#716 · Primary category: AI Agents & Automation
paperjury
Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.
Project last updated:08/14/26
GitHub Stars
1.0K
Forks
43
Contributors
1
License
MIT
Why we included this project
PaperJury is a Claude Code skill that runs a structured review over a LaTeX manuscript before you submit it, so the weak spots surface while you can still fix them. A panel of domain reviewers reads the whole paper, a contestability router sends genuine disputes to a two-sided trial, and a jury returns one of three verdicts: a fixable text problem, an issue that needs the author's own judgment, or a complaint that should be dropped. The model does the reading and drafting, while deterministic code handles the state, voting, patch application, and stop conditions, so edits land only behind your sign-off. It also compiles the actual LaTeX and produces an issue ledger and verification report, which makes it useful for researchers who want a structured, auditable pre-submission check rather than a chatty rewrite. The repo includes a dogfood sample with before and after PDFs of a real draft's review, and for teams already inside Claude Code it installs in two commands and routes requests to direct-edit, review, or auto mode.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.