Skill UI

A comprehensive guide for building and strengthening the conceptual or theoretical framework for academic manuscripts, particularly for submission to top-tier journals like AERJ. It teaches researchers how to ensure that theory drives the entire study—from question generation and design choices to data analysis and interpretation—transforming findings from mere reports into genuine theoretical contributions.

This comprehensive checklist guides authors through the final pre-submission review process for demanding academic journals. It ensures the manuscript is scientifically rigorous and complete, focusing on critical areas such as model-driven theoretical advancement, model comparison, data reproducibility (depositing code and verifying fit regeneration), and adherence to open science mandates. Use this guide before uploading to the journal's portal.

Provides stringent guidelines for formatting tables and figures in high-level economics and finance manuscripts. Covers mandatory three-line table styles, column count limits, rigorous variable definition requirements (including naming specific databases), data source transparency, and professional figure generation techniques (e.g., 300 dpi, proper event study plots).

This router guides authors through the entire lifecycle of a manuscript targeting the Journal of Econometrics (JoE). It diagnoses the current bottleneck—from initial idea generation and methodological positioning to data analysis, writing, and final submission/rebuttal—and recommends the precise specialized skill to invoke next, ensuring the work meets the high standards of econometric theory and evidence.

An essential orchestrator for academic manuscripts submitting to specialized journals. This router guides authors through the entire publishing lifecycle—from initial idea generation and literature positioning to final submission and rebuttal. It assesses the article's scope (Research Article vs. Short Article), manages page limitations, and ensures early focus on data replicability, directing users to the precise sub-skill needed at any stage.

This guide details the methodology for packaging scientific artifacts (code, solvers, data, logs) for machine learning submissions. It focuses on creating double-blind, self-contained ZIP archives that allow reviewers to independently and quickly verify complex probabilistic claims, even under strict time constraints. It covers best practices for anonymity, structured README generation, and handling data/licensing.