“OCR”

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

Change or evaluate Xberg OCR backends, preprocessing, caching, page acceptance, geometry, hOCR structure, table reconstruction, or cross-backend quality.

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 text content from images using Tesseract OCR via Python

使用 OCR 全局识别 Cocos Creator 编辑器或场景截图，返回识别文本与区域坐标；用于确认 Scene、UI、层级面板等区域实际状态。仅允许访问当前 Cocos 项目内的图像与输出文件。

Extract a VIN from a photo or image URL using the CarsXE VIN OCR API.

Extract a VIN from a vehicle image URL via the CarsXE MCP tool extract_vin_from_image.

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

Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer.

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

7 ocr & translation skills.

OCR commands for extracting text from images and screenshots, with silent clipboard copy and interactive SmartBar display modes.

Use when the user wants OCR text extraction from an image file such as .png, .jpg, .jpeg, .tif, or .tiff.

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

Extract text from images using Tesseract OCR

Extract one cropped OopsNote problem image into strict OopsMark v1 OCR JSON without solving, guessing, or mixing student work into the printed question.

Extract text from PDFs, images, scans, and Word documents using Python libraries and CLI tools

Extract text from PDFs, images, scans, Word docs (Python)

Transcribing and attributing text in speech bubbles, thought bubbles and captions.

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

Run Alibaba Open Code Review as Gate 7b in the 8-gate pipeline on generated Playwright tests.

Extract text from images using the Tesseract OCR engine directly via command line.

Standardized extraction protocol for PaddleOCR-VL-1.6 generated Markdown books (files ending _by_PaddleOCR-VL-1.6.md).

Use this skill for debugging PDF transaction extraction, fixing regex patterns, and optimizing OCR (Tesseract) fallback.