No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by u7079256 · Claude Skill · ★ 516
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is paperjury safe to install? View the security audit →
English · 中文 PaperJury A pre-submission AI review stress-test for research papers. Before a reviewer tears it apart, let a jury do it first. PaperJury turns paper feedback into a closed loop: review → verdict → revise → verify. Instead of taking every AI suggestion at face value, it sorts each issue into one of three outcomes: Fixable: safe, text-level issues that can be patched automatically. Author-required: missing experiments, missing evidence, or research decisions that stay with you. Invalid: reviewer misreadings or unsupported critiques that should not be applied. It offers three modes: direct-edit, review, and auto. PaperJury is built for pre-submission self-checking. It does not replace peer review, it does not invent missing experiments, and it keeps res
| Stars | 516 |
| Forks | 36 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 67.9354890112286/100 |
| Last Updated | 2026-06-30 |
| Created | 2026-06-02 |
| Platforms | claude-code, node |
| Est. Tokens | ~18k |
These tools work well together with paperjury for enhanced workflows:
Looking for a paperjury alternative? If you're comparing paperjury with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify
Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济
Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrica
Agent Skill that transforms AI assistants into expert economics paper writers. Synthesizes 50+ guides by Cochr
A collection of AI agent skills for Clawdbot, Claude Code, Codex
An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all r
Explore other popular claude skill tools:
paperjury is Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.. It is categorized as a Claude Skill with 516 GitHub stars.
paperjury is primarily written in JavaScript. It covers topics such as academic-writing, ai-agents, claude-code.
You can find installation instructions and usage details in the paperjury GitHub repository at github.com/u7079256/paperjury. The project has 516 stars and 36 forks, indicating an active community.
paperjury is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to paperjury on Agent Skills Hub include paperjury, Awesome-Journal-Skills, Anti-Autoresearch. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: