Skill UI

Enables Claude to analyze historical time series patterns, select the best forecasting model, and predict future values with confidence intervals for sales, traffic, or other time-dependent metrics.

High-performance Rust toolkit with Python bindings for genomic interval analysis, covering overlap detection, coverage track generation, ML tokenization, reference sequence handling, fragment processing, and scoring workflows for sequencing datasets.

This skill provides zero-shot time series forecasting using Google's TimesFM foundation model. It forecasts any univariate time series (like sales, sensor data, or weather) without requiring custom model training. The model delivers point forecasts along with calibrated prediction intervals (quantiles), offering a robust and probabilistic view of future trends. It is ideal for rapid, reliable forecasting across diverse time-based datasets.

This tool provides comprehensive network traffic analysis capabilities by querying the Arkime API. Users can search sessions, download PCAPs for forensics, detect sophisticated threats like C2 beaconing (via jitter/interval analysis), spot DNS tunneling patterns, and flag connections to known-bad TLS certificate issuers. Ideal for security assessment and incident investigation.

Geniml validates genomic interval workflows, BED files, and model compatibility for ML/statistical analysis. Plan Region2Vec/scEmbed runs, inspect tokenizers, and assess consensus universes locally without network requests. Requires Python 3.10+ and uv for reproducible bioinformatics ML pipelines.

Gtars offers local genomic interval models, set algebra, overlap/count operations, consensus and coverage, tokenization, fragment processing, and refget/BEDbase planning across Python, Rust, and CLI.

Build or audit reproducible research workflows with NeuroKit2 for physiological time-series: preprocessing, event/interval analysis, multimodal alignment, variability and complexity on ECG, RSP and EDA signals.

High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Supports overlap, nearest, merge, coverage, complement and subtract for BED/VCF/BAM/GFF files, with streaming and cloud-native access as a faster bioframe alternative.

Utilize Google's TimesFM foundation model for zero-shot univariate time series forecasting without training custom models. Supports sales, sensor, and weather data with point forecasts and prediction intervals. Includes mandatory system checks for RAM and GPU before inference to prevent crashes.

This skill automatically processes MP4 videos by extracting key frames at configurable intervals. It then applies Tesseract OCR to recognize text on these frames, generating a comprehensive, structured Markdown report. The report includes full video metadata and timestamped, searchable transcripts, making it ideal for analyzing lectures, presentations, or screencasts programmatically.

A comprehensive tool for training and evaluating advanced neural network models (including LSTM, Transformer, and N-BEATS) on time-series market data. It facilitates the prediction of financial trends, generating results with confidence intervals, and comparing performance across multiple architectures. Ideal for quantitative trading research and financial forecasting.

A comprehensive guide for formatting and presenting empirical results (tables and figures) for submission to the American Economic Journal: Applied Economics (AEJ: Applied). It ensures that main causal estimates are immediately legible to referees by adhering to rigorous academic standards, including presenting standard errors, confidence intervals, and specific exhibit structures like event-study plots and balance tables.