Skill UI

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 module converts diverse clinical inputs—including scanned images, faxes, CSV/TSV exports, and C-CDA XML—into a normalized, clean text format (`ExtractedDocument`). It supports on-device OCR (Tesseract/PaddleOCR) and structured redaction for tables. It is the crucial first stage for feeding de-identification and Named Entity Recognition (NER) pipelines.

Extract text from scanned PDFs, photos, screenshots, and images without a text layer using the xberg CLI. Covers OCR backends (Tesseract, PaddleOCR, VLM), language packs, force-OCR, batch runs, and performance tuning.

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.