cs-paper-review

Draft evidence-based CS/ML paper reviews from PDFs and venue forms.

13|1|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/yzhao062/agent-config --skill cs-paper-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cs-paper-review
Source: https://github.com/yzhao062/agent-config/tree/main/reference-skills/cs-paper-review
Command: npx skills add https://github.com/yzhao062/agent-config --skill cs-paper-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Draft grounded CS/ML reviews for research papers using the provided PDF, extracted text, venue form, and user notes, ensuring evidence-based evaluation.

Core Features & Use Cases

  • Draft a technically grounded review using only the paper and other user-supplied materials.
  • Validate claims against extracted content, surface ethical and integrity considerations, and generate author-facing questions.
  • Adapt the review for venues such as IJCAI, NeurIPS, ICML, and similar, with structure suitable for the venue form.

Quick Start

Draft a grounded CS/ML paper review using the provided PDF, extracted text, venue form, and user notes.

Frequently Asked Questions about cs-paper-review

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

FAQPage Schema
How do I draft a grounded CS/ML paper review using only the provided PDF?

To draft a grounded CS/ML paper review, the Skill extracts text from the provided PDF and user notes, verifying all technical claims strictly against these source materials to produce an evidence-based evaluation.

Can I generate a peer review tailored for specific ML venues like NeurIPS or ICML?

Yes, you can generate a peer review tailored for ML venues like NeurIPS, ICML, or IJCAI. The Skill adapts its structured evaluation, author questions, and ethics considerations to fit the specific venue form fields you provide.

What is evidence-based peer review and how does it handle prompt-injection or integrity concerns?

Evidence-based peer review validates paper claims against extracted source content. The Skill applies rigorous evidence gathering to flag prompt-injection attempts or integrity concerns, ensuring a clear, defendable evaluation of the CS/ML research.

How do I generate author-facing questions for a computer science paper evaluation?

You generate author-facing questions by supplying the paper PDF, extracted text, and user notes. The Skill drafts a technically grounded evaluation that surfaces relevant, targeted questions for the authors based on the verified content.

Do I need to provide extracted text and venue form fields to review a machine learning paper?

You need to provide the paper PDF at minimum. Supplying extracted text, venue form fields, and user notes allows the Skill to draft a more accurate, venue-specific review with rigorous evidence gathering and validated claims.