adversarial-review

Spawn opposing-model reviewers to critique code changes and plans.

Updated May 28, 2026

Search Tags:#code review #maintainability #codex #claude #synthesis #adversarial review #branch review

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you catch real flaws in code or plan changes by challenging the work with independent reviewers that think from different critical angles.

Core Features & Use Cases

Opposing-model review orchestration: Spawns 1–3 reviewers on the opposite model to avoid self-confirmation bias.
Multi-lens critique: Examines work through skeptic, architect, and minimalist perspectives to surface correctness, design, and complexity issues.
Synthesis without implementation: Produces a single verdict and remediation-focused findings without making changes.
Use Cases: Best for large diffs, implementation phases, and planning outputs that need a rigorous adversarial pass before shipping.

Quick Start

Use the adversarial-review skill to assess the latest branch changes and return a concise verdict with the most important risks.

Frequently Asked Questions about adversarial-review

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

FAQPage Schema

How do I run an adversarial code review on a large branch diff?▼

Adversarial code review catches hidden flaws by challenging work with independent reviewers that think from different critical angles. It applies multi-lens critique through skeptic, architect, and minimalist perspectives to surface correctness, design, and complexity issues before shipping.

How do I use codex exec and claude -p to review code changes?▼

To review code changes, you spawn independent reviewers through codex exec or claude -p and synthesize their findings. This opposing-model orchestration prevents self-confirmation bias and produces a remediation-focused verdict without modifying your files.

What's the best way to stress-test implementation plans for hidden flaws?▼

Stress-testing implementation plans for hidden flaws is best done by running independent adversarial reviewers through skeptic, architect, and minimalist perspectives. This multi-lens critique surfaces correctness, design, and complexity issues before shipping.

Does adversarial review modify my code during the synthesis process?▼

No, adversarial review does not modify your code during the synthesis process. It strictly produces a single verdict and remediation-focused findings from the reviewers without making any changes to your working files.

When should I use an opposing-model review for my code?▼

You should use an opposing-model review when you have large diffs, implementation phases, or planning outputs that need rigorous critical scrutiny. It catches real flaws by challenging the work with independent reviewers on the opposite model.