Verified:GitHub

god-research-review

Critique research papers for flaws in claims, methodology, statistics, and reproducibility.

1|Updated Apr 23, 2026

Search Tags:#reproducibility #peer-review #adversarial-review #paper-review #statistical-rigor #literature-survey #methodology-analysis

Ready to run

npx skills add https://github.com/gnanirahulnutakki/god-skill-suite --skill god-research-review

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: god-research-review
Source: https://github.com/gnanirahulnutakki/god-skill-suite/tree/main/skills/god-research-review
Command: npx skills add https://github.com/gnanirahulnutakki/god-skill-suite --skill god-research-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skill equips researchers and reviewers with a battle-hardened framework to perform rigorous, adversarial critiques of technical papers, uncovering flaws in claims, methodology, statistics, and reproducibility.

Core Features & Use Cases

Adversarial abstract and introduction analysis to surface unclear motivations and claimed contributions.
In-depth methodology and experiments evaluation, including baselines, ablations, and statistical rigor checks.
Systematic literature review guidance with best-practice search strategies and fair evaluation criteria for reproducibility.

Quick Start

Provide an adversarial, structured critique of a research manuscript focusing on abstracts, methodologies, experiments, and reproducibility.

Frequently Asked Questions about god-research-review

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

FAQPage Schema

How do I perform an adversarial peer review of a machine learning paper?▼

Adversarial peer review rigorously evaluates machine learning papers by applying evidence-based critique to identify methodology flaws, assess statistical accuracy, and verify reproducibility. It systematically examines abstracts, claimed contributions, experimental baselines, and ablations to uncover weaknesses.

What is statistical rigor in academic paper review and how is it evaluated?▼

Statistical rigor in paper review evaluates the accuracy of claimed results, experimental setups, and baseline comparisons. It verifies whether hypotheses are clearly defined and whether statistical evidence supports stated contributions without overclaiming.

How do I check if a research paper has enough reproducibility details?▼

Checking reproducibility details involves verifying whether a paper provides sufficient information to replicate experiments, including datasets, baselines, and methodology. A rigorous review assesses whether these elements allow independent validation of claimed results.

Does this adversarial review approach work for NeurIPS and ICML style papers?▼

Yes, the adversarial review framework is applicable to NeurIPS and ICML style papers. It evaluates technical manuscripts by applying strict criteria for clear hypotheses, fair baseline comparisons, and reproducibility to match conference standards.

What is the best way to evaluate research methodology and literature surveys?▼

The best way to evaluate methodology and literature surveys is using a structured critique framework that assesses search strategies, baseline fairness, and experimental design. This ensures claims are evidence-based and methodology flaws are systematically uncovered.