メニュー
Extract text and structure from scans, images, and scanned PDFs. Use for OCR, searchable PDFs, table extraction, receipt parsing, and business card parsing.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | ocr-document-processor |
| description | Extract text and structure from scans, images, and scanned PDFs. Use for OCR, searchable PDFs, table extraction, receipt parsing, and business card parsing. |
Handle OCR-heavy inputs where text must be recovered from images or scanned pages.
scripts/ocr_processor.py for core OCR tasks.scripts/business_card_scanner.pyscripts/receipt_scanner.pydocument-converter-suite instead of OCR by default.Run multi-indicator technical analysis on crypto or market OHLCV data. Use for deterministic trend, momentum, volume, and divergence analysis.
Analyze datasets and turn them into narrative reports with charts, audits, comparisons, and statistical summaries. Use for exploratory analysis and executive-ready outputs.
Convert PDFs, Office docs, markdown, HTML, and tables between editable formats. Use for best-effort document conversion, PDF utilities, form filling, and table extraction.
Run loan, investment, NPV, retirement, savings, and risk calculations with schedules and charts. Use for deterministic financial modeling tasks.
Parse, convert, geocode, visualize, and measure geographic data. Use for address cleanup, geo file conversion, mapping, and distance workflows.
Process images for cleanup, conversion, metadata, comparison, icons, palettes, collages, and sprite sheets. Use for single-image or batch image workflows.