peer-review

Open repos and models their makers tagged peer-review, most starred first. The same for everyone.

AI agentsRepo

Awesome-Journal-Skills

Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. | 覆盖主流期刊的 Claude Code/Codex 期刊技能包,从选题、识别策略到表格规范与审稿回复全流程,助你快速发论文。

  • 1.4k
  • Stata
  • MIT
  • 8 wk ago
AI agentsRepo

Anti-Autoresearch

Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

  • 181
  • Python
  • MIT
  • 3 d ago
wanshuiyinTake it
AI on my own machineRepo

PeerQA

Code and Data for PeerQA: A Scientific Question Answering Dataset from Peer Reviews, NAACL 2025 https://aclanthology.org/2025.naacl-long.22/

  • 18
  • Python
  • Apache-2.0
  • 6 mo ago
UKPLabTake it
AI on my own machineRepo

sci-paper

Claude Code plugin for scientific paper writing, source-traced review, and de-AI rewriting. 12 skills + 35 tools under one typed standard: non-waivable integrity blockers, zero-target L0 lexicon, ranked advisories, and explicit measurement states so missing calibration never reads as clean. Corpus-calibrated for ApJ/MNRAS/PRD/JCAP manuscripts.

  • 6
  • Python
  • 2 wk ago
skymanbpTake it
AI on my own machineRepo

context-aware-humanizer

AI humanizer, LLM writing assistant & bilingual Agent Skill for Chinese/English text polishing, rewriting, copyediting, proofreading, paraphrasing, tone adaptation and personal voice. Chat, social media, papers, grants, talks, slides, peer review & rebuttals. 中英文去AI味、说人话、润色改写、微信、小红书、推特、公众号、论文、基金本子、讲稿、PPT、审稿意见与回复。 Text only; no platform APIs.

  • 3
  • Python
  • MIT
  • 2 wk ago
quqxuiTake it
GitHubRepo

dsh-response-letter

Reviewer-response workflow for DeepSeek Harness: parse reviewer comments (Reviewer/Referee/审稿人 headers, numbered or paragraph mode) with locators, check point-by-point coverage by response number (missing, too short, extra, duplicates), and export a Markdown response letter with a coverage table. Parsed reviews become REP evidence; coverage counts

  • 1
  • TypeScript
  • Apache-2.0
  • 3 d ago
PerryLinkTake it
Search GitHub and Hugging Face for peer-review

Get , open it once and sign in. Then come back here and press the button again.