Skill UI

A powerful command-line interface (CLI) tool for comprehensive management of Microsoft Word (.docx) documents. It supports the entire document lifecycle, including creating complex reports, extracting data, editing content, and modifying structural elements like headers, footers, and tables. Designed for programmatic use, it enforces professional document standards such as clear heading hierarchies and standardized formatting.

A comprehensive CLI skill for managing PowerPoint presentations (.pptx). This tool allows users to create, read, parse, edit, split, or combine slide decks programmatically. Beyond basic file manipulation, it enforces professional design standards, ensuring every output deck adheres to best practices regarding text hierarchy, visual components, and content density, making it ideal for automated report generation and pitch deck creation.

This guide provides comprehensive standards for analyzing and reporting results in Organization Science, a field characterized by diverse methodologies. It ensures methodological rigor and transparency whether the work is qualitative (establishing trustworthiness), quantitative (matching estimators to design), computational (reporting seeds and sensitivity), or formal/analytical. It emphasizes full reproducibility and mechanism-based inference.

A comprehensive guide for designing and reporting rigorous computational studies in Operations Research (OR) manuscripts. It covers best practices for selecting benchmark instances and strong baselines, applying statistical methods to stochastic output (e.g., confidence intervals), and adhering to mandatory code and data deposit standards (ORJournal workflow) to ensure full reproducibility.

A comprehensive guide for structuring academic system evaluation papers (e.g., OSDI). It dictates how to frame experiments around core research questions, select robust baselines, utilize realistic workloads (including adversarial tests), and apply rigorous measurement disciplines (e.g., reporting distributions, p99s) while maintaining conciseness within strict page limits.

A comprehensive guide for designing and auditing rigorous empirical evaluations for sensing systems, particularly Human Activity Recognition (HAR). It emphasizes best practices such as leave-one-subject-out cross-validation, using real human subjects under diverse conditions, reporting event-level metrics (e.g., Macro-F1) over raw accuracy, establishing fair baselines, and mitigating data leakage (e.g., subject or session leakage). This ensures that reported results are robust, generalizable, and defensible against academic skepticism.

Provides comprehensive guidelines for conducting highly rigorous, reproducible statistical analysis for complex survey data (e.g., weights, strata, clusters). This guide ensures that analyses meet the standards of top academic journals, emphasizing design-based inference, honest uncertainty reporting (CIs, MOE), and thorough robustness checks. Use this when you need to build a master script that regenerates every published table and figure.

This skill guides the creation of rigorous, self-contained tables and figures (exhibits) for academic journals like Public Opinion Quarterly (POQ). It ensures that all visual data accurately report design-based uncertainty, weighting adjustments, and the base N, meeting the high standards required for empirical survey research.

This guide provides a comprehensive checklist for designing, executing, and presenting empirical evidence for academic papers in Pattern Recognition and AI. It covers critical areas like establishing fair baselines, ensuring statistical rigor (mean ± std dev, significance testing), conducting sufficient ablation studies, preventing data leakage, and reporting computational costs. It helps authors make their findings withstand rigorous external review.

A comprehensive guide and fit test designed to help researchers assess whether their empirical psychology project meets the high standards of top-tier journals like Psychological Science. It evaluates key criteria including broad impact, statistical robustness, open science readiness (preregistration/data sharing), and adherence to strict format limits. Use this skill to pressure-test your idea before committing resources to data collection or analysis, guiding you toward the optimal manuscript type (e.g., Research Article vs. Registered Report).

A comprehensive skill for advanced meta-analysis in psychology, designed to assess the reliability and sources of heterogeneity. It performs moderator/subgroup analyses (meta-regression) to explain effect size variation and runs multiple publication-bias diagnostics (e.g., Funnel plot, Egger's test, p-curve, selection models). Essential for rigorous academic reporting requiring robust evidence and sensitivity checks.

A comprehensive framework for designing, auditing, and reporting empirical results in recommender systems research. It covers best practices for handling temporal splits, mitigating evaluation bias (e.g., exposure/popularity), utilizing advanced off-policy estimators (IPS, SNIPS), and structuring the critical link between offline metrics and real-world A/B test results. Essential for academic submissions.