Claude Skills by brycewang-stanford

Generate a complete, manuscript-ready data profile: demographics summary table, scale identification with reliability (alpha, omega, CFA), comprehensive codebook, sample characteristics, and measurement documentation — all following current best practices at the time of execution. Searches for the latest reporting standards (JARS, TOP, APA) before generating output. Produces everything a Methods section needs to describe the data. Use when the user says "describe my data for the manuscript," ...

Run declarative data quality checks and generate a codebook. Checks completeness, distributions, impossible values, duplicates, outliers, encoding issues, attention check failures, and manipulation check results. Produces a pointblank/pandera validation report and an auto-generated codebook. Use when the user says "validate data," "check data quality," "generate codebook," "what's wrong with my data," "data audit," "check my dataset," or when /research-intake identifies missing validation. Tr...

Comprehensive exploratory data analysis with publication-quality descriptive tables, correlation matrices, distribution plots, and assumption testing. Generates a standalone EDA report with Table 1 (gtsummary/great_tables), correlation heatmap, distribution diagnostics, VIF for multicollinearity, and normality/homoscedasticity tests. All figures are APA-formatted and colorblind-safe. Use when the user says "exploratory analysis," "EDA," "descriptive statistics," "explore the data," "Table 1,"...

Implement Hayes PROCESS mediation and moderation models transparently via lavaan and bruceR, with bootstrap CIs, index of moderated mediation, Johnson-Neyman regions of significance, and APA-formatted output that matches familiar PROCESS tables. Maps model numbers (1-24) to inspectable lavaan syntax instead of black-box macros. Use when the user says "PROCESS model," "mediation," "moderated mediation," "conditional indirect effect," "Hayes model," "indirect effect," "moderation," or when /ana...

Scaffold a new research project with full reproducibility infrastructure in R and/or Python. Creates directory structure, pipeline stubs (targets/Snakemake), environment lockfiles (renv/uv), documentation templates (codebook, decision log, pre-registration, Cornell README), Quarto manuscript template, and proper .gitignore. Can wrap existing data in gold-standard structure. Use when the user says "new project," "scaffold," "start a study," "set up a project," "I have data and need to organize...

Bidirectional review — THE entry point for every research engagement. Reviews everything the researcher has (data, docs, code, instruments) and produces two outputs: (1) a gap analysis showing what their project needs to meet gold standards, and (2) suite-learning findings identifying what our skill suite can learn from what they brought. Runs at the START of every engagement and in lighter form at session END. Use when the user says "I have data," "review what I have," "where do I start," "l...

Create publication-quality figures that meet journal submission standards. APA 7th defaults with journal-specific overrides. Supports interaction plots, mediation path diagrams, forest plots, marginal effects, Johnson-Neyman plots, correlation heatmaps, and coefficient plots. All figures are colorblind-safe, high DPI, and exported in multiple formats (PDF, PNG, SVG, TIFF). Use when the user says "publication figures," "journal figures," "APA figures," "visualize results," "make plots," "inter...

Verify academic citations against CrossRef, Semantic Scholar, and OpenAlex. Detects AI-hallucinated references, chimeric citations, and suspicious patterns.

Causal inference framework for answering "does X cause Y?" beyond correlation. DoWhy (Microsoft Research) provides the identify-estimate-refute loop: define a causal graph (DAG), identify the causal effect using backdoor/frontdoor/instrumental variable criteria, estimate treatment effects with multiple estimators, and validate results with automated refutation tests. Use when: distinguishing causation from correlation, estimating treatment effects (ATE, ATT, CATE), designing and analyzing A/B...

Complete survival analysis library in Python. Handles right-censored data, Kaplan-Meier curves, and Cox regression. Standard for clinical trial analysis and epidemiology.

Design, run, and critique causal inference workflows in Stata. Use when the user is working on identification, treatment effects, DiD, IV, event studies, RD, or assumption-sensitive empirical claims.

Audit datasets for structure, missingness, labeling, suspicious values, duplicate identifiers, and documentation readiness. Use when a researcher asks for data QA, codebook review, sanity checks, or pre-analysis cleanup guidance.

Track dataset lineage, transformation steps, merge logic, and reproducibility risks in Stata workflows. Use when the user needs to explain where data came from, how it changed, or why a pipeline can be trusted.

Diagnose local Stata, MCP, package, startup, graph-export, and permissions issues. Use when setup is failing, Stata is not discovered, packages are missing, logs are truncated, or a managed machine behaves differently from a normal workstation.

List, export, and review Stata graphs from the current session.

Look up Stata command documentation and display formatted help text.

Describe and summarize the current dataset in memory. Optionally inspect a specific variable with codebook.

Run static analysis on a Stata .do or .ado file and report style and best-practice issues.

Tail, read, or search a Stata log file from a previous command or background task.

Improve, modernize, and optimize existing Stata code for performance, portability, and maintainability. Use when legacy patterns such as preserve/restore, cd, #delimit, slow aggregation, or weak fixed-effects workflows appear in code under review.

Plan and critique power, MDE, and sample-size calculations for Stata-based research workflows. Use when the user is designing a study, checking detectability, or defending precision claims.

Review regression outputs, tables, and graphs for publication readiness. Use when the user asks whether a result is ready for a paper, appendix, seminar, referee response, or coauthor review.

Organize and execute Stata workflows for referee responses, robustness requests, and coauthor follow-ups. Use when the user needs to answer a critique with targeted reruns, tables, figures, and a defensible audit trail.

Run replication, robustness, and specification-sensitivity workflows for Stata projects. Use when a researcher wants to reproduce a result, rerun a pipeline, compare specifications, audit a do-file sequence, or check whether a claim is stable.

Fetch and display stored r(), e(), and s() results from the last Stata command.

Run arbitrary Stata code or a .do file and display the result.

Install, configure, update, or verify mcp-stata across Claude Code, Codex, Gemini CLI, Cursor, Windsurf, and VS Code. Activate when users ask to set up the Stata toolkit or troubleshoot the installation.

Build and review paper-ready regression, balance, and summary tables from Stata outputs. Use when the user needs a clean table for a draft, appendix, or coauthor share-out.

Activate when users mention Stata commands, .do files, regressions, econometrics, stored results, graphs, dataset inspection, replication, or Stata errors. Route the task through mcp-stata tools and the specialized research skills instead of treating it as plain text coding.

Show mcp-stata identity, connected tools, and status. Use when the user asks if mcp-stata is available, asks about access to the toolkit, or asks what Stata tools are connected.

Generate, continue, revise, polish, and stress-test game theory research papers. Use when the user provides a game theory topic, phenomenon, draft, outline, model idea, literature anchor, reviewer comments, or asks for 博弈论论文生成, 选题建模, 文献迁移, 模型修正, 均衡分析, 数值模拟, 论文润色, 改稿打磨, or R&R response work.

R语言实证分析优化Skill。优化R代码效率、处理大规模面板数据、加速回归计算（并行化、向量化、向量化）。触发词：R语言优化/R加速/R性能优化/大规模数据处理/R optimization

学术引用核查Skill。要求每条引用必须定位到PDF原页，区分直接引用/间接引用，找不到原文则标注"待核"。触发词：引用核查/检查引用/citation check/核实文献/引用 fidelity

调查数据清洗Skill。处理调查数据（CGSS/CHIP/CSS等）时的标准化清洗流程，包括缺失值处理、变量编码统一、数据异常值检测。触发词：数据清洗/调查数据/codebook/数据清洗流程/问卷数据处理

双重差分(DID)实证审查Skill。做DID分析前必须检查平行趋势假设、画图可视化、报告违背情况。触发词：DID审查/双重差分检查/平行趋势/DiD reviewer/difference-in-differences

经济学顶刊标准审稿Skill。按AER/QJE/Econometrica/JPE顶刊标准审查论文输出（图表+回归表），列出潜在致命缺陷。触发词：顶刊审稿/论文审查/econ reviewer/经济学期刊标准/PR

苏格拉底诘问式研究选题Skill。通过连续追问帮你厘清研究思路、聚焦研究子领域、明确研究问题(RQ)，识别出未被研究过的新意选题。触发词：帮我选题/研究问题不清晰/想做一个有新意的论文/不断问我问题/厘清思路

LaTeX回归表格生成Skill。辅助生成符合AER/QJE等顶刊格式的三线表，包括标准误聚类标注、显著性星标、固定效应标注。触发词：LaTeX表格/回归表/三线表/table制作/latex table

根据研究者提供的**研究计划书（Research Proposal）**执行基于中国制度环境的公司金融类实证研究全流程。**启动后第一件事：根据计划书的主题、识别策略、贡献边际与样本范围，从中国-context 英文顶级期刊池（JF/JFE/RFS/JFQA/MS/JCF/JBF/JAR/JAE/TAR/CAR/JIBS/China Economic Review/PBFJ 等 25+ 期刊）中推荐 5 本最匹配的目标期刊（[J1]–[J5]），等待研究者明确选定一本；该期刊决定 main.tex 的 bibliographystyle、Section 骨架、Introduction 风格与表注规范**。然后用 Python 完成数据清洗、描述性统计、基准回归、内生性检验（IV/2SLS、DML）、平行趋势、异质性、机制、稳健性检验与图表绘制。LaTeX 表格和图像严格遵循 template/ 示例格式，研究逻辑与排版严格遵循 rule/ 下的《通用实证研究逻辑与规范总结》与《回归表写作规范总结》。数据集与政策集从 asset/ 中按计划书中的关键词检索。**当计划书预期的实证结...

根据研究者提供的**研究计划书（Research Proposal）**执行基于**外国（美国/欧盟/英国/日本/跨国）制度环境**的公司金融类实证研究全流程。**启动后第一件事：根据计划书的主题、识别策略、贡献边际与样本范围，从外国 CF 顶刊池（AER/QJE/JPE/JF/JFE/RFS/JFQA/JAR/JAE/MS/JCF/JBF 等 25+ 期刊）中推荐 5 本最匹配的目标期刊（[J1]–[J5]），等待研究者明确选定一本；该期刊决定 main.tex 的 bibliographystyle、Section 骨架、Introduction 风格与表注规范**。然后用 Python 完成数据清洗、描述性统计、基准回归、内生性检验（IV/2SLS、DML）、平行趋势、异质性、机制、稳健性检验与图表绘制。LaTeX 表格和图像严格遵循 template/ 示例格式，研究逻辑与排版严格遵循 rule/ 下的《通用实证研究逻辑与规范总结》与《回归表写作规范总结》。数据集与政策集从 asset/ 中按计划书中的关键词检索（WRDS / NBER/Fed releases / FR...

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Search and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read full paper content.

Upgrade of chinese-ppt for Chinese Beamer decks (xelatex + ctex + fandol, CUFE template). Same 7-section outline and X→M→Y framework, but adds (a) mandatory 1.3 line-spacing + 3pt paragraph spacing, (b) overflow-prevention line budget + balanced split-frame rules, (c) prose rewrites that strip AI-ish "关键比较/理论映射" labels and redundant 章节括号注释, (d) stricter CJK-space + middle-dot rules, (e) retrofit workflow for existing chinese-ppt decks, (f) mandatory local linespread reset inside TikZ / table ...

Convert English straight quotation marks ("...") to Chinese curved quotation marks ("..." U+201C/D). Use when processing Chinese text documents, markdown files, or any content that needs proper Chinese typography with directional quotes. Triggers on keywords like "转换引号", "中文引号", "英文引号转中文", "quote conversion", "convert quotes".

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

Clean and transform messy data for analysis in Python, R, or Stata

Fetch economic data from FRED, World Bank, BLS, OECD, and Yahoo Finance

Econometrics skill for Difference-in-Differences (DID) analysis. Activates when the user asks about: "difference in differences", "DID", "DiD", "diff-in-diff", "parallel trends", "treatment group", "control group", "pre-treatment", "post-treatment", "policy evaluation", "natural experiment", "staggered DID", "event study regression", "two-way fixed effects DID", "callaway santanna", "sun and abraham", "双重差分", "倍差法", "平行趋势", "处理组", "对照组", "政策评估", "事件研究", "交错DID", "渐进处理"

This skill should be used when the user asks to "/do-agent", asks for "Execute complex tasks using multi-agent architecture with context protection", or needs the workflow previously provided by the /do-agent slash command.

公司金融实证研究的"漏斗式选题查找器"。互动开场先后询问 (1) 研究方向、(2) 候选标题数量 N， 再扫描全球文献（已出版英文学术期刊 + SSRN working paper + 全球高校 department seminar 1 年内日程），基于 Edmans (2024) "1000 Rejections" 红线生成 N 个候选标题，**通过并行 subagent（Agent 工具）批量生成计划书 + 查新；每个 subagent 必须强制调用 Skill 工具加载 econfin-proposal 与 novelty-check 两个预设 skill 完成各自模块**，**只有当 novelty score >= 9 时（即 JF/JFE/RFS 顶刊层次），subagent 才把 proposal + 查新报告合并的 md 写入 F:\Dropbox\CC\选题大全\<研究方向短名>\（以"简短选题名称-分数"命名，子文件夹名由 Step 0 从用户输入的研究方向派生）；< 9 分的选题在 subagent 内部直接丢弃，绝不写盘、绝不输出**。当用户说"找选题"、...