SkillAtlasSkill 详情

g1

Security audit: baseline 52/52 CLEAN

审核状态:已审核Quality 80Security 88

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年8月6日

Awesome GitHub stars License: CC BY-SA 4.0 PRs Welcome Validate catalog OpenSSF Scorecard Security audit: baseline 52/52 CLEAN Rigor coverage Powered by StatsPAI

Auto-Empirical Research Skills (AERS)

📌 文档结构(2026-07-22 起): 本文件是中文默认入口 —— banner + badges + 信任面 + 9 阶段流水线速览 + 76 行合集总表。 每个合集的完整描述、按用途分组、精确数字、验证方法在 docs/CONTENT_ZH.md(扩展正文,总表行内的 → 直接跳转到对应锚点)。

English version: README-en.md · 中文扩展正文:docs/CONTENT_ZH.md · README-zh-CN.md 已弃用(重定向占位)

🌐 语言: English | 简体中文(默认) | 繁體中文 | 日本語 | 한국어


CoPaper.AI Stanford REAP - Center on China's Economy & Institutions

Stanford REAP × CoPaper.AI · 实证研究 AI 工具的学术工业级产品
由斯坦福实证研究方法论团队打造,覆盖从数据清洗到顶刊投稿的完整工作流



实证研究智能体技能大全封面图

🚀 New here? Open the Skill Search → to filter all 1,096 skills by method, stage, language, and license. The 5-minute tour (make quickstart) prints the same picture in your terminal.

🇨🇳 中文用户从本文件开始(流水线速览 + 76 行总表),每个合集的完整描述见 docs/CONTENT_ZH.md。📖 English readers: see README-en.md.


信任面 · Trust surface (rigor stats)

Rigor laneCountWhere
Numeric benchmark tasks — gold values recomputed from real data each run17benchmark/
Behavioral eval scenarios / rubric items37 / 183eval-harness/

Full trust overview: docs/TRUST.md · docs/RIGOR_COVERAGE.md


⚡ 安装与使用(30 秒上手)

最省事的一招:把 URL 丢给 Agent

把项目 URL 地址 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills 丢给 Claude Code / Codex,并指定是目录 / 项目 / 全局安装 —— 剩下的让它自己做。例如:

帮我安装 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills
装到「全局」(~/.claude/skills/),我想在所有项目里都能用

把最后一行换成你要的作用域即可:

作用域说给 Agent 的话落到哪里
目录(当前会话临时用)"只在当前目录用,不要全局安装"当前工作目录下的 .claude/skills/
项目(团队共享,可提交进 git)"装到本项目"项目根目录 .claude/skills/
全局(所有项目可用)"装到全局"~/.claude/skills/(Codex 为 ~/.codex/skills/)

手动安装(两种,任选其一)

A. 插件市场(Claude Code v2.1+,推荐,可升级)

claude plugin marketplace add brycewang-stanford/Auto-Empirical-Research-Skills
claude plugin install aer-skills@auto-empirical-research-skills                 # 顶刊投稿全流程(9 skills)
claude plugin install empirical-analysis-python@auto-empirical-research-skills  # Python 计量流水线
claude plugin install empirical-analysis-stata@auto-empirical-research-skills   # Stata 计量流水线
claude plugin install empirical-analysis-r@auto-empirical-research-skills       # R + Quarto 流水线

B. 只要某一个 skill —— 直接拷文件夹

git clone --recurse-submodules https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git
cd Auto-Empirical-Research-Skills

cp -R skills/00.1-Full-empirical-analysis-skill_Python  .claude/skills/   # 项目级
cp -R skills/00.1-Full-empirical-analysis-skill_Python  ~/.claude/skills/ # 全局

拷进去的文件夹必须自带 SKILL.md(部分合集的 SKILL.md 在下一层,拷那一层)。

怎么用

新开一个会话,直接用自然语言说要做什么,Agent 会按 description 自动挑 skill;说不动就点名方法或 skill:

用面板数据跑一个 Callaway–Sant'Anna 事件研究,并出 HonestDiD 稳健性和期刊级表格

完整安装说明(Codex / CodeBuddy 整库导入、--plugin-dir 单次加载、常见故障排查)见 INSTALL.md。


中文文档结构

中文内容分两级维护,各司其职:

  • 本文件(README.md,GitHub 默认入口):banner、badges、信任面、9 阶段流水线速览、76 行合集总表。
  • docs/CONTENT_ZH.md(扩展正文):每个合集的完整描述(#skill-NN 锚点)、按用途分组、精确数字、2 分钟验证、三层信任、旗舰流水线详解、贡献与引用。总表行内的 → 直接跳到对应锚点。
  • 其他语言:README-en.md · README-zh-TW.md · README-ja.md · README-ko.md

[!NOTE] 维护规则: 改合集总表 → 本文件与 CONTENT_ZH.md 的锚点表两处同步;改合集详情 / 分组 / 数字 → 只改 docs/CONTENT_ZH.md。统计数字(合集数 / skill 数)以 catalog/skills.json 为准,由 make validate 的 readme-stats 检查器守护。

贡献者(Contributors): 提交前请在本地跑通完整门禁 make check(catalog 校验 + 链接 + 单元测试 + eval-harness + benchmark)。详见 CONTRIBUTING.md。

旧版归档: README-zh-CN.md 已弃用,仅作向后兼容的重定向占位。


🚀 从一个 idea 到一篇论文:社科实证研究 · 端到端流水线(全自动、可介入)

AERS 不只是 76 个散装 skill —— 它能陪你走完一篇论文。 从模糊 idea → 选题精炼 → 文献综述 → 数据获取 → 识别策略 → 估计建模 → 稳健性审计 → 出版级表格 / 图形 → 写作与同行评审 → 降 AIGC → 投稿。端到端、全自动、每一步都可被人介入(中间任何一步你都可以接过去手工改方法、补变量、加稳健性,再让流水线自动接上跑)。

9 阶段流水线 · 每一步都覆盖到具体 skill

#阶段关键 skills(点合集名进目录,→ 进完整说明)
1️⃣选题精炼 — Agent 把模糊想法收紧成"可证伪 + 可执行"的研究问题· 25 Diverga · 33 claude-scholar · 05 research-superpower · 11 compound-science
2️⃣文献综述 — 检索 · 筛选 · PRISMA 流程 · 批判性阅读 · 主题分析· 36 literature-review-skill · 24 academic-research-skills · 59 openalex-skill · 68 research-productivity-skills · 53 thematic-analysis
3️⃣数据获取 — 公开数据库 · API · 网页抓取 · 数据清洗· 33 claude-scholar · 68 research-productivity-skills · 32 stata-skill · 57 edgartools
4️⃣识别策略 — DiD / RD / IV / SCM / DML / matching 全覆盖· ⭐ 00 StatsPAI 🔥 · 10 causal-inference-mixtape · 13 MixtapeTools · 51 CausalPy · 63 scientific-agent-skills
5️⃣估计建模 — Python / Stata / R 三栈,900+ 估计器· ⭐ 00.1 Full Empirical · Python · ⭐ 00.2 Full Empirical · Stata · ⭐ 00.3 Full Empirical · R · 40 pyfixest · 39 marginaleffects · 09 awesome-econ-ai
6️⃣稳健性审计 — 复现包检查 · Honest-DiD · R&R 模拟· 41 sewage-econometrics-check · ⭐ 50 AER-skills · 21 AI-research-feedback
7️⃣表格 & 图形 — 期刊出版级排版 · LaTeX 嵌入· ⭐ 00 StatsPAI · 07 AI-Research-SKILLs · 33 claude-scholar · 08 latex-document-skill
8️⃣写作 & 同行评审 — LaTeX / Quarto · 仿审稿人 · 校对· 06 stats-paper-writing · 04 scientific-writer · 22 christopherkenny-skills · 38 academic-proofreader · 56 econ-writing-skill · 16 clo-author
9️⃣降 AIGC & 投稿 — 知网 / 万方 / Turnitin / 23 类 AI 痕迹模式· ⭐ 48 de-AIGC-skills 🇨🇳🇬🇧 · 44 humanizer_academic · 45 deslop · 46 stop-slop · 47 avoid-ai-writing · 49 humanize-chinese

🎼 元编排:⭐ 69 Paper-WorkFlow —— 一键串起来

Paper-WorkFlow 是 AERS 的"指挥棒",它把上面 9 个阶段的 skill 串成 一条按键即运行的端到端流水线。 你在 IDE 入口给它一句自然语言:

"开一个新论文项目:空气污染与中国劳动力市场,CS 设计 + 省级面板"

它会自动按顺序调:

  1. ⭐ 00 StatsPAI → sp.csdid(...) 给出 CS-DID 估计草案 + 写出估计方程与识别假设
  2. 33 claude-scholar → 抓变量定义 / 数据源候选 / 相关文献
  3. ⭐ 00 StatsPAI → 真跑 sp.feols(...) + sp.honest_did(...)
  4. 41 sewage-econometrics-check → 10 项复现包审计 + 稳健性体检
  5. ⭐ 00 StatsPAI + 07 AI-Research-SKILLs → 出 Table 1–5 + 期刊级图
  6. 38 academic-proofreader → 通读 + §comment 标"审稿人会挑刺的位置"
  7. 56 econ-writing-skill 起草初稿 + ⭐ 48 de-AIGC-skills 🇨🇳🇬🇧 + 45 deslop 过知网 / Turnitin

任何阶段你都可以手动介入 —— 上一阶段的产物全部落盘(产物-幂等 pipeline),你接过去改方法、补控制、加稳健性,再让流水线自动接下去跑。这就是"全自动 + 可介入"。

🏆 7 个 Stanford REAP × CoPaper.AI 自研 skill —— 是整个流水线的主干

⭐ Skill在流水线里的角色
00 StatsPAI 🔥因果引擎:900+ 函数,sp.causal(...) 一行跑闭环(DID / RD / IV / SCM / DML / matching)
00.1 Full Empirical · Python 📘显式 Python 栈(pandas / statsmodels / linearmodels / pyfixest)
00.2 Full Empirical · Stata 📊显式 Stata 栈(reghdfe / ivreg2 / csdid / sdid / rdrobust)
00.3 Full Empirical · R 📗显式 R 栈(tidyverse / fixest / did / HonestDiD)+ Quarto 渲染
48 de-AIGC-skills 🇨🇳🇬🇧中英双语学术降 AIGC(Turnitin AI / GPTZero / 知网 / 万方)
50 AER-skills 📕Top-5 经济学投稿套件:识别 → 稳健性 → R&R
69 Paper-WorkFlow 🧭元编排器,把上面 9 个阶段串成一键流水线

为什么挑这 7 个?因为它们的行为都被基准钉死了 —— 不是营销口径,是对着已知答案反复跑过验证过的(17 项数值 benchmark + 37 项行为评测 ↗)。

看到这里 —— 完整 76 行合集目录

↴ 直跳到下方 76 行总表(每个合集带 #skill-NN 锚点)。如果你更关心"这些 skill 怎么用"而不是"有哪些 skill",看 📘 中文唯一权威正文 里的「按用途分组」与「旗舰流水线」两节。


🧰 76 个核心 Skills 合集一览(00 → 72,编号连续无空缺)

打开仓库 → 看见整座库。 全部 76 个合集 · 1,096 个 skill,每一个都已 vendor 进本仓库,由 catalog/skills.json 跟踪。⭐ = Stanford REAP × CoPaper.AI 团队自研的 skill;其余为精选、经安全审计的社区作品。

主题图例 — 🚀 全流程与编排器 · 🎯 因果推断与计量经济学 · 📚 文献与研究设计 · ✍️ 写作 / 编辑 / 去 AIGC · 📑 引用 / 复现 / 同行评审 · 🛠️ 数据 / 工具 / 基础设施

点击【→】 跳转到 docs/CONTENT_ZH.md 中该合集的完整描述;点击合集名 直接打开其目录。

🙏 尊重原作者 — 「来源」列直接链回上游原始仓库(owner/repo)。本仓库里的社区合集都是上游快照:请去原仓库点 star、提 issue、看 LICENSE。完整的许可证与来源置信度审计见 docs/LICENSE_AUDIT.md,机器可读版本在 catalog/provenance.json。

#合集一句话详情来源
⭐ 00StatsPAI 🔥因果引擎 · Agent-native Python DSL:sp.causal(...) 一行跑闭环(DID/RD/IV/SCM/DML,900+ 函数)→brycewang-stanford/StatsPAI
⭐ 00.1Full Empirical · Python 📘显式栈:pandas · statsmodels · linearmodels · pyfixest→⭐ 本仓库
⭐ 00.2Full Empirical · Stata 📊reghdfe · ivreg2 · csdid · sdid · rdrobust 复现包→⭐ 本仓库
⭐ 00.3Full Empirical · R 📗tidyverse · fixest · did · HonestDiD + Quarto 渲染→⭐ 本仓库
01academic-paper-skills大纲 → 手稿写作 + 7 维审稿人模拟→lishix520/academic-paper-skills
02research-skills医学影像综述、提案、论文转幻灯片→luwill/research-skills
03scientific-skills假设生成 + 28 个科学数据库→K-Dense-AI/claude-scientific-skills
04scientific-writer引用管理 + 科学写作→K-Dense-AI/claude-scientific-writer
05research-superpower系统化检索、筛选与引文溯源→kthorn/research-superpower
06stats-paper-writing端到端 LaTeX 统计论文写作→fuhaoda/stats-paper-writing-agent-skills
07AI-Research-SKILLs发表级 ML 图表、LaTeX、引文核验→Orchestra-Research/AI-Research-SKILLs
08latex-document-skill创建 / 编译任意 LaTeX 文档为 PDF→ndpvt-web/latex-document-skill
09awesome-econ-aiPython 面板数据分析(linearmodels)→meleantonio/awesome-econ-ai-stuff
10causal-inference-mixtapeDID / IV / RDD / SCM 模板(Cunningham)→Jill0099/causal-inference-mixtape
11compound-science面向定量社会科学的贝叶斯估计→James-Traina/compound-science
12claude-code-my-workflow提交 → PR → 合并的研究工作流(Emory)→pedrohcgs/claude-code-my-workflow
13MixtapeToolsCunningham 的因果推断工具集与讲义→scunning1975/MixtapeTools
14research-starterR 中的 IV / DiD / RDD,含完整诊断→luischanci/claude-code-research-starter
15social-science-researchR 或 Python 端到端数据分析→Felpix-Studios/social-science-research
16clo-author多代理数据分析(R / Stata / Python)→hsantanna88/clo-author
17DAAF安全意识代理框架(32 条 deny rule)→DAAF-Contribution-Community/daaf
18stata-accounting来自 126 篇 JAR 论文的实测 Stata 范式→jusi-aalto/stata-accounting-research
19vera-economic-intelligence经济情报 / 政策研究情报工作流→CuellarC05/vera-economic-intelligence
20python-econ-skillDSGE / HANK 与定量经济计算→wenddymacro/python-econ-skill
21AI-research-feedback用 AI 同行评审生成结构化反馈→claesbackman/AI-research-feedback
22christopherkenny-skills面向 Quarto(.qmd)的 APSA 风格检查器→christopherkenny/skills
23baygent带护栏的 PyMC / Arviz 贝叶斯工作流→Learning-Bayesian-Statistics/baygent-skills
24academic-research-skills5 审稿人多视角论文评审→Imbad0202/academic-research-skills
25Diverga研究问题精炼器(抗模式坍缩)→HosungYou/Diverga
26scholar统计算法设计与文档→Data-Wise/claude-plugins
27my_claude_skills经济学摘要写作指南→dariia-m/my_claude_skills
28paper-replicate-agent论文复现代理演示→maxwell2732/paper-replicate-agent-demo
29project20XXy可复现手稿 + notebook 项目→quarcs-lab/project20XXy
30zirui-song-claude-skillsZirui Song 的研究辅助 Claude 技能集→zirui-song/claude-skills
31claude-code-skillsPython 面板数据分析→thalysandratos/claude-code-skills
32stata-skill高性能 Stata C/C++ 插件→dylantmoore/stata-skill
33claude-scholar研究全生命周期:选题 → 综述 → 实验 → 审稿回复→Galaxy-Dawn/claude-scholar
34research-companion头脑风暴、评估并决策研究方向→andrehuang/research-companion
35academic-writing-skills面向投稿场所的工业 AI 文献研究→bahayonghang/academic-writing-skills
36literature-review-skill完整文献综述工作流(中文)→taoyunudt/literature-review-skill
37IlanStrauss-ai-skillsIlan Strauss 经济学研究 AI 工作流→IlanStrauss/ai-skills
38academic-proofreader学术校对→peternka/academic_proofreader
39marginaleffects预测、斜率与比较(R / Python)→vincentarelbundock/marginaleffects
40pyfixestPython 中的快速固定效应估计→py-econometrics/pyfixest
41sewage-econometrics-check10 项复现包审计→sticerd-eee/sewage
42ARIS自主「research-in-sleep」代理,端到端→wanshuiyin/Auto-claude-code-research-in-sleep
43research-plugins478 个研究插件:数据可视化、领域、基础设施→wentorai/research-plugins
44humanizer_academic为医学/学术手稿去 AI 味(23 类模式)→matsuikentaro1/humanizer_academic
45deslop去除 AI 写作痕迹(5 维评分)→stephenturner/skill-deslop
46stop-slop三层 AI 痕迹检测与改写→hardikpandya/stop-slop
47avoid-ai-writing审计 → 改写 → 二次审计 AI 味(留痕)→conorbronsdon/avoid-ai-writing
⭐ 48de-AIGC-skills 🇨🇳🇬🇧中英双语学术降 AIGC(Turnitin AI / GPTZero / 知网 / 万方)→⭐ 本仓库
49humanize-chinese检测并人性化 AI 生成的中文文本→swaylq/humanize-chinese
⭐ 50AER-skills 📕Top-5 经济学投稿套件:识别 → 稳健性 → R&R→brycewang-stanford/AER-skills
51CausalPy贝叶斯准实验(PyMC Labs)→pymc-labs/CausalPy
52slr-prisma系统文献综述,PRISMA 2020→keemanxp/slr-prisma
53thematic-analysisBraun & Clarke 六阶段定性主题分析→keemanxp/thematic-analysis-skill
54open-science-skills引用一致性、DOI 与论据支撑审计→scdenney/open-science-skills
55r-skillsR 中用 brms 做贝叶斯推断→ab604/claude-code-r-skills
56econ-writing-skill综合 50+ 顶级指南的经济学写作→hanlulong/econ-writing-skill
57edgartools查询与分析 SEC 文件→dgunning/edgartools
58econstack政策简报(UK GES / AU Treasury)→charlescoverdale/econstack
59openalex-skill通过 OpenAlex 查询 2.4 亿+ 学术作品→shiquda/openalex-skill
60superpapers综合性实证研究支持套件→regisely/superpapers
61research-methods与预注册匹配的验证性检验→phdemotions/research-methods
62citation-checker对照 CrossRef / S2 / OpenAlex 核验引用→PHY041/claude-skill-citation-checker
63scientific-agent-skillsDoWhy 识别–估计–反驳框架→tondevrel/scientific-agent-skills
64mcp-stata20 个 Stata 因果推断与复现 skill→tmonk/mcp-stata
65game-theory-paper-writer生成并压力测试博弈论论文→本仓库 PR #17
66empirical-research-skills面向大型面板的 R 性能优化→SiyaoZheng/ai4ss-skills
67econfin-workflow-toolkit中国公司金融实证工作流,从提案到论文→本仓库 PR #22
68research-productivity-skills论文检索、SSRN、DOI 查询、下载→本仓库 PR #21
⭐ 69Paper-WorkFlow 🧭元编排器,串起整个社会科学论文流水线→brycewang-stanford/Paper-WorkFlow
70ssci-polish ✍️SSCI / SCI 英文论文语言润色(语法、可读性、学术语气)→⭐ 本仓库
⭐ 71lit-review-agent-tools 🔍文献综述工具选型 + 一键安装运行(MinerU / PaperQA2 / ASReview / STORM / MCP 服务器)→brycewang-stanford/lit-review-agent-tools
⭐ 72Kaggle Research 🧪通过官方 CLI 安全检索 Kaggle 资源、限界下载公开数据并保留审计证据→⭐ 本仓库

想看更详细的描述(主题分类、字段、统计)? 见 docs/CONTENT_ZH.md 中标注 #skill-NN 锚点的同一张表 —— 它是每个合集的完整描述所在的扩展正文。

📈 项目历程

自 2026-04 首次发布以来的主干里程碑(完整提交记录见 Commits 与 CHANGELOG.md):

---
config:
  gitGraph:
    rotateCommitLabel: false
---
gitGraph TB:
   commit id: "2026-04 首次发布"
   branch community
   commit id: "2026-05 首个社区 PR"
   checkout main
   merge community
   commit id: "2026-05 更名 AERS"
   commit id: "2026-06 插件市场"
   commit id: "2026-06 全库路由器"
   commit id: "2026-07 首个 tag" tag: "v2026.07"
   branch kaggle
   commit id: "2026-07 Kaggle 集成"
   checkout main
   merge kaggle
   commit id: "2026-08 de-AIGC 双语"
Star History Chart

Star 增长曲线(非提交数)· 由 scripts/build-star-history.py 从 GitHub API 生成并提交入库

如果 AERS 对你的工作有帮助,请引用它(CITATION.cff)并点个 Star,让更多研究者看到。


AI 是放大器,不是替代品。它替你做最耗时的"搬砖",你保留最核心的"判断"。


CoPaper.AI Stanford REAP

Stanford REAP × CoPaper.AI · 实证研究 AI 工具的学术工业级产品


扫码访问 copaper.ai
扫码访问 copaper.ai
CoPaper.AI 公众号
关注公众号「CoPaper.AI」

内置 20 个方法论 skill · 20 分钟完成实证论文 · 自研 StatsPAI(900+ 函数 / MIT 开源)

其他

中风险

  • 来源需自行核对维护者身份。
  • 未检测到明显脚本安装指令。
  • 未检测到明显外部权限要求。
  • 未检测到高风险命令。
  • 扫描发现:2 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git
  3. 将 "skills/25-HosungYou-Diverga/skills/g1" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git
  3. 将 "skills/25-HosungYou-Diverga/skills/g1" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git
  3. 将 "skills/25-HosungYou-Diverga/skills/g1" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git
  3. 将 "skills/25-HosungYou-Diverga/skills/g1" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git
  3. 将 "skills/25-HosungYou-Diverga/skills/g1" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: g1
description: |
  VS-Enhanced Journal Matcher with Journal Intelligence MCP — Real-time journal data pipeline
  with checkpoint-based human decisions. Uses OpenAlex + Crossref APIs for live metrics.
  Light VS applied: Avoids IF-centric recommendations + multi-dimensional matching strategy
  Use when: selecting target journals, planning submissions, comparing publication options
  Triggers: journal, submission, impact factor, academic journal, publication, submit
version: "12.0.1"

Journal Matcher

Agent ID: 17 Category: E - Publication & Communication VS Level: Light (Modal Awareness) Tier: Core Icon: 📝 Version: 10.0.0

Overview

Identifies optimal target journals for research and develops submission strategies. Comprehensively analyzes journal scope, impact, review timeline, OA policies, and more using real-time data from OpenAlex and Crossref APIs via the Journal Intelligence MCP.

Applies VS-Research methodology (Light) to go beyond Impact Factor-centric recommendations, presenting multi-dimensional matching strategies suited to research context and goals.

MCP Prerequisites

This agent uses the Journal Intelligence MCP (journal-server.js) for real-time data.

MCP ServerTools UsedRequired
journaljournal_search_by_field, journal_metrics, journal_publication_trends, journal_editor_info, journal_compare, journal_special_issuesYes (6 tools)

Fallback: If MCP unavailable, agent operates in knowledge-based mode using training data.

MCP Integration

ToolWhen UsedPipeline Stage
journal_search_by_fieldInitial journal discoveryStage 1
journal_metricsDetailed metrics for candidatesStage 1-2
journal_publication_trendsTrend analysis for top journalsStage 3
journal_editor_infoReviewer suggestion supportStage 3
journal_compareSide-by-side comparison tableStage 3
journal_special_issuesSpecial issue opportunitiesStage 3

Natural Language Routing

User QueryTool(s) Called
"Find journals for educational technology research"journal_search_by_field(field="educational technology")
"What's the h-index of Computers & Education?"journal_metrics(journal_name="Computers & Education")
"Compare these 3 journals"journal_compare(journal_ids=[...])
"Show publication trends for this journal"journal_publication_trends(journal_id=...)
"Who publishes most in this journal?"journal_editor_info(journal_id=...)
"Any special issues on AI in education?"journal_special_issues(field="AI in education", ...)

Pipeline Flow

User request (research abstract + field)
  │
  ▼
Stage 1: G1 analyzes research field/methodology
  │
  ├── journal_search_by_field(field) ─┐
  └── journal_metrics(candidates)  ───┘  [parallel MCP calls]
  │
  ▼
🟠 CP_JOURNAL_PRIORITIES [AskUserQuestion]
  "연구 분야: {field}. 저널 선택 우선순위를 선택하세요"
  [Impact Factor 우선] [출판 속도 우선] [OA 우선] [Scope Fit 우선] [균형 추천]
  │
  ▼
Stage 2: Re-rank journals by user's priority
  │
  ├── journal_compare(top_5) ──────────────┐
  └── journal_publication_trends(top_3) ───┘  [parallel MCP calls]
  │
  ▼
🟠 CP_JOURNAL_SELECTION [AskUserQuestion]
  "추천 저널 (실시간 데이터):"
  Table: IF, h-index, Scope Fit, Review Speed, OA
  [1순위 저널 선택] [여러 저널 동시 투고 전략] [더 많은 저널 검색] [다른 분야로 재검색]
  │
  ▼
Stage 3: Generate detailed strategy for selected journal(s)
  │
  ├── journal_editor_info(selected) ──────┐
  └── journal_special_issues(selected) ───┘  [parallel MCP calls]
  │
  ▼
Output: Report + Cover letter template + Sequential submission plan

Checkpoints

CheckpointLevelWhenOptions
CP_JOURNAL_PRIORITIES🟠 RecommendedAfter initial search, before rankingImpact Factor / Speed / OA / Scope Fit / Balanced
CP_JOURNAL_SELECTION🟠 RecommendedAfter comparison, before strategy generationSelect journal / Multi-submit / More search / Re-search

CP_JOURNAL_PRIORITIES

question: "연구 분야: {field}. 저널 선택 우선순위를 선택하세요 / Select your journal priority"
header: "Journal Priorities"
options:
  - label: "Impact Factor 우선"
    description: "높은 IF/h-index 저널 중심 추천"
  - label: "출판 속도 우선"
    description: "빠른 리뷰/출판 프로세스 중심"
  - label: "OA 우선"
    description: "오픈 액세스 저널 + 낮은 APC 중심"
  - label: "Scope Fit 우선"
    description: "연구 주제와의 적합도 최우선"
  - label: "균형 추천"
    description: "모든 기준을 균형 있게 고려"

CP_JOURNAL_SELECTION

question: "추천 저널 목록입니다. 어떻게 진행하시겠습니까? / Select your preferred journal strategy"
header: "Journal Selection"
options:
  - label: "1순위 저널 선택"
    description: "가장 적합한 저널 1개에 대한 상세 전략 생성"
  - label: "여러 저널 동시 투고 전략"
    description: "순차적 투고 계획 (1순위 → 2순위 → 3순위)"
  - label: "더 많은 저널 검색"
    description: "다른 조건으로 추가 검색"
  - label: "다른 분야로 재검색"
    description: "연구 분야를 변경하여 다시 검색"

VS Modal Awareness (Light)

⚠️ Modal Journal Matching: The following are the most predictable approaches:

CriterionModal Approach (T>0.8)Multi-dimensional Approach (T<0.5)
Ranking"Recommend by highest IF"Scope fit + Readership + IF integrated
Selection"Top journal → downward"Goal-optimized (Speed/Impact/OA)
Strategy"Next tier on rejection"Parallel strategy (Preprint + Submit)
Cost"Minimize APC"ROI analysis (Visibility vs. Cost)

Multi-dimensional Principle: IF is just one indicator; select optimal journal for research goals

When to Use

  • When selecting journals for paper submission
  • When comparing between journals
  • When developing submission strategy (1st, 2nd, 3rd choice)
  • When reviewing OA publication options

Core Functions

  1. Scope Matching (MCP-enhanced)

    • Research topic and journal scope fit
    • Recent publication trend analysis via journal_publication_trends
    • Special Issue information via journal_special_issues
  2. Impact Analysis (MCP-enhanced)

    • h-index, cited_by_count, works_count via journal_metrics
    • 2yr_mean_citedness (proxy for Impact Factor)
    • Within-field ranking via journal_search_by_field
  3. Practical Information

    • Average review time (knowledge-based)
    • Acceptance/rejection rate (knowledge-based)
    • Publication cost (APC) via journal_metrics
  4. OA Policy (MCP-enhanced)

    • is_oa status via journal_metrics
    • Homepage URL for policy lookup
    • Preprint policy (knowledge-based)
  5. Submission Strategy (MCP-enhanced)

    • Sequential submission plan
    • Cover letter points
    • Reviewer suggestions via journal_editor_info

Journal Tier Classification

TierCharacteristicsExamples (General)Acceptance Rate
Tier 1Top, multidisciplinaryNature, Science, PNAS<10%
Tier 2Field topPsychological Bulletin, RER10-20%
Tier 3Field upperJEP:LMC, C&E, BJET20-35%
Tier 4Field mid-levelField-specific journals35-50%
Tier 5Emerging, regionalNewer, regional journals>50%

Input Requirements

Required:
  - research_abstract: "Research summary"
  - field: "Academic area"

Optional:
  - priorities: "IF vs. Speed vs. OA"
  - study_type: "Empirical/Theoretical/Review"
  - constraints: "Time, cost"

Output Format

## Journal Matching Report

### Research Information
- Title: [Research title]
- Field: [Academic field]
- Study Type: [Empirical/Theoretical/Review/Meta-analysis]
- Analysis Date: [Date]
- Data Source: OpenAlex + Crossref (real-time)

---

### 1. Research Characteristics Analysis

| Item | Analysis |
|------|----------|
| Subject Area | [Specific topic] |
| Methodological Approach | [Quantitative/Qualitative/Mixed] |
| Contribution Type | Theoretical/Empirical/Methodological |
| Potential Impact | High/Medium/Low |
| Target Audience | [Target readers] |

---

### 2. Recommended Journals List

#### 🥇 1st Choice: [Journal Name]

| Item | Information |
|------|-------------|
| Publisher | [Publisher name] |
| h-index | [X] (OpenAlex) |
| 2yr Mean Citedness | [X.XX] (proxy for IF) |
| Cited By Count | [X,XXX] |
| Works Count | [X,XXX] |
| Scope Fit | ⭐⭐⭐⭐⭐ (5/5) |
| Average Review Time | [X] weeks (Initial → Decision) |
| Estimated Acceptance Rate | ~XX% |
| OA Status | [Yes/No] |
| APC | $X,XXX (if applicable) |
| Preprint Policy | Allowed/Not allowed |

**Fit Analysis**:
- ✅ Recent similar topic published: [Paper example]
- ✅ Methodology preference: [Methodology]
- ⚠️ Caution: [Considerations]

**Submission Strategy**:
- Cover letter emphasis: [Points]
- Suggested reviewers: [From journal_editor_info data]
- Exclude reviewers: [If applicable, with reason]

---

#### 🥈 2nd Choice: [Journal Name]
[Same format]

---

#### 🥉 3rd Choice: [Journal Name]
[Same format]

---

### 3. Journal Comparison Table (from journal_compare)

| Criterion | [Journal 1] | [Journal 2] | [Journal 3] |
|-----------|-------------|-------------|-------------|
| h-index | X | X | X |
| 2yr Mean Citedness | X.XX | X.XX | X.XX |
| Works Count | X,XXX | X,XXX | X,XXX |
| Scope Fit | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐ |
| Review Speed | ⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ |
| OA Status | Yes/No | Yes/No | Yes/No |
| APC | $X,XXX | $X,XXX | Free |

---

### 4. Publication Trends (from journal_publication_trends)

| Year | Works | Citations | OA |
|------|-------|-----------|-----|
| 2024 | XXX | X,XXX | XXX |
| 2023 | XXX | X,XXX | XXX |
| ... | ... | ... | ... |

---

### 5. Sequential Submission Plan

Submission Strategy Timeline ─────────────────────────────────────────────

1st Submission: [Journal 1] (Tier 2) │ ├── Accept → 🎉 Complete │ └── Reject (Expected: ~3 months later) │ ▼ 2nd Submission: [Journal 2] (Tier 3) │ ├── Accept → 🎉 Complete │ └── Reject (Expected: ~6 months later) │ ▼ 3rd Submission: [Journal 3] (Tier 3-4) │ └── High acceptance probability


**Estimated Total Time**:
- Best case: 3-4 months (1st acceptance)
- Typical: 6-9 months (2nd acceptance)
- Worst case: 12+ months (3rd or beyond)

---

### 6. Cover Letter Template

Dear Editor,

We are pleased to submit our manuscript entitled "[Title]" for consideration for publication in [Journal Name].

[Why this journal - 2-3 sentences] This study aligns well with [Journal]'s scope in [Area] and addresses [Topic] that would be of interest to your readership.

[Key contribution - 2-3 sentences] Our research [Main contribution] by [Method]. We found that [Key finding].

[Significance - 1-2 sentences] These findings have implications for [Implications].

We confirm that this manuscript has not been published elsewhere and is not under consideration by another journal.

Suggested reviewers:

  1. [Name], [Affiliation] - [Reason] (from journal_editor_info data)
  2. [Name], [Affiliation] - [Reason]

Thank you for your consideration.

Sincerely, [Corresponding Author]


---

### 7. Additional Considerations

#### Open Access Options
| Journal | OA Status | APC | Institutional Agreement |
|---------|-----------|-----|------------------------|
| [Journal 1] | [Yes/No] | $X,XXX | Check needed |
| [Journal 2] | [Yes/No] | $X,XXX | None |
| [Journal 3] | [Yes/No] | Free | N/A |

#### Preprint Strategy
- ✅ Recommended: [Journal] allows preprints
- Recommended server: [arXiv/SSRN/OSF Preprints]
- Timing: Just before or after submission

#### Special Issue Opportunities (from journal_special_issues)
- [Journal]: "[Topic]" (Recent themed publications found)

Prompt Template

You are an academic publishing strategy expert with access to real-time journal data
via the Journal Intelligence MCP (OpenAlex + Crossref APIs).

Please recommend suitable journals for the following research:

[Research Abstract]: {abstract}
[Field]: {field}
[Priorities]: {priorities}
[Study Type]: {study_type}

Pipeline:
1. Call journal_search_by_field(field) for initial candidates
2. Call journal_metrics for top candidates (parallel)
3. Present CP_JOURNAL_PRIORITIES checkpoint
4. Re-rank by user's priority
5. Call journal_compare(top_5) + journal_publication_trends(top_3) (parallel)
6. Present CP_JOURNAL_SELECTION checkpoint
7. For selected journal(s):
   - Call journal_editor_info for reviewer suggestions
   - Call journal_special_issues for opportunities
8. Generate full report with cover letter template

Field-Specific Major Journals (Examples)

Educational Technology/EdTech

TierJournalIF
T2Computers & Education~12
T2Internet & Higher Education~8
T3British Journal of Educational Technology~6
T3Educational Technology Research & Development~5
T3Journal of Computer Assisted Learning~5

Educational Psychology

TierJournalIF
T1Review of Educational Research~11
T2Journal of Educational Psychology~5
T3Learning and Instruction~5
T3Contemporary Educational Psychology~5

HRD/Organizational Psychology

TierJournalIF
T2Human Resource Development Quarterly~4
T2Journal of Organizational Behavior~6
T3Human Resource Development Review~5
T3Human Resource Development International~3

Related Agents

  • 18-academic-communicator: Abstract and summary writing
  • 19-peer-review-strategist: Review response
  • 13-internal-consistency-checker: Pre-submission check

References

  • VS Engine v3.0: ../../research-coordinator/core/vs-engine.md
  • Dynamic T-Score: ../../research-coordinator/core/t-score-dynamic.md
  • Creativity Mechanisms: ../../research-coordinator/references/creativity-mechanisms.md
  • Project State v4.0: ../../research-coordinator/core/project-state.md
  • Pipeline Templates v4.0: ../../research-coordinator/core/pipeline-templates.md
  • Integration Hub v4.0: ../../research-coordinator/core/integration-hub.md
  • Guided Wizard v4.0: ../../research-coordinator/core/guided-wizard.md
  • Auto-Documentation v4.0: ../../research-coordinator/core/auto-documentation.md
  • Journal Citation Reports (Clarivate)
  • Scimago Journal & Country Rank
  • DOAJ (Directory of Open Access Journals)
  • Sherpa Romeo (OA policies)
  • OpenAlex API: https://docs.openalex.org/
  • Crossref API: https://api.crossref.org/

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!