“OCR”

当遇到需要分析本地图片（如.png, .jpg，包含国际象棋、公式、表格图），或者需要依靠“视觉”去观察视频画面中的物体（例如数鸟的数量、描述某人的动作）时使用。必须调用视觉大模型充当你的眼睛进行多模态推理。

Parses items, prices, and tax from photos of printed menus or paper receipts

Tools for Agents

max124vip-dev

Decision Layer for AI Agents — 58+ tools, Advisor, MCP.

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

Auto-imported skill computer_vision_ocr_screenshot_agent

Route clipboard images, local image paths, and Markdown-embedded media through the best available image workflow.

CPFL: Download via link + OCR, official-source lookup.

Light: Download via ZIP code + OCR, official-source lookup.

Neoenergia (Elektro): Download + OCR, official-source lookup.

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.

Invoice and receipt extractor: reads PDF and image invoices/receipts with AI, pulling date…

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.

Bank statement PDF to CSV, OCR, Office to PDF, PDF to Word, any file to Markdown, merge and split.

LensaOCR

saastemly.com

Tesseract-compatible OCR over HTTP: send an image, get its text and word boxes in Tesseract's...

DevX Agent Hub

agents.madebydevx.com

x402 pay-per-call agent tools: token safety/honeypot check, speech to text, TTS, translate, OCR, web

Render Mermaid diagrams, Markdown to PDF and outlines, image OCR, and media metadata cleanup.

检查/修正某日 md 里 cls 图 OCR 自动填充的四小节(午评/午间涨停分析/收评/涨停分析)。用户下班说'检查今天md'时用。Java 定时链已自动下载+OCR+填充, 本 skill 做 AI 复核: 直接看图 vs md 小节全量比对, 错字直改, 数据以图为准覆盖, PARSE_FAIL/缺图列清单。

科研工具能力入口：文档解析、OCR、知识图谱、代码执行与数据采集。Use for research software, diagrams, scraping, notebooks, OCR, and graphs.

Live-test any Electron desktop app with native-devtools-mcp, Chrome DevTools Protocol, screenshots, OCR, and accessibility tools.

Paxa Labs

paxalabs.comOfficial

Thai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction

Change or diagnose Xberg PDF extraction, native/Pdfium backend selection, PDF rendering sessions, encrypted documents, OCR fallback, or backend-specific…