review-adversarial

Run six adversarial personas across file globs to identify argumentative, evidentiary, and framing vulnerabilities.

Updated Jan 20, 2026

Search Tags:#audit #manuscript #peer-review #adversarial-review #vulnerability-assessment #persona-testing

Ready to run

npx skills add https://github.com/yannickloth/health-me-cfs --skill review-adversarial

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill exposes argumentative, evidentiary, and framing weaknesses in manuscripts by running multiple hostile-but-fair reviewer personas so authors can prioritize fixes before submission or publication.

Core Features & Use Cases

Sequentially runs six adversarial personas that target rhetorical bias, logical fallacies, strawmaning, overcomplication, clinical relevance, and weakest-link claims.
Resolves file globs, enforces guards for empty scopes, collects per-persona findings, and produces an aggregated convergence report highlighting cross-persona vulnerabilities and resilient claims.
Use cases include pre-submission manuscript red-teaming, internal quality assurance for research chapters, and automated stress-testing of clinical recommendations.

Quick Start

Ask the skill to run an adversarial review on the manuscript glob typst/**/*.typ and produce a consolidated vulnerabilities report in your runtime directory.

Frequently Asked Questions about review-adversarial

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

FAQPage Schema

How do I run an adversarial review on a manuscript before submission?▼

Adversarial peer-review systematically stress-tests document claims by applying multiple hostile-but-fair reviewer personas. This approach targets argumentative flaws, logical fallacies, and evidentiary gaps to identify manuscript vulnerabilities before publication.

Can I audit a repository file glob for argumentative vulnerabilities?▼

Yes, you can audit repository file globs. The process resolves scope, enforces guards for empty scopes, and sequentially runs persona audits to stress-test claims, logic, and clinical relevance across matched files, aggregating per-persona findings.

What does the adversarial vulnerability assessment report include?▼

The vulnerability assessment report aggregates per-persona findings and detects cross-persona convergence. It highlights cross-persona vulnerabilities and resilient claims, outputting the consolidated markdown report to your XDG_RUNTIME_DIR.

Does the adversarial review tool support clinical relevance testing?▼

Yes, clinical relevance testing is a core feature. One of the six ordered adversarial personas specifically targets clinical recommendations to ensure research chapters withstand rigorous stress-testing and maintain medical relevance.