Extract text from images via OCR and save it as Markdown.
npx skills add https://github.com/sunLeee/optimization --skill ref-image-ocr
Please help me install this Agent Skill. Skill: ref-image-ocr Source: https://github.com/sunLeee/optimization/tree/main/.claude/skills/data-fetch/ref-image-ocr Command: npx skills add https://github.com/sunLeee/optimization --skill ref-image-ocr
Extract text from images using OCR and save it as a Markdown reference, enabling rapid access to textual content from diagrams, screenshots, and scanned documents.
Run the command /ref-image-ocr <image-path> to extract text from an image and save it as a Markdown reference.
High-intent search queries and answers about installing and using this skill.
To extract text from an image and save it as a Markdown file, run the /ref-image-ocr command with your image path. The tool validates the input, performs OCR, structures the content, and persists the result as a searchable MD file.
Yes, you can convert scanned documents into searchable Markdown references. The OCR process extracts text from scans and screenshots, structuring the content into a portable MD file stored under docs/references/ocr.
Image text extraction works with system architecture diagrams by converting the visual text into structured Markdown content. This enables rapid access to textual content from diagrams for searchable knowledge bases.
The best way to turn a screenshot into searchable text is using OCR to extract the content and save it as a Markdown reference. This produces a portable, searchable MD file that integrates directly into your documentation.
You do not necessarily need Tesseract to perform OCR on images. The extraction can be performed using either Claude Vision or Tesseract to process the image and convert the text into Markdown format.
tiankong0101-byteExtract text from images and scanned PDFs using PaddleOCR.
Gimpy666Convert Tribot JavaDoc HTML pages into per-class Markdown files and a consolidated reference.
JongsixGenerate technical documentation from source code and API definitions.
nadicodeaiExtract and convert PDF, scanned document, and image text to plain text or Markdown using OCR and pymupdf/marker-pdf.
