By zhouziyue233
A comprehensive econometrics skills set for empirical study, covering the complete workflow of empirical study.
Identification Strategy Analysis. Synthesizes research question and literature review to diagnose endogeneity threats, evaluate feasible identification strategies, select the optimal one, and produce an Identification Strategy Memo.
Phase 6 Code Generation & Execution. Reads identification-memo.md, data-report.md, and model-spec.md, asks user to select software (Python / R / Stata), dispatches to the appropriate estimation skill, generates a reproducible analysis script with main regression, diagnostics, and output export, then executes and verifies results.
Phase 4 Data Preparation Pipeline. Data fetch, data clean and exploratory analysis. Produce a data report in the end.
Phase 5 Econometric Model Construction. Reads identification-memo.md and data-report.md, writes formal model specification with LaTeX equations, discusses identification assumptions and SE strategy, calls the appropriate estimation skill, and produces model-spec.md.
Publication Polish. Runs after results-analysis (Phase 7). Audits all tables and figures produced in Phases 4–7, upgrades them to top-journal standards by calling the table and figure skills.
Econometrics skill for time series analysis. Activates when the user asks about: "time series", "stationarity", "unit root test", "ADF test", "KPSS test", "ARIMA", "ARMA", "autocorrelation", "ACF", "PACF", "VAR model", "VECM", "Granger causality", "cointegration", "impulse response function", "forecast", "seasonal decomposition", "ARCH", "GARCH", "时间序列", "平稳性检验", "单位根", "自回归", "格兰杰因果", "协整", "脉冲响应", "预测", "向量自回归"
Create Beamer-style academic PPTX presentations using python-pptx. Produces publication-quality .pptx files with navy-blue Metropolis theme (16:9, frame title bars, progress bar) for conference talks, job market presentations, and seminar slides. Called by /present command.
End-to-end data pipeline for empirical research: fetch economic data from APIs (FRED, World Bank, IMF, BLS, OECD, Yahoo Finance), clean and transform raw data, construct strategy-specific variables, and validate panel structure. Use when asked to fetch data, download data, clean data, merge datasets, prepare analysis-ready data.
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"
Called by /plot to generate and upgrade econometric figures to top-journal standards.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
![]()
A comprehensive econometrics plugin for end-to-end empirical research automation — from research question scoping, literature review, and identification strategy design, through data fetching and cleaning, econometric modeling, code generation, results analysis, table and figure production, full-paper writing, and conference presentation.
# Step 1: Add the marketplace
/plugin marketplace add zhouziyue233/great-econometrics
# Step 2: Install the plugin
/plugin install econometrics@great-econometrics
git clone https://github.com/zhouziyue233/great-econometrics.git
cd great-econometrics
/plugin install .
This plugin implements a 9-phase iterative empirical research workflow targeting the standards of Top-5 economics journals (AER, QJE, JPE, ReStud, Econometrica). Each phase maps to dedicated slash commands, skills, and agents that work together under a unified system prompt in CLAUDE.md.
[Phase 1] Research Question
↕
[Phase 2] Literature Review
↕
[Phase 3] Identification Strategy
↕
[Phase 4] Data Preparation & EDA
↕
[Phase 5] Econometric Model
↕
[Phase 6] Code Execution
↕
[Phase 7] Results & Visualization
↕
[Phase 8] Robustness & Heterogeneity
↕
[Phase 9] Full Paper Writing
↕
Peer Review Response & Iteration
great-econometrics/
├── .claude-plugin/
│ ├── plugin.json # Plugin metadata
│ └── marketplace.json # Claude marketplace
├── CLAUDE.md # Agent 9-phase workflow
├── .env # Environment variables
│
├── shared/ # Cross-command reusable modules
│ ├── context-reader.md # Upstream file reading protocol (Step 0)
│ └── output-standards.md # LaTeX/figure/table formatting standards
│
├── hooks/
│ └── hooks.json # SessionStart banner + Stop phase-completion prompt
│
├── commands/ # Slash commands — one per workflow phase
│ ├── question.md # /question · Phase 1: Research question scoping
│ ├── analyze.md # /analyze · Phase 3: Identification strategy memo
│ ├── data.md # /data · Phase 4: Data fetch, clean & EDA
│ ├── model.md # /model · Phase 5: Formal model specification
│ ├── code.md # /code · Phase 6: Code generation & execution
│ ├── plot.md # /plot · Phase 7: Tables & figures
│ ├── robustness.md # /robustness· Phase 8: Robustness & hetero checks
│ ├── write.md # /write · Phase 9: Full paper drafting
│ └── present.md # /present · Beamer slides (optional, no phase number)
│
├── agents/
│ └── checker.md # Parallel robustness/heterogeneity/mechanism checks (Phase 8)
│
└── skills/ # Estimation, output & utility skills
│
├── — Causal Inference —
├── iv-estimation/ # IV / 2SLS
├── did-analysis/ # DID / TWFE, event study, staggered DID
├── rdd-analysis/ # Sharp / fuzzy RDD, bandwidth selection, validity tests
├── synthetic-control/ # Abadie SCM, augmented SCM, synthetic DID, etc
├── ml-causal/ # Causal forest (GRF), Double ML, etc
│
├── — Regression & Panel —
├── ols-regression/ # OLS, assumption tests, robust / clustered SE
├── panel-data/ # FE / RE, two-way FE, Hausman, dynamic panels (GMM)
│ └── references/
│ ├── panel-reference.md # Diagnostics: poolability, serial corr, unit roots, cointegration
│ └── panel-ldv-advanced.md # Advanced: FD estimator, conditional logit, PPML, Cox PH
├── time-series/ # ADF / KPSS, ARIMA, VAR / VECM, etc
│
├── — Output & Presentation —
├── results-analysis/ # Descriptive stats, coefficient interpretation, etc
├── table/ # Multi-model regression tables, LaTeX
├── figure/ # Event study, binscatter, RDD, density, coefplot
├── beamer-ppt/ # LaTeX Beamer slide decks for conferences & seminars
│
├── — Data & Literature —
├── data-pipeline/ # End-to-end: API fetch + clean + validate
├── literature-review/ # Phase 2: search, summarise & synthesise literature
├── scrapling/ # Web scraping toolkit for custom data collection
│
├── — Writing —
├── paper-writing/ # Full paper drafting to Top-5 journal standards
│
└── — Software Reference —
npx claudepluginhub zhouziyue233/great-econometrics --plugin econometricsComprehensive Stata reference — syntax, data management, econometrics, causal inference, graphics, Mata, and 20 community packages.
Stata statistical analysis for publication-ready sociology research. Phased workflow for DiD, IV, matching, panel methods, and more with pauses for user review.
R statistical analysis for publication-ready sociology research. Phased workflow for DiD, IV, matching, panel methods, and more with pauses for user review.
Research Agent Harness — a controlled execution environment for reproducible empirical research agents. Enforces source-of-truth files, data integrity rules, evidence trails, and human review gates across the full research lifecycle.
mcp-stata - an agentic toolkit for empirical researchers. Gives AI agents native control over a local Stata installation, allowing agents to run do-files, inspect data, check stored results, and export graphs.
PhD-level research capabilities: literature review, multi-source investigation, critical analysis, hypothesis-driven exploration, quantitative/qualitative methods, and lateral thinking