mcpField
O
ocr

ocr

github.com/byzhangkuiDocuments046 installsUpdated 37w ago
Repository

About ocr

This skill runs OCR on screenshots in `output/captures/` and displays the extracted text, for workflows that need text from images.

Key features

  1. 01Run OCR on screenshots
  2. 02Write extracted text to a file
  3. 03Display the result

Use cases

  1. 01Extract text from screenshots
  2. 02Review OCR output

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/byzhangkui/video-processing-hub --skill ocr

After installing, type/ocrin Claude Code to confirm it loaded.

Details

From the project README

对 output/captures/ 中的截图运行 OCR，提取文字内容。

执行以下命令：

source .venv/bin/activate && python pipeline.py ocr --input-dir output/captures --output output/extracted_text.txt

完成后读取 output/extracted_text.txt，将内容展示给用户。

Comments

Markdown supported