Imbad0202 /academic-research-skills
Academic Research Skills for Claude Code: research → write → review → revise → finalize
★ 57,015⑂ 4,345👁 146⑃ 606● 450▤ 52
Download: v3.24.3 — An author letter in the user's language, a field analyst that names no unconfirmed journal, and Phase 1 checks that count Chinese and Japanese textv3.24.3 ↓3.24.32026-11-14
+135
Daily
+961
Weekly
57,015
stars
4,345
forks
146
watchers
606
prs
450
issues
52
releases
README
Academic Research Skills for Claude Code 简体中文版 | 繁體中文版 | 日本語版 | 한국어 | Español | Português A comprehensive suite of Claude Code skills for academic research, covering the full pipeline from research to publication. Install in 30 seconds (Claude Code CLI / VS Code / JetBrains, v3.7.0+): text /plugin marketplace add Imbad0202/academic-research-skills /plugin install academic-research-skills Then try /ars-plan to walk through your paper structure via Socratic dialogue, or jump to Quick install for prerequisites and the traditional symlink flow. On claude.ai or Claude Desktop (paid plans), add the same repository under Customize → Plugins → Add → Add marketplace → Add from a repository, then install academic-research-skills. Hooks and plugin agents do not run in plain chat there; see SETUP Method 0. AI is your copilot, not the pilot. It can draft text, including a whole paper in full mode, but the decisions stay yours, and the pipeline stops for your confirmation at every stage. It handles the grunt work (hunting down references, formatting citations, verifying data, checking logical consistency) so you can focus on the parts that actually require your brain: defining the question, choosing the method, interpreting what the data means, and deciding what comes after "I argue that." You remain the author, and you answer for every claim you submit. Unlike a humanizer, this tool doesn't help you hide the fact that you used AI. It helps you write better. Style Calibration learns your voice from past work. Writing Quality Check catches the patterns that make prose feel machine-generated. The goal is quality, not cheating. Why human-in-the-loop, not full automation? Lu et al. (2026, Nature 651:914-919) built The AI Scientist — the first fully autonomous AI research system to publish a paper through blind peer review at a top-tier ML venue (ICLR 2025 workshop, score 6.33/10 vs workshop average 4.87). Their Limitations section enumerates the failure modes that any fully-autonomous AI research pipeline inherits: implementation bugs, hallucinated results, shortcut reliance, bug-as-insight reframing, methodology fabrication, frame-lock, citation hallucinations. ARS is built on the premise that a human researcher augmented by AI avoids these failure modes better than either alone. Stage 2.5 and Stage 4.5 integrity gates run a 7-mode blocking checklist (see academic-pipeline/references/ai_research_failure_modes.md); the reviewer offers an opt-in calibration mode that measures its own FNR/FPR against a user-supplied gold set. Zhao et al. (2026-05) audited 111M references across 2.5M papers on arXiv, bioRxiv, SSRN, and PMC. Their conservative estimate is 146,932 hallucinated citations for 2025 alone, with an observed mid-2024 inflection; for the bioRxiv-to-PMC pairing they report 85.3% preprint-to-published persistence. The paper describes "real citations deployed to support claims the cited references do not actually make" as an open challenge.
Top issues
#684Bind field/venue criteria across three consumers and measure constructive-review value8 comments · 2026-08-08#1025Windows: prefer a Python outside WindowsApps so the guard launcher does not start the Install Manager alias at all (follow-up to #1015)7 comments · 2026-10-26#879Gemini/Antigravity support?7 comments · 2026-09-17#575[META] User-confirmed review target and source-backed field/venue criteria4 comments · 2026-07-24#996Support Perplexity AI3 comments · 2026-10-21#828Reviewer calibration corpus: OpenReview camera-ready replacement leaks the accept label (blocks #653 first scored run)3 comments · 2026-09-06#1093citation_compliance_agent: some checks still assume APA 7th for every citation style2 comments · 2026-11-14#1001Reviewer-recommended references: verify through the existing resolver clients before they reach the decision letter (paper-derived: King & Worthington 2026)2 comments · 2026-10-23
Discussions
#1047分享一个面向机器学习实证的实验—主张交接 skill,想请教复审与来源记录设计1 comments · 2026-11-04#1046Newbie questions1 comments · 2026-11-04#848Review of acronyms and their appearance in text2 comments · 2026-09-09#818ARS token fee claim2 comments · 2026-09-04#780Clarification on bibliographic API usage in ARS-Codex1 comments · 2026-08-18#767Feature Proposal: Integration of Institutional Subscription Databases (Scopus, WoS, ScienceDirect)2 comments · 2026-08-17#765Will it 100% work with the Codex app for Windows OS and PoweShell , without Linux?1 comments · 2026-08-17#721会不会做成deepseek harness插件1 comments · 2026-08-13
Latest release
v3.24.3 — An author letter in the user's language, a field analyst that names no unconfirmed journal, and Phase 1 checks that count Chinese and Japanese text v3.24.3 2026-11-14Reviewer, citation, and adapter repairs and one new reviewer output; no new skill or mode, and the prompt-level changes are unmeasured: A full review now also writes the author a letter in the user's language beside the Editorial Decision Package. scripts/check_author_letter.py fails a quotation in the supported quotation marks that it cannot find in the manuscript, a machine line or internal id in the letter, and an item map that does not list each roadmap row once (1078). The field analyst lists what it read before the Reviewer Configuration Cards (1075), and the cards give checks with manus
相关报道 (9)
blog.csdnAcademic Research Skills 如何 2 条命令装好:完整安装与快速上手指南2026-10-07xGithubトレンド on X: "9/2 21:47 JST|GitHub Trendingから academic-research-skills をピックアップ。中身はスレッドへ。"2026-09-02note★31,400のClaude Code論文スキルを、note記事・Gumroad商品づくりに転用する全手順2026-06-15bilibiliAcademic Research Skills 全解析 — Claude Code 学术研究技能套件(25k+ Stars)2026-06-02noteAcademic Research Skillsとは?Claude Codeで論文作成・文献レビュー・引用チェックを半自動化する使い方2026-05-26view.inews.qq.com想用Codex做科研,可以先从这9个Skills开始2026-07-21Pasquale PillitteriGitHub Trending Top 10: 智能体、内存与端侧运行主导本周2026-05-21智源社区6.4k Stars!用Claude Code写论文的全套流水线,有人打包开源了2026-05-19CSDN博客Claude Code学术研究流水线开源!4个skill跑通科研全流程,多机制防AI出错2026-05-17
News & coverage (3)
Hacker NewsAcademic Research Skills for Claude Code▲ 82 · 25 comments · 2026-05-10Pasquale PillitteriGitHub Trending Top 10: Agents, Memory and On-Device Dominate the Week2026-05-24finance.biggo.comChinese Developers Bypass VPN to Use Claude Code: One-Line Command Connects DeepSeek, Academic Writing Toolkit Arrives2026-05-17