Is it suitable for internal research documentation?

Yes, it is ideal for teams wanting to maintain high technical standards for internal R&D before publication or actual deployment.

How does it handle reproducibility concerns?

It identifies missing details in methodology, data splits, and hyperparameter tuning protocols that could prevent other researchers from reproducing your results.

Does this skill follow specific academic standards?

Yes, it adheres to the rigorous peer review guidelines and rating rubrics used by top-tier conferences like NeurIPS, ICML, and ICLR.

Does the reviewer provide a final score?

Yes, the skill provides a standardized rating ranging from Strong Reject to Strong Accept, along with a confidence level for the assessment.

Can it help identify issues with my machine learning experiments?

Absolutely. It specifically audits for experimental rigor, including baseline selection, metric choice, ablation studies, and potential data leakage.

ML Paper Peer Reviewer

Name: ML Paper Peer Reviewer
Author: ihmorol

byihmorol

•

Data Science & ML

Conducts rigorous, elite-level peer reviews of machine learning manuscripts following NeurIPS, ICML, and ICLR standards.

This skill transforms Claude into Dr. Ayaan Rahman, a high-level ML researcher, to provide structured, critical feedback on research papers. It systematically audits technical correctness, experimental rigor, and reproducibility while identifying common red flags like benchmark leakage or unfair comparisons. It is an essential tool for researchers preparing submissions, students learning the review process, or teams evaluating the validity of new internal or external ML methodologies before implementation.

Key Features

01Standardized review rubrics based on top-tier ML conferences like NeurIPS, ICML, and ICLR.

02Detection of common ML red flags including benchmark leakage and unfair baselines.

03Actionable feedback with prioritized suggested experiments and substantive author questions.

04Ethical impact assessment and reproducibility verification checklists.

051 GitHub stars

06Comprehensive technical auditing for correctness, novelty, and experimental integrity.

Use Cases

01Critiquing and validating new ML techniques or papers discovered on arXiv.

02Internal pre-submission review for researchers targeting major machine learning conferences.

03Standardizing the evaluation process for internal company R&D reports and technical whitepapers.

Key Features

01Standardized review rubrics based on top-tier ML conferences like NeurIPS, ICML, and ICLR.

02Detection of common ML red flags including benchmark leakage and unfair baselines.

03Actionable feedback with prioritized suggested experiments and substantive author questions.

04Ethical impact assessment and reproducibility verification checklists.

051 GitHub stars

06Comprehensive technical auditing for correctness, novelty, and experimental integrity.

Use Cases

01Critiquing and validating new ML techniques or papers discovered on arXiv.

02Internal pre-submission review for researchers targeting major machine learning conferences.

03Standardizing the evaluation process for internal company R&D reports and technical whitepapers.