“OCR”

Extract text from an image using the on-device OCR model via the zettos-ai engine (private/offline).

ローカル Tesseract OCR でスクリーンショット画像群を Markdown に文字起こしする。Playwright による自動スクショ取得も可能。社外秘ドキュメントを外部 API に出さずに処理したいときに使う。

Extract and verify OCR text from images, screenshots, scanned pages, PDFs, Korean or mixed Korean-English UI captures, receipts, signs, ebook captures…

Use this whenever the user has scanned records, images, PDFs, OCR text, raw clinical documents, or asks to extract text before cleaning.

Extract text from images using Tesseract.js OCR (100% local, no API key required).

Extract visible text from local video files by sampling frames and running OCR via a local multimodal LLM.

Search traceable academic papers, download legally accessible PDFs from arXiv and open-access sources, convert PDFs or page images to Markdown with a…

截图 OCR 识别工具。截图→自动识别文字→复制/保存，适合提取图片内容、表格数据、验证码。

Extract text from PDFs and scanned documents.

Extract text from PDFs and scanned documents.

Handle cathlab surgery schedule input (images, Word docs, or mixed multi-file).

Auto-imported skill computer_vision_ocr_screenshot_agent

用 OCR 技术识别增值税发票图片并导出到 Excel，支持批量处理和翻译。当用户提到发票识别、增值税发票 OCR、电子发票识别、发票汇总时使用。

Extract text from PDFs and scanned documents.

Extract text from PDFs and scanned documents.

Capture or refresh the desktop_markdown_sync fixture set for KDE virtual desktops.

读取、OCR、创建、设计排版、转换和处理 PDF。支持本地文件与 HTTPS PDF、扫描件和任务图像，以原生文本提取及本地 OCR 为主，模型辅助疑难复核；提供 HTML/CSS 出版排版、文本生成、Office/LaTeX 导出、表单、页面与元数据操作。用户要求阅读或总结…

律师助理与法律助手在处理繁杂法条时，当需要将 PDF/Word/TXT 格式的法律规范文件转为结构化 Markdown 时适用。自动完成 OCR 解析、法律层级识别与三阶段保真校验，一键生成排版完美的法条 Markdown 文档及审核报告，让法律文本数字化工作事半功倍。

Analyze images using GPT-4 Vision for detailed description, OCR text extraction, object recognition, and visual Q&A.

Analyze images using Dashscope (Qwen) Vision models for detailed description, OCR text extraction, object recognition, and visual Q&A.

PDF processing: read, extract text/tables, merge, split, fill forms, OCR scanned PDFs.

Convert PDFs to Markdown with Mistral OCR and extracted images.

FastAPI and clean architecture study assistant backed by a public-safe ontology and knowledge graph extracted from verified OCR notes.

Modern Java study assistant backed by a public-safe graph extracted from private OCR-derived notes.