red-team

Generate steelman and counter-argument analyses to expose flaws in user ideas.

7|2|Updated Nov 30, 2025

Search Tags:#parallel agents #red team #first principles #steelman #counter-argument #adversarial analysis #argument validation

Ready to run

npx skills add https://github.com/ajbmachon/ajbm-skills --skill red-team-ajbmachon

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: red-team
Source: https://github.com/ajbmachon/ajbm-skills/tree/main/plugins/development-skills/skills/thinking/red-team
Command: npx skills add https://github.com/ajbmachon/ajbm-skills --skill red-team-ajbmachon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The red-team skill prevents you from trusting arguments that only look convincing by exposing hidden assumptions and weak logic.

Core Features & Use Cases

Parallel adversarial analysis: Deploy multiple expert perspectives (engineers, architects, pentesters, interns) to attack strengths and weaknesses.
Steelman + counter-argument output: Produces the strongest fair version of your idea plus the strongest rebuttal.
Protocol-driven decomposition: Breaks arguments into atomic claims, synthesizes convergence, and targets the core failure point.
First-principles integration: Uses first-principles Deconstruct and Challenge to classify constraints and prioritize the most damaging assumptions.
Use cases: Architecture decisions, business plans, feature specs, code/design critiques, and any important content that must withstand scrutiny.

Quick Start

Ask the skill to red team your proposal and return a steelman plus an 8-point counter-argument.

Frequently Asked Questions about red-team

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

FAQPage Schema

How does adversarial analysis expose fatal flaws in an argument?▼

A steelman counter-argument builds the strongest fair version of your idea, then challenges it using first-principles deconstruction to classify constraints. This protocol-driven approach identifies the most damaging assumptions that could cause your proposal to fail.

When do I need stress-testing for architecture decisions or feature specs?▼

Stress-testing architecture decisions or feature specs is needed when content must withstand scrutiny before commitment. Apply adversarial analysis to validate designs, expose weak logic, and generate robust critiques that prevent trusting arguments that only look convincing.

Can I use parallel expert perspectives to validate a business plan?▼

Yes, you can validate a business plan by deploying multiple parallel expert perspectives such as engineers, architects, and pentesters. This protocol synthesizes their convergence to target the core failure point and produces a steelman plus an 8-point counter-argument.

What is the best way to generate a counter-argument using first principles?▼

The best way to generate a first-principles counter-argument is to decompose the proposal into atomic claims, classify constraints, and prioritize the most damaging assumptions. This produces a structured rebuttal that targets the core failure point of the idea.

What are the limitations of relying on parallel agents for argument validation?▼

Parallel agents for argument validation are limited by the quality of the initial decomposition into atomic claims. If the structured breakdown misses hidden assumptions, the synthesized convergence and first-principles challenge may not expose the true core failure point.