Directory · #188 trending skills repo · ↗ +98 stars this week
Auto-Empirical-Research-Skills
brycewang-stanford/Auto-Empirical-Research-Skills
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
- Stars
- 4.9k
- This week
- +98
- Forks
- 569
- Open issues
- 0
- Skills inside
- 1.3k
Get started
Install the skills
npx skills add brycewang-stanford/Auto-Empirical-Research-SkillsInstalls into Claude Code, Codex, Cursor, OpenCode and the other agents it finds on your machine.
/plugin marketplace add brycewang-stanford/Auto-Empirical-Research-SkillsRun inside Claude Code, then pick what to install from /plugin.
git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git /tmp/auto-empirical-research-skills
cp -r /tmp/auto-empirical-research-skills ~/.claude/skills/auto-empirical-research-skillsClaude Code reads ~/.claude/skills/ (or .claude/skills/ in a project). Other agents read the same SKILL.md format from their own skills folder.
Inside this repo
48 of 1262 skills
auto-empirical-research-skillsRoute empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acqui
/Full-empirical-analysis-skillClassical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest + rdrobust + econml + causalml + matplotlib/seaborn. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a plugins/empirical-analysis-python/skills/pipelineFull-empirical-analysis-skill-RClassical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest + clubSandwich + AER + ivreg + did + bacondecomp + HonestDiD + eventstudyr + rdrobust + rddensity + Synth + gsynth + synthdid + MatchIt + WeightIt plugins/empirical-analysis-r/skills/pipelineFull-empirical-analysis-skill-StataClassical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid + rdrobust + rddensity + synth + synth_runner + psmatch2 + teffects + ebalance + coefplot + esttab + asdoc + binscatter. **Defaulplugins/empirical-analysis-stata/skills/pipelineStatsPAI_skillUse when the user asks to run a full empirical / causal analysis in Python — by default in the style of an applied economics paper (AER / QJE / JPE / ReStud / AEJ) with DID / RD / IV / SCM / DML / matching, written-out estimating equation + identifying assumption, Table 1 / Table 2 / event-study figskills/00-Full-empirical-analysis-skill_StatsPAIFull-empirical-analysis-skillClassical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest + rdrobust + econml + causalml + matplotlib/seaborn. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a skills/00.1-Full-empirical-analysis-skill_PythonFull-empirical-analysis-skill-StataClassical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid + rdrobust + rddensity + synth + synth_runner + psmatch2 + teffects + ebalance + coefplot + esttab + asdoc + binscatter. **Defaulskills/00.2-Full-empirical-analysis-skill_StataFull-empirical-analysis-skill-RClassical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest + clubSandwich + AER + ivreg + did + bacondecomp + HonestDiD + eventstudyr + rdrobust + rddensity + Synth + gsynth + synthdid + MatchIt + WeightIt skills/00.3-Full-empirical-analysis-skill_Racademic-paper-composerSystematic writing framework for philosophy and interdisciplinary academic papers from optimized outline to submission-ready manuscript. Use when users want to: (1) write a paper from a detailed outline, (2) ensure quality control during writing, (3) maintain consistency across chapters, (4) prepareskills/01-lishix520-academic-paper-skills/composeracademic-paper-strategistSystematic strategic planning framework for philosophy and interdisciplinary academic papers targeting preprint platforms (PhilArchive, arXiv, PhilSci-Archive). Use when users want to: (1) plan a paper on a specific topic, (2) identify research gaps and assess originality, (3) develop optimized papeskills/01-lishix520-academic-paper-skills/strategistmedical-imaging-reviewWrite comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on topics like segmentation, detection, classification in CT, MRI, X-ray, ultrasound, or pathology imaging. Triggers on requests for "review paper", "surskills/02-luwill-research-skills/medical-imaging-reviewpaper-slide-deckGenerate professional slide deck images from academic papers and content. Creates comprehensive outlines with style instructions, auto-detects figures from PDFs, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", or "slide deck" forskills/02-luwill-research-skills/paper-slide-deckresearch-proposalGenerate academic research proposals for PhD applications. Use when user asks to "write a research proposal", "create PhD proposal", "generate research plan", "撰写研究计划", "写博士申请", "doctoral proposal", or mentions specific research topics for PhD application. Supports STEM, humanities, and social scienskills/02-luwill-research-skills/research-proposalhypothesis-generationStructured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brskills/03-K-Dense-AI-claude-scientific-skills/hypothesis-generationliterature-reviewConduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical,skills/03-K-Dense-AI-claude-scientific-skills/literature-reviewresearch-grantsWrite competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.skills/03-K-Dense-AI-claude-scientific-skills/research-grantsscientific-writingCore skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tskills/03-K-Dense-AI-claude-scientific-skills/scientific-writingcitation-managementComprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to Biskills/04-K-Dense-AI-claude-scientific-writer/citation-managementhypothesis-generationGenerate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions, propose mechanisms, for scientific inquiry across domains.skills/04-K-Dense-AI-claude-scientific-writer/hypothesis-generationliterature-reviewConduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical,skills/04-K-Dense-AI-claude-scientific-writer/literature-reviewpeer-reviewSystematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.skills/04-K-Dense-AI-claude-scientific-writer/peer-reviewresearch-grantsWrite competitive research proposals for NSF, NIH, DOE, and DARPA. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.skills/04-K-Dense-AI-claude-scientific-writer/research-grantsscholar-evaluationApply the ScholarEval framework to systematically evaluate scholarly work across quality dimensions (novelty, rigor, significance, and clarity). Use to critique academic papers, research proposals, literature reviews, or grant applications and produce a structured, criterion-based assessment.skills/04-K-Dense-AI-claude-scientific-writer/scholar-evaluationscientific-critical-thinkingEvaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.skills/04-K-Dense-AI-claude-scientific-writer/scientific-critical-thinkingscientific-writingCore skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process: (1) create section outlines with key points using research-lookup, (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/taskills/04-K-Dense-AI-claude-scientific-writer/scientific-writingGetting Started with Research SuperpowersIntroduction to literature search & review skills - systematic paper finding, screening, extraction, and citation traversalskills/05-kthorn-research-superpower/getting-startedAnswering Research QuestionsMain orchestration workflow for systematic literature research - search, evaluate, traverse, synthesizeskills/05-kthorn-research-superpower/research/answering-research-questionsBuilding Paper Screening RubricsCollaboratively build and refine paper screening rubrics through brainstorming, test-driven development, and iterative feedbackskills/05-kthorn-research-superpower/research/building-screening-rubricsChecking ChEMBL for Structured SAR DataCheck if medicinal chemistry papers are in ChEMBL database to access curated bioactivity dataskills/05-kthorn-research-superpower/research/checking-chemblCleaning Up Research SessionsSafely remove intermediate files from completed research sessions while preserving important dataskills/05-kthorn-research-superpower/research/cleaning-up-research-sessionsEvaluating Paper RelevanceTwo-stage paper screening - abstract scoring then deep dive for specific data extractionskills/05-kthorn-research-superpower/research/evaluating-paper-relevanceFinding Open Access PapersUse Unpaywall API to find free full-text versions of paywalled papersskills/05-kthorn-research-superpower/research/finding-open-access-papersSearching Scientific LiteraturePubMed search with keyword optimization, result parsing, and metadata extractionskills/05-kthorn-research-superpower/research/searching-literatureSubagent-Driven Literature ReviewUse parallel subagents for large-scale paper screening and deep dive analysisskills/05-kthorn-research-superpower/research/subagent-driven-reviewTraversing Citation NetworksSmart backward and forward citation following via Semantic Scholar, with relevance filtering and deduplicationskills/05-kthorn-research-superpower/research/traversing-citationsstat-writingEnd-to-end statistical writing assistant for LaTeX - draft title/abstract/keywords, expand outlines into sections, audit manuscripts, write reviewer reports and response letters, and scaffold book manuscripts.skills/06-fuhaoda-stats-paper-writing/stat-writingacademic-plottingGenerates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via skills/07-Orchestra-Research-AI-Research-SKILLs/academic-plottingautoresearchOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for executiskills/07-Orchestra-Research-AI-Research-SKILLs/autoresearch-skillml-paper-writingWrite publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citatioskills/07-Orchestra-Research-AI-Research-SKILLs/ml-paper-writinglatex-documentUniversal LaTeX document skill: create, compile, and convert any document to professional PDF with PNG previews. Supports resumes, reports, cover letters, invoices, academic papers, theses/dissertations, academic CVs, presentations (Beamer), scientific posters, formal letters, exams/quizzes, books, skills/08-ndpvt-web-latex-document-skillpython-panel-dataPanel data analysis with Python using linearmodels and pandas.skills/09-meleantonio-awesome-econ-ai-stuff/_skills/analysis/python-panel-datar-econometricsRun IV, DiD, and RDD analyses in R with proper diagnosticsskills/09-meleantonio-awesome-econ-ai-stuff/_skills/analysis/r-econometricsstata-regressionRun regression analyses in Stata with publication-ready output tables.skills/09-meleantonio-awesome-econ-ai-stuff/_skills/analysis/stata-regressionbeamer-presentationCreate academic presentations in Beamer with professional themesskills/09-meleantonio-awesome-econ-ai-stuff/_skills/communication/beamer-presentationecon-visualizationCreate publication-quality charts and graphs for economics papers.skills/09-meleantonio-awesome-econ-ai-stuff/_skills/communication/econ-visualizationapi-data-fetcherFetch economic data from FRED, World Bank, and other APIsskills/09-meleantonio-awesome-econ-ai-stuff/_skills/data/api-data-fetcherstata-data-cleaningClean and transform messy data in Stata with reproducible workflowsskills/09-meleantonio-awesome-econ-ai-stuff/_skills/data/stata-data-cleaningcode-simplifierSimplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.skills/09-meleantonio-awesome-econ-ai-stuff/_skills/engineering/code-simplifierDocumentation
README
Auto-Empirical Research Skills (AERS)
🔥 力荐 · StatsPAI — Stata 与 R 的 Python 平替，为 AI Agent 而生
- 🔁 Stata / R 平替：
reghdfe、csdid、rdrobust、synth、fixest、did等常用命令在 Python 中一站式替代，一个import statspai as sp搞定 DID / RD / IV / SCM / DML / matching- 🤖 面向 Agent 设计：结构化结果对象 + 内置 MCP Server，Claude / Codex 等智能体可直接调用、诊断、审计与出表
- ⚡ 运行速度更快：无需启动 Stata / R 会话，免许可证，纯 Python 流水线端到端提速
- 🏛️ 同一团队维护：StatsPAI 与 AERS 由同一团队（Stanford REAP）开发和持续维护，两者深度集成、同步迭代
github.com/brycewang-stanford/StatsPAI ·
pip install statspai· MIT 开源 · 欢迎 ⭐ Star
🌐 语言: English | 简体中文（默认） | 繁體中文 | 日本語 | 한국어
|
|
Stanford REAP × StatsPAI · 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
🚀 New here? Open the Skill Search → to filter all 1,151 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 + 78 行总表），每个合集的完整描述见
docs/CONTENT_ZH.md。📖 English readers: seeREADME-en.md.
信任面 · Trust surface (rigor stats)
| Rigor lane | Count | Where |
|---|---|---|
| Numeric benchmark tasks — gold values recomputed from real data each run | 19 | benchmark/ |
| Behavioral eval scenarios / rubric items | 42 / 217 | eval-harness/ |
| 其中已证明能区分对错的场景（pass/fail 双 fixture 自检） | 9（全部 6 个 critical 场景在内） | eval-harness/fixtures/ |
Full trust overview:
docs/TRUST.md·docs/RIGOR_COVERAGE.md🏁 带上你自己的 agent 来考同一份卷子：
pip install -e .后用aers-score给自己打分，成绩发布在docs/EXTERNAL_SCOREBOARD.md（规则见docs/SCOREBOARD_RULES.md）。榜上的数字是我们用同一套评分器重算出来的，不是提交者自报的。
⚡ 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 ~/.agents/skills/，老版本 ~/.codex/skills/） |
已经 clone / 下载到本地？ 把 Auto-Empirical-Research-Skills 文件夹的本地路径复制给 Agent，让它读 INSTALL.md 自己装：
帮我安装这个本地 skills 包：/Users/你的用户名/Downloads/Auto-Empirical-Research-Skills
我用的是 Codex（或 Claude Code / WorkBuddy），装到全局，所有项目都能用。
请先读这个文件夹里的 INSTALL.md，按我这个软件的方式装好；装完告诉我装到了哪个目录、怎么确认已经生效。
复制路径：macOS 在访达选中文件夹按
Option + Command + C；Windows 按住Shift右键 →「复制为路径」；或者直接把文件夹拖进 Agent 输入框。详细步骤见INSTALL.md方法 0。
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 安装见方法 2C、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、78 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 78 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
🎼 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：
- ⭐ 00 StatsPAI →
sp.csdid(...)给出 CS-DID 估计草案 + 写出估计方程与识别假设 - 33 claude-scholar → 抓变量定义 / 数据源候选 / 相关文献
- ⭐ 00 StatsPAI → 真跑
sp.feols(...)+sp.honest_did(...) - 41 sewage-econometrics-check → 10 项复现包审计 + 稳健性体检
- ⭐ 00 StatsPAI + 07 AI-Research-SKILLs → 出 Table 1–5 + 期刊级图
- 38 academic-proofreader → 通读 + §comment 标"审稿人会挑刺的位置"
- 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 × StatsPAI 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 + 去水印层（Turnitin AI / GPTZero / 知网 / 万方 · 隐藏字符 / C2PA / docx 元数据）；2026-10 对照 GitHub 星数前十的去 AI 味 skill 升级：英 30 + 中 28 类模式、只诊断 / 编辑 / 作者重述三种模式、aigc_audit.py 保真闸门 |
| 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 78 行合集目录
↴ 直跳到下方 78 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。
🧰 78 个核心 Skills 合集一览（00 → 74，编号连续无空缺）
打开仓库 → 看见整座库。 全部 78 个合集 · 1,151 个 skill，每一个都已 vendor 进本仓库，由
catalog/skills.json跟踪。⭐ = Stanford REAP × StatsPAI 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 |
|---|---|---|---|---|
| ⭐ 00 | StatsPAI 🔥 | 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 |
| ⭐ 00.1 | Full Empirical · Python 📘 | 显式栈：pandas · statsmodels · linearmodels · pyfixest |
→ | ⭐ 本仓库 |
| ⭐ 00.2 | Full Empirical · Stata 📊 | reghdfe · ivreg2 · csdid · sdid · rdrobust 复现包 |
→ | ⭐ 本仓库 |
| ⭐ 00.3 | Full Empirical · R 📗 | tidyverse · fixest · did · HonestDiD + Quarto 渲染 |
→ | ⭐ 本仓库 |
| 01 | academic-paper-skills | 大纲 → 手稿写作 + 7 维审稿人模拟 | → | lishix520/academic-paper-skills |
| 02 | research-skills | 医学影像综述、提案、论文转幻灯片 | → | luwill/research-skills |
| 03 | scientific-skills | 假设生成 + 28 个科学数据库 | → | K-Dense-AI/claude-scientific-skills |
| 04 | scientific-writer | 引用管理 + 科学写作 | → | K-Dense-AI/claude-scientific-writer |
| 05 | research-superpower | 系统化检索、筛选与引文溯源 | → | kthorn/research-superpower |
| 06 | stats-paper-writing | 端到端 LaTeX 统计论文写作 | → | fuhaoda/stats-paper-writing-agent-skills |
| 07 | AI-Research-SKILLs | 发表级 ML 图表、LaTeX、引文核验 | → | Orchestra-Research/AI-Research-SKILLs |
| 08 | latex-document-skill | 创建 / 编译任意 LaTeX 文档为 PDF | → | ndpvt-web/latex-document-skill |
| 09 | awesome-econ-ai | Python 面板数据分析（linearmodels） |
→ | meleantonio/awesome-econ-ai-stuff |
| 10 | causal-inference-mixtape | DID / IV / RDD / SCM 模板（Cunningham） | → | Jill0099/causal-inference-mixtape |
| 11 | compound-science | 面向定量社会科学的贝叶斯估计 | → | James-Traina/compound-science |
| 12 | claude-code-my-workflow | 提交 → PR → 合并的研究工作流（Emory） | → | pedrohcgs/claude-code-my-workflow |
| 13 | MixtapeTools | Cunningham 的因果推断工具集与讲义 | → | scunning1975/MixtapeTools |
| 14 | research-starter | R 中的 IV / DiD / RDD，含完整诊断 | → | luischanci/claude-code-research-starter |
| 15 | social-science-research | R 或 Python 端到端数据分析 | → | Felpix-Studios/social-science-research |
| 16 | clo-author | 多代理数据分析（R / Stata / Python） | → | hsantanna88/clo-author |
| 17 | DAAF | 安全意识代理框架（32 条 deny rule） | → | DAAF-Contribution-Community/daaf |
| 18 | stata-accounting | 来自 126 篇 JAR 论文的实测 Stata 范式 | → | jusi-aalto/stata-accounting-research |
| 19 | vera-economic-intelligence | 经济情报 / 政策研究情报工作流 | → |
…
Releases