Skills tagged: ocr

• image2ppt - Convert slide images and PDFs into editable PowerPoint

  image2pptppt-reconstructionocrpowerpoint

  ★ 39 · Updated 2026-09-22

  Converts slide images, screenshots, scanned PDFs, and image-only PPT files into object-level editable PowerPoint presentations with visual QA.

  ⚙ Reconstruct editable PPT from images⚙ Decompose semantic page regions⚙ Reconstruct flowcharts and knowledge graphs
• azure-ai-document-intelligence-ts - Azure Document Intelligence REST SDK for TypeScript

  azuredocument-intelligencetypescriptocr

  ★ 17 · Updated 2026-09-21

  Extract text, tables, and structured data from documents using prebuilt and custom models.

  ⚙ Analyze documents with prebuilt models⚙ Extract invoice and receipt fields⚙ List document models
• pdf - PDF processing and manipulation guide

  pdftext-extractiontable-extractionocr

  ★ 16 · Updated 2026-09-20

  Provides instructions and code snippets for PDF text extraction, table parsing, merging, splitting, rotation, creation, watermarking, and OCR.

  ⚙ Extract text from PDFs⚙ Extract tables from PDFs⚙ Merge multiple PDF files
• pdf - PDF Processing and Manipulation Guide

  pdfdocument-processingpythonocr

  ★ 66 · Updated 2026-09-19

  Process PDF files including reading, extracting text and tables, merging, splitting, rotating, creating, watermarking, encrypting, and OCR.

  ⚙ Extract text from PDF files⚙ Extract tables from PDF files⚙ Merge multiple PDF files
• pdf - PDF Document Processing and Generation Guide

  pdfdocument-processingocrtext-extraction

  ★ 196 · Updated 2026-09-18

  Provides instructions and code snippets for PDF text extraction, table parsing, file merging, page rotation, creation, encryption, and OCR.

  ⚙ Extract text from PDF⚙ Extract tables from PDF⚙ Merge PDF files
• azure-ai-vision-imageanalysis-py - Azure AI Vision Image Analysis SDK for Python

  azurecomputer-visionimage-analysisocr

  ★ 0 · Updated 2026-09-17

  Python SDK for Azure AI Vision 4.0 image analysis supporting captions, tags, object detection, OCR, people detection, and smart cropping.

  ⚙ Analyze images from URLs⚙ Analyze images from files⚙ Generate image captions
• azure-ai-vision - Azure AI Vision Development and Integration Guide

  azure-ai-visionimage-analysisocrazure

  ★ 0 · Updated 2026-09-16

  Provides technical guidance for Azure AI Vision including Image Analysis, Read OCR containers, Blob Storage image access, and video frame analysis.

  ⚙ Guide Vision API version migration⚙ Configure Read OCR containers⚙ Configure Blob Storage image access
• nutrient-document-processing - Process and convert documents with Nutrient DWS API

  document-processingpdfocrconversion

  ★ 2 · Updated 2026-09-16

  Process, convert, OCR, extract data, redact, sign, and fill form documents using the Nutrient DWS API.

  ⚙ Convert document formats⚙ Extract text and tables⚙ OCR scanned documents
• mineru - Parse PDF, Office, and image files into clean Markdown.

  pdf-parserdocument-conversionmarkdownocr

  ★ 115 · Updated 2026-09-15

  Parses PDF, Office, and image files into Markdown with LaTeX formulas, tables, images, and OCR.

  ⚙ Convert documents to Markdown⚙ Extract text, tables, and formulas⚙ Perform OCR on scanned documents
• transloadit-media-processing - Transloadit Media Processing

  media-processingvideo-encodingimage-processingaudio-transcoding

  ★ 17 · Updated 2026-09-15

  Process, transform, and encode video, audio, image, and document files using Transloadit.

  ⚙ Encode video files⚙ Generate video thumbnails⚙ Resize and watermark images
• ds-vision-skill - Vision extension skill for text reasoning models

  visionocrdocument-parsingrouting

  ★ 166 · Updated 2026-09-15

  Routes image, document, and OCR tasks to specialized execution tools and returns standard JSON output for text models.

  ⚙ Route vision reasoning tasks⚙ Parse document files⚙ Perform OCR text recognition
• recipe-image-to-json - Convert recipe images into full recipe JSON format

  recipeocrimage-processingjson-parser

  ★ 0 · Updated 2026-09-15

  Reads recipe details from an image or screenshot and produces a standardized recipe JSON for app import.

  ⚙ Read recipe images using Read tool⚙ Download image files via curl⚙ Extract recipe details from pictures
• ppt-image-to-editable-ppt - Convert slide images into editable PowerPoint decks.

  pptpowerpointocrimage-to-pptx

  ★ 58 · Updated 2026-09-14

  Convert slide screenshots or exported slide images into editable PowerPoint decks with separate PNG picture objects, editable text boxes, and native shapes.

  ⚙ Extract text using PaddleOCR⚙ Extract material assets as PNGs⚙ Rebuild editable PowerPoint decks
• pdf-to-markdown - Convert PDF files to Markdown offline

  pdfmarkdownocrconverter

  ★ 0 · Updated 2026-09-12

  Converts PDF documents to Markdown offline with deterministic output, table preservation, OCR for scanned pages, and figure extraction.

  ⚙ Convert PDF to Markdown⚙ Inspect PDF for scanned pages⚙ Extract figures as PNG images
• scan-organizer - Organize and classify scanned PDFs using AI and OCR.

  pdfocrdoclingclassification

  ★ 73 · Updated 2026-09-11

  Processes scanned PDFs using Docling OCR and language models to extract text, classify content, and organize files into category subfolders.

  ⚙ Extract text from scanned PDFs⚙ Perform vision OCR on pages⚙ Classify documents by category
• pdf-reader - PDF Reader and Text Extraction Skill

  pdftext-extractionocrdocument-analysis

  ★ 2 · Updated 2026-09-11

  Reads and analyzes PDF files, extracts text by page range, and produces structured summaries with page citations.

  ⚙ Extract text from PDF files⚙ Perform OCR on scanned PDFs⚙ Clean text extraction noise
• remarkable - Access and search reMarkable tablet documents

  remarkablemcptabletnotes

  ★ 225 · Updated 2026-09-10

  Access, browse, search, and extract text or rendered pages from reMarkable tablet documents and notes.

  ⚙ Read document content and text⚙ Browse folders and filter tags⚙ Search multi-document content with OCR
• document-classification - Classification of insurance and pension documents.

  document-classificationocrinsurancepension

  ★ 0 · Updated 2026-09-10

  Classifies insurance and pension documents using OCR pipeline, taxonomy rules, and Claude Haiku model.

  ⚙ Classify insurance and pension documents⚙ Log classification decisions and metadata⚙ Flag low confidence predictions for review
• nano-pdf - Tools for PDF processing, extraction, form filling, and OCR

  pdfdocumentextractionocr

  ★ 0 · Updated 2026-09-09

  Provides tools for PDF text extraction, mining, form filling, file manipulation, and OCR integration.

  ⚙ Extract text from PDF documents⚙ Mine extracted text for patterns⚙ Fill interactive PDF forms
• reading-withholding - Withholding Tax Statement Image Reader

  withholding-taxocrpdfimage-reading

  ★ 284 · Updated 2026-09-09

  Reads withholding tax statement images and returns structured data.

  ⚙ Extract text from PDF files⚙ Convert PDF files to PNG⚙ Read tax statement images

Scroll to load more