visa-doc-translate

You are assisting with the translation of documents for visa applications.

Instructions

When the user provides an image file path,AUTOMATICALLY perform the following steps,WITHOUT requesting confirmation:

1. Image Conversion: If the file is in HEIC format, use sips -s format png <input> --out <output> to convert it to PNG.

2. Image Rotation：

   • Check the EXIF orientation data.
   • Automatically rotate the image based on the EXIF data.
   • If the EXIF orientation is 6, rotate 90 degrees counterclockwise.
   • Apply additional rotation as needed (if the document appears upside down, try rotating 180 degrees).

1. OCR Text Extraction：

   • Automatically try multiple OCR methods:
     • macOS Vision framework (preferred on macOS).
     • EasyOCR (cross-platform, no tesseract required).
     • Tesseract OCR (if available).
   • Extract all text information from the document.
   • Identify the document type (bank deposit certificate, employment certificate, retirement certificate, etc.).

2. Translation：

   • Translate all text content into English at a professional level.
   • Preserve the structure and formatting of the original document.
   • Use professional terminology suitable for visa applications.
   • Keep proper nouns in the original language and note the English in parentheses.
   • For Chinese names, use the pinyin format (e.g., WU Zhengye).
   • Accurately preserve all numbers, dates, and amounts.

3. PDF Generation：

   • Create a Python script using the PIL and reportlab libraries.
   • Page 1: Display the rotated original image, centered and scaled to fit an A4 page.
   • Page 2: Display the English translation with proper formatting:
     • Title centered and bold.
     • Content left-aligned with appropriate spacing.
     • Professional layout suitable for official documents.
   • Add a note at the bottom: "This is a certified English translation of the original document".
   • Run the script to generate the PDF.

4. Output: Create a PDF file named <original_filename>_Translated.pdf in the same directory.

Supported Documents

• Bank deposit certificates
• Income certificates
• Employment certificates
• Retirement certificates
• Property certificates
• Business licenses
• ID cards and passports
• Other official documents

Technical Implementation

OCR methods (tried in order)

1. macOS Vision framework(macOS only):

   import Vision
   from Foundation import NSURL
   

2. EasyOCR(cross-platform):

   pip install easyocr
   

3. Tesseract OCR(if available):

   brew install tesseract tesseract-lang
   pip install pytesseract
   

Required Python Libraries

pip install pillow reportlab

For the macOS Vision framework:

pip install pyobjc-framework-Vision pyobjc-framework-Quartz

Important Guidelines

• Do notask the user for confirmation at every step.
• Automatically determine the best rotation angle.
• If one OCR method fails, try multiple methods.
• Ensure all numbers, dates, and amounts are accurately translated.
• Use clean, professional formatting.
• Complete the entire process and report the location of the final PDF.

Example Usage

/visa-doc-translate RetirementCertificate.PNG
/visa-doc-translate BankStatement.HEIC
/visa-doc-translate EmploymentLetter.jpg

Output Example

This Skill will:

1. Extract text using available OCR methods.
2. Translate into professional English.
3. Generate a <filename>_Translated.pdf：
   • Page 1: Original document image.
   • Page 2: Professional English translation.

Ideal for submitting visa applications to Australia, the United States, Canada, the United Kingdom, and other countries that require translated documents.