Skill UI

A Python materials science library for constructing, analyzing, and converting crystal structures, computing phase diagrams and electronic properties, and integrating with the Materials Project API for high-throughput workflows.

RDKit delivers a Python-based cheminformatics toolkit for parsing SMILES/SDF, computing descriptors, generating 2D/3D coordinates, fingerprinting, searching substructures, managing reactions, and visualizing molecules, ideal for drug discovery and computational chemistry workflows.

SciPy provides open-source algorithms and utilities for scientific computing, including integration, optimization, statistics, and signal processing, enabling researchers and engineers to build reliable numerical applications.

This skill detects covert data exfiltration occurring over DNS tunnels. It analyzes DNS query names by computing Shannon entropy, examining query length distributions, and identifying high subdomain cardinality. It is essential for security operations, incident response, and proactive threat hunting when suspicious or encoded DNS activity is suspected.

Dask is a Python library for parallel and distributed computing that scales pandas, NumPy, and custom workflows beyond memory limits. It supports DataFrames, Arrays, and Bags for processing large datasets across single machines or clusters. Ideal for scientific computing, ETL tasks, and parallelizing operations when data exceeds available RAM or requires distributed execution.

This skill covers using the SHAP library to explain and audit machine learning predictions. It guides users on selecting explainers, computing feature attributions, and validating results. It includes workflows for local and global visualizations, handling multi-output models, and ensuring model behavior descriptions are accurate without implying causality. Requires Python 3.12+ and specific SHAP versions.

A comprehensive guide for achieving experimental reproducibility and verifiability in academic writing, specifically targeting top-tier journals. It covers crucial aspects like fixing computing environments, managing random seeds, ensuring data provenance, preventing data leakage, and structuring scripts for external review, transforming research rigor into actionable steps.

This skill helps authors evaluate whether their research—particularly in algorithms, optimization, or machine learning for Operations Research (OR)—meets the high computational standards required by the INFORMS Journal on Computing (IJOC). It acts as a fit/venue-selection tool, guiding authors on methodological rigor, computational evidence, and structuring their submission to maximize acceptance chances.

This guide outlines the rigorous process for estimating, validating, and interpreting structural models in Marketing Science manuscripts. It covers advanced econometric techniques (GMM, MLE, Bayesian), demonstrating empirical identification, assessing model fit (in-sample/out-of-sample), and computing robust counterfactuals. It ensures the final results are statistically sound, economically plausible, and prepared for replication.

Analyze PIV image pairs with OpenPIV: preprocessing, cross-correlation, vector validation, outlier replacement, and computing vorticity, strain rate, and turbulence statistics for fluid flow experiments.

This guide provides comprehensive standards for packaging ubiquitous computing sensing artifacts and datasets for academic publication. It covers best practices for ensuring reproducibility, emphasizing cross-subject evaluation (LOSO), necessary de-identification protocols for human-subjects data, and structuring the submission package for rigorous peer review.

A comprehensive guide for researchers in Pervasive Computing on ensuring the verifiable and reproducible nature of sensing data-driven claims. It mandates strict documentation practices covering dataset availability statements, sensing provenance (devices, labeling, preprocessing), cross-subject evaluation (LOSO), and consistency between published results and source data, adhering to ethical guidelines.