absent-author

What is absent-author

Absent Author is an open-source project that provides an evidence checklist and Agent skills for detecting AI-generated papers and determining whether there is a real human author behind them.

Key features

• Provides an evidence checklist of 83 sourced indicators of AI-generated papers, including strength, false-positive notes and paper-type exemptions
• Includes the paper-author-pass skill to help authors complete AI-assisted papers by generating questions only humans can answer, claim-evidence mappings, citation verification and figures
• Includes the paper-slop-screen skill to help reviewers or ACs assign W/R/Q ratings, four-quadrant analysis, findings with locations and citations, and review paragraphs for suspicious papers
• Provides the slop_lint.py tool that performs calibrated counting of 28 surface traces as candidates for human reading
• Outputs review results containing locations, citations, review paragraphs and notes for the AC

Who it is for

Suitable for authors completing AI-assisted papers, reviewers or ACs facing suspicious submissions, researchers needing quick surface scans, and maintainers of review standards.

How to get started

1. Run ./install.sh to install the skills to ~/.claude/skills (or use the --project, --codex, --dest DIR, --link parameters)
2. Use the paper-author-pass or paper-slop-screen skills in Claude Code, Codex or any Agent that can read SKILL.md

Compiled from public descriptions on the tool's official website / README / launch page. Pricing and user numbers have not been verified; please check the official website. Some sections were drafted with AI assistance. Written in Chinese and English; other languages are machine-translated.