RedTeam

Coordinate 32 agents to critique arguments and synthesize convergent insights.

4|1|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/pynbj1001/alpha-sense --skill redteam-pynbj1001
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: RedTeam
Source: https://github.com/pynbj1001/alpha-sense/tree/main/.pai_runtime/.claude/skills/RedTeam
Command: npx skills add https://github.com/pynbj1001/alpha-sense --skill redteam-pynbj1001

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Delivers structured adversarial critique by coordinating 32 expert-like agents to stress-test arguments, surface hidden assumptions, and provide rigorous counterpoints.

Core Features & Use Cases

  • 32-agent parallel analysis for comprehensive critique
  • Steelman and counter-argument generation with FirstPrinciples integration
  • Phase-based synthesis and convergent insights for decision support
  • Suitable for evaluating architectures, policies, and strategic bets

Quick Start

Invite the RedTeam skill to run a ParallelAnalysis cycle on your argument to expose weaknesses and generate steelman and counter-arguments

Frequently Asked Questions about RedTeam

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

FAQPage Schema
How do I run an adversarial analysis to stress-test a strategic argument?

Adversarial analysis stress-tests arguments by deploying 32 parallel agents to critique your position, surface hidden assumptions, and generate rigorous counterpoints. It synthesizes multi-perspective insights to highlight convergent strengths, weaknesses, and a clear recommendation for decision-makers.

What is a steelman counter-argument and how does it improve policy evaluation?

A steelman counter-argument is the strongest possible version of an opposing viewpoint. This Skill generates steelman arguments alongside robust critiques using 32 expert-like agents, exposing blind spots and providing phase-based convergent insights for evaluating policies or strategic bets.

Can I use parallel analysis for evaluating software architectures and strategic bets?

Yes, parallel analysis suits evaluating architectures, policies, and strategic bets. By coordinating 32 agents to perform structured adversarial critique, it surfaces hidden assumptions and provides rigorous counterpoints tailored to decision support for complex technical and strategic proposals.

What is the best way to surface hidden assumptions in a proposed strategy?

The best way to surface hidden assumptions is through structured adversarial critique. This approach uses 32 agents in a parallel analysis cycle to stress-test your argument, generating both a steelman version and strong counter-arguments to reveal underlying weaknesses.

When should I not use a 32-agent red team critique for argument analysis?

You should avoid a 32-agent red team critique for simple, straightforward arguments that do not require comprehensive multi-perspective synthesis. This approach is designed for complex evaluations where deep stress-testing, hidden assumption surfacing, and convergent insight generation are strictly necessary.