adversarial-review

Name: adversarial-review
Availability: InStock
Author: robertphyatt

Automate five-phase adversarial code reviews with mandatory verification and findings reports.

7|1|Updated Mar 26, 2026

Search Tags:#workflow #documentation #security #verification #code-review #adversarial #findings

Ready to run

npx skills add https://github.com/robertphyatt/ironclaude --skill adversarial-review-robertphyatt

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: adversarial-review
Source: https://github.com/robertphyatt/ironclaude/tree/main/worker/skills/adversarial-review
Command: npx skills add https://github.com/robertphyatt/ironclaude --skill adversarial-review-robertphyatt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Adversarial code reviews guided by a mandatory verification process produce objective, evidence-backed findings.

Core Features & Use Cases

Guided five-phase review workflow: Orientation, Deep Read, Verification, Cross-cutting Analysis, and Report.
Produces a structured findings document with severity-classified results for audit and quality assurance.
Ideal for security audits, subsystem reviews, and pre-release code quality checks.

Quick Start

Provide --files and --scope to start a five-phase adversarial review and generate a findings document.

Frequently Asked Questions about adversarial-review

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

FAQPage Schema

How do I automate an adversarial code review for a security audit?▼

You can automate an adversarial code review by providing target files and scope to trigger a structured five-phase workflow. This process enforces input validation and mandatory verification, ultimately generating a findings document with severity-classified, evidence-backed conclusions for security audits.

What is an adversarial code review workflow with mandatory verification?▼

An adversarial code review workflow with mandatory verification is a structured process that enforces evidence-backed findings through five phases: Orientation, Deep Read, Verification, Cross-cutting Analysis, and Report. It ensures objective, disciplined code quality checks and security audits.

Can I use this for pre-release code quality checks and subsystem architecture reviews?▼

Yes, you can use this for pre-release code quality checks and subsystem architecture reviews. The guided workflow applies across code domains, producing a structured findings document with severity-classified results that are ideal for audit and quality assurance tasks.

What's the best way to generate structured findings from a code review?▼

The best way to generate structured findings from a code review is to use a discipline-driven, five-phase adversarial workflow. It validates inputs, enforces verification, and outputs a report with severity-classified, evidence-backed conclusions for objective quality assurance.

Do I need any external dependencies to run a structured adversarial code review?▼

No external dependencies are required to run a structured adversarial code review. You only need to provide the target files and review scope to initiate the five-phase workflow, which handles input validation and findings generation internally.

Limitations of using a structured five-phase workflow for code reviews?▼

A limitation of using a structured five-phase workflow for code reviews is its rigid discipline-driven sequence. While it ensures mandatory verification and evidence-backed findings, it may be less flexible for rapid, informal checks that do not require a full cross-cutting analysis or formal report generation.