Skill UI

This comprehensive tool automates the process of translating non-English official documents (images) for visa applications. It handles image preprocessing (conversion and rotation), performs robust OCR using multiple frameworks, translates the extracted text into professional English while maintaining document structure, and generates a certified bilingual PDF containing both the original image and the formatted translation.

PathML is a Python toolkit for computational pathology workflows, loading 160+ slide formats, preprocessing H&E images, constructing spatial graphs, training HoVer-Net/HACTNet models, and analyzing multiplex imaging for ML-ready pathology data.

Astropy is a core Python library for astronomy and astrophysics workflows. It provides essential functionality for astronomical research and data analysis, including coordinate transformations, unit and quantity calculations, FITS file operations, cosmological calculations, precise time handling, tabular data manipulation, and astronomical image processing. Use it for implementing or debugging astronomical data analysis code.

Build local, research-only computational pathology workflows with PathML: load and tile whole-slide images, run preprocessing and QC pipelines, manage h5path data, quantify multiplex images, construct spatial graphs, and plan bounded model inference.

This utility detects and redacts sensitive personally identifiable information (PII) from screenshots and images. It can mask various data types, including IDs, credit card numbers, API keys, phone numbers, and emails. Crucially, all processing is conducted locally and offline, ensuring that sensitive data never leaves the user's machine. It is essential for secure debugging, data sharing, and analysis workflows.

This comprehensive tool automates the process of translating non-English official documents (images) for visa applications. It handles image preprocessing (conversion and rotation), performs robust OCR using multiple frameworks, translates the extracted text into professional English while maintaining document structure, and generates a certified bilingual PDF containing both the original image and the formatted translation.

This skill provides comprehensive guidance for authors seeking to submit manuscripts to the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). It helps evaluate the fit of research in signal processing, speech, audio, and image processing. It guides the framing, required empirical evidence (mathematical models, reproducible validation), and optimal positioning of the paper to maximize acceptance chances.

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.

Extract structured tabular data from PDFs, spreadsheets, and images using layout-aware detection and configurable table models, with markdown or JSON cell output for LLM ingestion and downstream processing.

GPU-accelerated toolkit for curating LLM training data across text, image, video, and audio. Includes fuzzy and semantic deduplication, quality filtering, PII redaction, and NSFW detection.

Distributed data processing library for ML workloads with streaming execution across CPU/GPU, supporting Parquet, CSV, JSON, images, batch inference, ETL, and Ray Train/PyTorch/TensorFlow integration.