What does pdf-ocr-skill do?
A PDF OCR skill with four-engine support, capable of extracting Chinese and English text from scanned PDF files and image files.
A PDF OCR skill with four-engine support, capable of extracting Chinese and English text from scanned PDF and image files.
This skill provides a powerful PDF OCR (Optical Character Recognition) solution for developers using AI agent platforms like Claude Code, Cursor, or Codex. It supports four different OCR engines, allowing flexible and accurate text extraction from scanned PDFs (also known as 'scanned' or 'image-based' PDFs) and common image file formats (e.g., PNG, JPG). The skill is particularly useful for processing documents that do not contain selectable text, such as old books, contracts, or faxed materials. By leveraging multiple engines, it can handle a wide variety of document quality levels and multilingual text (Chinese and English). The skill is designed to be invoked via a simple API or agent tool call, returning the extracted text for further processing or analysis. It works by first detecting the file type and then applying an appropriate OCR pipeline (e.g., using Tesseract, PaddleOCR, or cloud-based services) with pre-processing steps like deskewing, thresholding, and layout analysis. This makes it an essential tool for document digitization workflows in AI-powered development environments.
npx skills add https://github.com/yejinlei/pdf-ocr-skill/tree/main/skills/pdf-ocr-skillInstalled? Explore more Image skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →
A PDF OCR skill with four-engine support, capable of extracting Chinese and English text from scanned PDF files and image files.
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Add documentation for a new AI provider — usage docs, env vars, Docker config, image resources.
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.