Skill UI

This skill provides comprehensive commands for creating, managing, versioning, and querying structured datasets within the Arize platform. It covers dataset CRUD operations, appending examples, and exporting data in various formats (JSON, CSV, Parquet) using the `ax` CLI. Ideal for preparing test data, generating evaluation examples, or retrieving golden datasets for LLM development and model testing.

Automates GA4 reporting and property management via Composio’s Rube MCP, covering account/property discovery, standard/batch/pivot/funnel reports, and key event workflows so analysts can run repeatable queries without manual UI steps.

A comprehensive expert prompt for evaluating Power BI data models. It guides the assessment of model architecture (Star Schema, relationships), storage optimization (Import, DirectQuery, Dual), data quality, performance scalability, and governance best practices. Use this when reviewing an existing BI model to ensure it is robust, maintainable, and highly performant.

Arboreto is a powerful Python library designed for inferring Gene Regulatory Networks (GRNs) from various gene expression datasets, including bulk and single-cell RNA-seq data. It leverages advanced machine learning algorithms like GRNBoost2 and GENIE3. The library supports scalable, distributed computation using Dask, making it ideal for analyzing large-scale, complex transcriptomics datasets to identify critical transcription factor-target gene relationships.

A powerful tool designed for systematic literature reviews and meta-analyses. It searches scientific papers and retrieves highly structured experimental data directly from the full text, going beyond mere abstracts. It extracts over 25 fields, including detailed methods, quantitative results, sample sizes, quality scores, and conclusions, enabling comprehensive evidence synthesis for academic research.

This skill automatically detects all available computational resources, including CPU core counts, GPU support (NVIDIA, AMD, Apple Silicon), memory capacity, and disk space. It generates a detailed JSON report that goes beyond simple metrics by providing strategic, context-aware recommendations. These recommendations guide users on the optimal computational approach—such as choosing between Dask for out-of-core processing, selecting the right GPU backend, or determining the ideal number of workers for parallel processing—before running any intensive scientific or data analysis task.

NetworkX is a powerful Python library designed for creating, manipulating, and analyzing complex graph and network structures. It supports core graph algorithms such as finding shortest paths, calculating centrality measures (e.g., PageRank, Betweenness), detecting communities, and generating various synthetic network models. It is indispensable for fields like social network analysis, bioinformatics, and transportation system modeling.

A comprehensive toolkit for analyzing high-density Neuropixels neural recordings. It supports the entire electrophysiology workflow, from raw data loading (SpikeGLX, Open Ephys) and preprocessing (filtering, motion correction) to advanced spike sorting (Kilosort4) and rigorous quality metric calculation. Features include Allen/IBL unit curation and AI-assisted visualization for publication-ready results.

Qiskit is a leading open-source framework for quantum computation. It enables users to build, optimize, and execute complex quantum circuits across diverse platforms, including local simulators and real IBM Quantum hardware. Ideal for implementing advanced algorithms in quantum machine learning, chemistry simulation, and combinatorial optimization.

A comprehensive skill for conducting systematic statistical hypothesis testing. It guides users through the entire data analysis lifecycle, including test selection (t-test, ANOVA, correlation, regression), rigorous assumption checking (normality, homogeneity), running advanced models (Bayesian, frequentist), calculating effect sizes, and generating publication-ready, APA-formatted reports. Ideal for academic research and quantitative analysis.

Statsmodels is a robust Python library designed for comprehensive statistical modeling and econometric analysis. It provides tools for classical linear regression (OLS), generalized linear models (GLM like Poisson and Logistic), time series forecasting (ARIMA), and mixed-effects models. Use this skill for rigorous statistical inference, detailed diagnostic testing, and generating publication-ready statistical tables.

This skill utilizes Google's TimesFM foundational model for zero-shot time series forecasting. It processes any univariate time series (e.g., sales, sensor data, weather) without requiring custom training. Users receive point forecasts alongside calibrated prediction intervals (quantiles), enabling robust probabilistic analysis. The skill includes a mandatory preflight checker to validate system resources (RAM/GPU/Disk) before model loading.