Skill UI

This guide helps authors structure and refine academic exhibits (tables and figures) for highly selective policy journals (like JPP&M). It addresses the crucial need to cater to a dual audience: methods-literate reviewers requiring technical detail (estimators, SEs, clustering) and policy practitioners needing immediate, decision-relevant magnitude (e.g., percentage points, dollars). It covers best practices for Event-Study, DiD, RDD, and forest plots, ensuring the presentation is actionable and adheres to strict page limits.

This comprehensive guide details professional standards for presenting complex empirical economic results (tables and figures) for top-tier journals like The Journal of World Economy. It instructs users on simplifying main regression tables, standardizing notes (clustering, significance), and correctly presenting specialized open-economy objects such as event studies, gravity regressions, and GVC decompositions, ensuring research meets publication quality.

A comprehensive guide for executing rigorous empirical accounting studies. This resource details best practices for advanced econometric techniques, including correct standard error clustering (firm-level, two-way clustering), executing identification strategies (DiD, RD, IV/2SLS), validating accounting constructs, and performing extensive robustness checks (falsification, placebo tests). It also emphasizes data provenance and reproducibility, critical for top-tier academic publications.

A comprehensive guide for executing and reporting complex social psychological analyses required for expert peer review. This skill covers norms for reporting uncertainty, assessing measurement quality, ensuring robustness checks, selecting appropriate statistical inference (e.g., multilevel models, clustering), and linking statistical findings back to the theoretical structure. It emphasizes methodological rigor and reproducibility.

Scanpy is a powerful, scalable Python toolkit built on AnnData for comprehensive single-cell RNA-seq data analysis. It supports the complete biological workflow, including quality control, normalization, dimensionality reduction (PCA, UMAP, t-SNE), clustering, marker gene identification, and sophisticated cell type annotation, enabling the generation of publication-quality figures.

Scikit-learn is the industry-standard Python library for classical machine learning. It provides comprehensive tools for supervised and unsupervised learning tasks, including classification, regression, clustering, and dimensionality reduction. Use it to build robust, production-ready ML pipelines, perform rigorous model evaluation, and preprocess complex datasets for various data science applications.

Train or fine-tune SentenceTransformer, CrossEncoder, and SparseEncoder models for retrieval, similarity, clustering, classification, reranking, and embedding tasks. This skill provides production-ready templates with proper loss functions, evaluators, and training configurations for various NLP tasks including bi-encoder, reranker, and sparse vector models.