adversarial-hat

Community

Expose and fix weaknesses before commitment

Authordvy1987
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It identifies unsupported claims, hidden assumptions, and fragile solutions in documents and plans so teams avoid committing to flawed strategies or designs.

Core Features & Use Cases

  • Three-phase red team process: Diagnostic (verify claims), Creative (broaden problem framing), and Challenge (stress-test solutions and failure modes).
  • Actionable findings: Each issue is reported with the challenged claim, specific evidence or reasoning, a severity label (Critical/Significant/Minor), and explicit resolution conditions.
  • Use cases: PRD reviews, product-soul validation, design doc critique, implementation plan risk assessment, and pre-launch sanity checks.

Quick Start

Run an adversarial review on the attached PRD and return critical, significant, and minor findings with evidence and concrete resolution conditions.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: adversarial-hat
Download link: https://github.com/dvy1987/agent-loom/archive/main.zip#adversarial-hat

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.