paper-reviewing

paper-reviewing is a skill for Claude Code from JeanDiable/academic-research-plugin. It costs 116 tokens per session (3,099 once invoked), scanned A, original, MIT.

A conference-style review workflow for evaluating an academic paper from its PDF. It examines originality, technical correctness, clarity, importance, reproducibility, and experimental design, using formats for conferences such as NeurIPS, ICML, CVPR, ACL, AAAI, ICCV, and ICLR.

In plain words
What is it for?
Use it to review a research paper before conference submission or publication, with the review calibrated to a selected conference and level of strictness.
Why use it?
It gives a paper a structured assessment instead of an informal reading summary. It helps identify major and minor problems, strengths, questions, and an overall recommendation score.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the academic-research plugin — 10 skills shipped together

Good fit Use it to review a research paper before conference submission or publication, with the review calibrated to a selected conference and level of strictness.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeandiable/academic-research-plugin/paper-reviewing
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add JeanDiable/academic-research-plugin --skill paper-reviewing
Clone the repo
git clone --depth 1 https://github.com/JeanDiable/academic-research-plugin

Made for: Claude Code.

Or install academic-research, the plugin that ships this one along with the rest of its 10 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for paper-reviewing

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/paper-reviewing/github.svg)](https://agentmods.dev/skills/jeandiable/academic-research-plugin/paper-reviewing)
Your own site
<a href="https://agentmods.dev/skills/jeandiable/academic-research-plugin/paper-reviewing"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/paper-reviewing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for paper-reviewing

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeandiable/academic-research-plugin/paper-reviewing"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/paper-reviewing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,099 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.03099
Opus 5 $0.00058 $0.01550
Sonnet 5 $0.00023 $0.00620
Haiku 4.5 $0.00012 $0.00310

Measured 11d ago against content hash 31280a4bd1c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

paper-reviewing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/bibtex_utils.py, scripts/paper_search.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/paper-reviewing/SKILL.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Conduct a comprehensive conference-style peer review of an academic paper. This skill analyzes papers across six key dimensions:

  1. Novelty: How original and innovative is the work?
  2. Technical Soundness: Are the methods correct and well-justified?
  3. Clarity: Is the paper well-written and organized?
  4. Significance: How impactful is this work?
  5. Reproducibility: Can others reproduce the results?
  6. Experimental Design: Are experiments properly designed and comprehensive?

The review follows the format and checklist of a specified conference (NeurIPS, ICML, CVPR, ACL, AAAI, ICCV, ICLR) or a generic academic format. Severity can be adjusted (lenient, standard, strict) to calibrate tone and scoring standards.

Arguments

<pdf-path> (required)

Path to the paper PDF file to review. Can be absolute or relative path.

--conference (optional)

Target conference to match review format. Options:

  • NeurIPS - Neural Information Processing Systems
  • ICML - International Conference on Machine Learning
  • CVPR - IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • ACL - Association for Computational Linguistics
  • AAAI - Association for the Advancement of Artificial Intelligence
  • ICCV - IEEE/CVF International Conference on Computer Vision
  • ICLR - International Conference on Learning Representations
  • If omitted, uses generic academic format

--severity (optional, default: standard)

Tone and scoring calibration:

  • lenient - Focus on strengths, constructive framing, generous scoring
  • standard - Balanced assessment, typical conference reviewer tone
  • strict - Rigorous evaluation, all issues flagged, conservative scoring

Setup

Install dependencies:

python -m pip install -r "BASE_DIR/scripts/requirements.txt"

Required packages:

  • PyPDF2 or pdfplumber - PDF parsing and text extraction
  • requests - HTTP requests for arXiv and paper searches
  • python-dateutil - Date handling

Read the full file on GitHub · 340 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 340 lines · 116 tokens per session scan A 31280a4bd1c5

Subscribe to this mod's changes

paper-reviewing is a skill published in the GitHub repository JeanDiable/academic-research-plugin (22 stars, last pushed 5mo ago), licensed MIT. It adds 116 tokens to every session and 3,099 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories