npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

research-paper-review

v1.0.0

Published

Review and analyze academic research papers — consistency checks, structured critique, venue-specific feedback, pre-submission review

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Maintainers

armenslarmensl

Keywords

skillresearchpaper-reviewacademicpeer-reviewliterature-reviewpre-submissionnumerical-consistency

Readme

research-paper-review

An AI agent skill for systematic academic paper review.

What It Does

When you share a research paper (PDF, LaTeX, or plain text), this skill guides the agent through a structured review process:

  1. Venue context — Adapts the review to the target conference/journal standards
  2. Structured summary — Problem, contributions, methodology, results, limitations
  3. Numerical & consistency checks — Cross-references numbers across text, tables, and figures; verifies statistics, acronyms, terminology, and citations
  4. Critical analysis — Evaluates novelty, soundness, significance, clarity, reproducibility, and venue alignment
  5. Actionable feedback — Strengths, weaknesses, questions, minor issues, and venue-specific recommendations
  6. Top 10 actions — Prioritized by impact-to-effort ratio so authors know where to start

Installation

Option A: Agent skills CLI (Claude Code, Cursor, Copilot, Windsurf, etc.)

npx skills add BESSER-PEARL/agent-skills@research-paper-review

This auto-installs the skill into your local agent. It activates automatically when you share a paper.

Option B: ChatGPT, Claude, Gemini, or any other AI chat

No installation needed. Just:

  1. Copy the contents of SKILL.md
  2. Paste it as:
    • ChatGPT → Custom Instructions or start of conversation
    • Claude.ai → Project Knowledge or start of conversation
    • Gemini → Gems or start of conversation
  3. Upload your paper (PDF) and ask for a review

Tip: For best results, paste the SKILL.md content first, then upload the paper and write: "Review this paper for [VENUE] as a [TYPE] submission."

Usage

Share a paper with the agent and optionally specify the venue and paper type:

Review this paper for ICWE 2026 as a tool demo submission.
Check this PDF for numerical inconsistencies and broken references.
Give me pre-submission feedback on our TOSEM journal paper.

The agent will fetch venue-specific guidelines when available and produce a review following the output template in SKILL.md.

Supported Formats

  • PDF files (read page by page)
  • LaTeX source (.tex files, follows \input / \include commands)
  • Plain text / markdown

Authors

Part of the BESSER-PEARL project at the Luxembourg Institute of Science and Technology.