AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Awesome Academic Research Skills

mcp-kael-odin-awesome-academic-research-skills · by kael-odin

面向中文用户的学术论文与科研 Agent Skill 每日排行榜 · 自动搜索、过滤并排名 GitHub 上的 Claude Code / Codex / OpenCode 科研 Skill 仓库

— No reviews yet
0 installs
47 views
0.0% view→install

Install

$ agentstack add mcp-kael-odin-awesome-academic-research-skills

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-kael-odin-awesome-academic-research-skills)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Awesome Academic Research Skills? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Awesome Academic Research Skills

> 面向中文用户的学术论文与科研 Agent Skill 每日排行榜。自动搜索、过滤并排名 GitHub 上与论文写作、文献综述、深度研究、评审反馈、实验复现相关的 Skill / Agent / Workflow 仓库。

[](#今日榜单) [](#今日榜单) [](#收录标准) [](LICENSE) [](.github/workflows/update-rankings.yml)

[English](#english) · 可视化页面 · [JSON](data/rankings.json) · [CSV](data/rankings.csv) · [排名方法](docs/methodology.md) · [贡献指南](CONTRIBUTING.md)

项目特色

  • 🔄 每日自动更新 — GitHub Actions 每天 02:20 UTC 运行,自动搜索、过滤、排名并提交。
  • 🎯 精准双重信号过滤 — 必须同时命中"Skill/Agent/Workflow"与"Academic/Research/Paper"信号,挡住泛 AI 项目。
  • 📈 7 天趋势窗口 — 基于历史快照计算一周 Stars 增长,告别单日抖动导致的"全稳定"假象。
  • 🆕 本周新收录 — 自动识别近 7 天新进入榜单的仓库。
  • 🏷️ 适用 Agent 标签 — 推断每个仓库面向 Claude Code / Codex / OpenCode / MCP。
  • 🌐 双语可视化 — 中文优先,支持英文切换、搜索、分类筛选与多维度排序。
  • 📦 机器可读 — 提供 JSON / CSV 数据文件,方便二次开发与订阅。

今日榜单

  • 更新时间:2026-07-07T06:19:29Z
  • 收录门槛:GitHub Stars ≥ 100,排除 fork、归档仓库和明显非学术项目。
  • 精准规则:必须同时命中 Skill/Agent/Workflow 信号 和 Academic/Research/Paper 信号。
  • 趋势指标:基于近 7 天新增 Stars、最近 push 时间、新仓库加权和总体 Stars 规模综合计算。
  • 分类概览:深度研究 6 · 论文写作 6 · 文献综述 0 · 评审反馈 0 · 实验复现 0 · 学科专项 3 · 综合研究 6

| # | 仓库 | Stars | 趋势 | 分类 | 适用 Agent | 简介 | 最近更新 | |---:|---|---:|---|---|---|---|---| | 1 | Imbad0202/academic-research-skills | 36,618 | 热门上升 (7d:+1214) | 论文写作 | Claude | Academic Research Skills for Claude Code: research → write → review → revise → finalize | 2026-07-06 | | 2 | K-Dense-AI/scientific-agent-skills | 30,350 | 热门上升 (7d:+728) | 学科专项 | Claude/Codex | Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by… | 2026-07-06 | | 3 | Yuan1z0825/nature-skills | 26,631 | 热门上升 (7d:+2226) | 深度研究 | Codex | 符合nature论文学术表达和科研绘图的Skill | 2026-07-06 | | 4 | wanshuiyin/Auto-claude-code-research-in-sleep | 13,076 | 热门上升 (7d:+275) | 深度研究 | Claude/Codex/MCP | ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML res… | 2026-07-06 | | 5 | Orchestra-Research/AI-Research-SKILLs | 10,448 | 热门上升 (7d:+212) | 深度研究 | Claude/Codex | Comprehensive open-source library of AI research and engineering skills for any AI model.… | 2026-06-16 | | 6 | Imbad0202/academic-research-skills-codex | 5,624 | 热门上升 (7d:+559) | 综合研究 | Codex | Codex-native Academic Research Skills suite for human-in-the-loop academic research workf… | 2026-07-04 | | 7 | Master-cai/Research-Paper-Writing-Skills | 4,800 | 热门上升 (7d:+275) | 学科专项 | Claude/Codex | Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's ope… | 2026-06-23 | | 8 | HKUSTDial/Supervisor-Skills | 3,682 | 热门上升 (7d:+298) | 学科专项 | 通用 | 将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿,你的 AI 科研副导师。 | 2026-07-04 | | 9 | Weizhena/Deep-Research-skills | 1,538 | 热门上升 (7d:+138) | 深度研究 | Claude/Codex/OpenCode | Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop con… | 2026-05-07 | | 10 | pedrohcgs/claude-code-my-workflow | 1,369 | 热门上升 (7d:+43) | 论文写作 | Claude | A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent re… | 2026-06-10 | | 11 | aipoch/medical-research-skills | 1,311 | 热门上升 (7d:+46) | 综合研究 | 通用 | Hundreds of agent skills for medical research, including protocol design, data analysis,… | 2026-06-23 | | 12 | lishix520/academic-paper-skills | 1,003 | 热门上升 (7d:+35) | 综合研究 | Claude | Systematic framework for planning and writing academic papers using Claude Code. Includes… | 2026-01-04 | | 13 | 199-biotechnologies/claude-deep-research-skill | 819 | 持续增长 (7d:+14) | 深度研究 | Claude | Enterprise-grade deep research skill for Claude Code with 8-phase pipeline, source credib… | 2026-04-11 | | 14 | LigphiDonk/Oh-my--paper | 678 | 持续增长 (7d:+5) | 论文写作 | Claude | A Claude Code plugin that turns your terminal into an autonomous research lab — literatur… | 2026-04-15 | | 15 | Ar9av/PaperOrchestra | 604 | 持续增长 (7d:+5) | 论文写作 | Claude | An automated AI research-paper writer based off Google's PaperOrchestra paper's implement… | 2026-06-13 | | 16 | jimmc414/Kosmos | 548 | 持续增长 (7d:+3) | 深度研究 | Claude | Kosmos: An AI Scientist for Autonomous Discovery - An implementation and adaptation to be… | 2026-04-04 | | 17 | hkcanan/katmer-code | 461 | 持续增长 (7d:+5) | 综合研究 | Claude/Codex | Multi-provider AI sidebar for Obsidian — Claude, Gemini, Codex, Antigravity. Per-tab rout… | 2026-05-26 | | 18 | hanlulong/econ-writing-skill | 445 | 热门上升 (7d:+25) | 论文写作 | Claude/Codex | Agent Skill that transforms AI assistants into expert economics paper writers. Synthesize… | 2026-05-30 | | 19 | claesbackman/AI-research-feedback | 440 | 热门上升 (7d:+44) | 综合研究 | Claude | A collection of Claude Code skills for academic research review. These tools were develop… | 2026-07-05 | | 20 | LimHyungTae/awesome-claudecode-paper-proofreading | 395 | 持续增长 (7d:+4) | 论文写作 | Claude | Claude Code-driven research paper proofreading prompt | 2026-04-19 | | 21 | fcakyon/phd-skills | 314 | 持续增长 (7d:+12) | 综合研究 | Claude/MCP | PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review,… | 2026-07-03 |

分类标准

| 分类 | 说明 | |---|---| | 深度研究 | 多阶段 research agent、source validation、autonomous discovery、deep research workflow | | 论文写作 | 论文构思、写作、润色、LaTeX、proofreading、revision | | 文献综述 | literature survey、citation、bibliography、source collection | | 评审反馈 | peer review、reviewer feedback、critique、referee report | | 实验复现 | experiment design、benchmark、evaluation、reproducibility | | 学科专项 | 面向经济学、生物、医学、ML/CV/NLP 等具体领域 | | 综合研究 | 覆盖多个科研流程的通用 research skill |

使用方式

  1. 浏览上方榜单,优先查看 Stars、趋势(7 天增量)和分类。
  2. 打开 可视化页面 使用搜索、分类筛选、排序和中英文切换。
  3. 机器读取请使用 [data/rankings.json](data/rankings.json) 或 [data/rankings.csv](data/rankings.csv)。
  4. 如需推荐新仓库,提交 Issue(附仓库链接和一句推荐理由)或直接 PR 修改 config/ranking.json。

收录标准

  • 仓库必须明确服务学术、科研、论文、文献、评审或实验复现场景。
  • 仓库必须具备 Skill、Agent、Workflow、Claude Code、Codex、OpenCode 或类似可复用工作流信号。
  • 默认最低门槛为 100 Stars(可在 config/ranking.json 调整)。
  • fork、归档仓库、明显非学术用途仓库不会收录。

自动更新

GitHub Actions 每天运行一次 [.github/workflows/update-rankings.yml](.github/workflows/update-rankings.yml):

  • 使用 GitHub Search API 搜索候选仓库 + 拉取种子仓库元数据。
  • 应用精准过滤、分类和趋势计算(基于 data/history/ 下的每日历史快照)。
  • 更新 README.md、data/rankings.json、data/rankings.csv、data/rankings.js。
  • 保存当日快照到 data/history/YYYY-MM-DD.json(保留近 60 天)。
  • 如数据发生变化,自动提交到 main。

手动本地更新:

python scripts/update_rankings.py
python -m unittest discover -s tests -v

English

Awesome Academic Research Skills is a daily-updated ranking of GitHub repositories that provide academic, paper-writing, literature-review, deep-research, peer-review, and experiment-reproducibility skills for AI coding agents (Claude Code, Codex, OpenCode, …).

The ranking requires both a skill/agent/workflow signal and an academic/research/paper signal. Low-star, archived, forked, and clearly unrelated repositories are excluded. The trend column shows 7-day star growth. A bilingual static dashboard is available at the link above.

License

MIT

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.