Skill UI

This skill builds and executes automated pipelines to clean, validate, and transform data for machine learning, covering ETL workflows, error handling, and quality reporting so Claude can deliver analysis-ready datasets.

Guides a Power BI DAX expert through performance, readability, best-practice, and maintainability reviews; recommends variable reuse, context tuning, and error handling; then outputs an optimized formula plus justification for analytics models.

Provides a comprehensive checklist for deploying Hex data analytics integrations into production. It covers critical operational best practices, including API key management, rate limit handling, error resilience (circuit breakers, exponential backoff), and robust monitoring strategies. This guide ensures that data pipelines are deployed reliably, minimizing downtime and guaranteeing consistent, high-quality data reporting for go-live scenarios.

A detailed guide for scrutinizing statistical inference in high-level econometric manuscripts, designed to withstand rigorous technical peer review. It covers critical areas such as selecting appropriate clustering levels, handling weak instrumental variables (IV), correcting for multiple hypothesis testing, and ensuring accurate standard error reporting for panel data and causal inference models.

A comprehensive guide for conducting rigorous empirical analysis on field and survey data in low- and middle-income settings. It covers advanced methods for handling clustered sampling, measurement error, differential attrition, and treatment-effect heterogeneity, ensuring results meet the high standards of reproducibility and robustness required by leading developmental economics journals.

A comprehensive guide for designing and stress-testing asset-pricing empirical models, tailored for submissions to top-tier finance journals. Covers methodologies like Fama–MacBeth regressions, factor model comparisons, handling standard-error subtleties, and rigorous out-of-sample validation. Essential for ensuring results survive academic scrutiny, addressing issues like multiple testing and economic magnitude.

This comprehensive guide assists in executing and documenting rigorous empirical finance research, tailored for top-tier journals like JFQA. It covers the entire pipeline, including complex financial data construction (CRSP, Compustat), advanced data cleaning (winsorizing, outlier handling), and sophisticated econometrics (fixed effects, clustered standard errors, Fama-MacBeth). The core focus is achieving absolute reproducibility, ensuring that all filters, robustness checks, and analytical steps are meticulously documented for archival and peer review.

A comprehensive guide for conducting reproducible empirical analysis in labor economics, adhering to high academic standards (e.g., JOLE norms). It covers essential steps including sample construction from CPS/ACS/registers, advanced wage decompositions (Oaxaca/RIF), proper handling of standard errors, and robust sensitivity checks to ensure results are fully replicable.

This comprehensive guide details advanced econometric methodologies required for rigorous causal inference studies. It covers how to defend both the causal identification strategy (DiD, RD, IV) and the quality of variables (handling measurement error, index construction). Learn to meet the stringent standards of top-tier journals by applying techniques like staggered DiD estimators, density testing, and attenuation correction.