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 skill initializes an autonomous, scheduled loop for running complex research or engineering experiments. Users specify the target experiment and select a recurring interval (e.g., 10 minutes, daily, weekly). It utilizes cron scheduling to ensure continuous research, guiding iterative changes, evaluating metrics, and committing results automatically until manually stopped.

Geniml is a comprehensive Python package designed for applying machine learning models to genomic interval data, typically stored in BED files. It provides several unsupervised methods—including Region2Vec and BEDspace—to learn robust embeddings of genomic regions, single cells (scATAC-seq), and associated metadata. Use cases include dimensionality reduction, structural variation analysis, cell-type annotation, and cross-modal querying in genomics research.

Gtars is a high-performance toolkit written in Rust with Python bindings, designed for comprehensive analysis of genomic interval data. It provides specialized modules for overlap detection, generating coverage tracks (WIG/BigWig), tokenization for Machine Learning models, and detailed fragment analysis in single-cell genomics. Use it for robust bioinformatics pipelines and computational genomics research.

A high-performance library built on Polars for advanced genomic interval operations and bioinformatics file I/O. It provides robust support for core interval arithmetic (overlap, merge, complement) and reading/writing major formats like VCF, BAM, BED, and GFF. Features include out-of-core streaming, cloud-native I/O (S3, GCS, Azure), and a powerful SQL interface, making it ideal for large-scale genomic research.

scikit-survival is a comprehensive Python library built on scikit-learn, designed for rigorous time-to-event analysis. It specializes in handling censored data (right, left, or interval-censored) and provides multiple advanced modeling techniques, including Cox proportional hazards models, Random Survival Forests, Gradient Boosting, and Survival SVMs. Users can evaluate model performance using metrics like the Concordance Index and Brier Score, making it ideal for clinical, reliability, and survival research.

This skill utilizes the TimesFM foundation model for zero-shot forecasting of any univariate time series. It predicts future values with calibrated probabilistic intervals without requiring custom model training. It includes a mandatory preflight system checker to ensure adequate RAM, GPU, and disk resources for safe, local inference across various data types (sales, sensor, energy).

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.

This skill provides a comprehensive workflow for training advanced neural network models, including LSTM, Transformer, and N-BEATS, using historical market data. It facilitates model training, prediction generation with confidence intervals, performance comparison across different model types, and the structured storage of results for further analysis and SONA training.