills to ensure agents don't rationalize away compliance rules?▼

Testing AI skills with subagents applies test-driven development to expose rationalization loopholes. The RED-GREEN-REFACTOR cycle validates skills against real agent behavior, ensuring rules persist even under pressure like time constraints or authority conflicts, making automation reliable and consistent.

What's the best way to pressure-test documentation for AI agent skills?▼

Pressure testing combines realistic scenarios—time limits, sunk costs, authority figures, exhaustion—to reveal skill weaknesses. This method identifies where agents bypass rules, then explicitly plugs those loopholes so skills remain bulletproof under maximum stress.

How do I apply test-driven development to AI skill documentation?▼

TDD for documentation uses RED-GREEN-REFACTOR to test skill descriptions against actual agent behavior. Write test scenarios first, verify the skill fails without the documented behavior, then refine the skill until it passes—ensuring documentation matches reality.

Can I verify my AI subagent skills work reliably before deployment?▼

Yes. Scenario design and verification workflows test subagent-based skills for compliance, audit trails, and consistent behavior. Testing methodology coverage ensures skills resist agent rationalization and perform reliably across automation workflows.

What testing methodology should I use for skills with subagents?▼

Use scenario design, pressure testing, and RED-GREEN-REFACTOR verification to test subagent skills. Mandatory usage announcements and audit trails enforce compliance. Integration with writing skills consolidates skill development and ensures agent behavior aligns with skill intent.