Summary
This is a multi-stage academic paper reviewer that runs OpenJudge's pipeline on PDFs or LaTeX sources. It checks for mathematical errors, scores papers 1-6 on quality and novelty, verifies BibTeX entries against CrossRef and arXiv, and outputs a structured markdown report. Covers 10 disciplines from computer science to social sciences. The pipeline uses vision-capable models by default (renders pages as images), so you need something like GPT-4o or Claude Opus, not a text-only model. Works in English or Chinese. The approach is thorough but opinionated: it's designed for formal peer review workflows, not quick skims. If you're evaluating submissions or need reference verification with actual database lookups, this handles the tedious parts.
Install to Claude Code
npx -y skills add agentscope-ai/openjudge --skill paper-review --agent claude-codeInstalls into .claude/skills of the current project.
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Files
SKILL.md
Select a file.
Featured
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →
