visa-doc-translate

Translate visa document images to English and generate bilingual PDFs.

Updated Mar 18, 2026
One-click install
npx skills add https://github.com/freedom909/real-estate-saas --skill visa-doc-translate-freedom909
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visa-doc-translate
Source: https://github.com/freedom909/real-estate-saas/tree/main/.trae/skills/visa-doc-translate
Command: npx skills add https://github.com/freedom909/real-estate-saas --skill visa-doc-translate-freedom909

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pillow, reportlab, pyobjc-framework-Vision, pyobjc-framework-Quartz, easyocr, pytesseract.

What problem does it solve? Visa applications require certified English translations of official documents like bank statements and employment certificates, which normally means paying translation services or manually retyping content from images. ## Core Features & Use Cases - Automatic OCR: Extracts text from document images using macOS Vision, EasyOCR, or Tesseract, with automatic fallback between methods. - Bilingual PDF Generation: Produces a two-page A4 PDF with the original image on page one and a professional English translation on page two. - Image Preprocessing: Converts HEIC to PNG and applies EXIF-based rotation so documents are correctly oriented before OCR. - Use Case: You have a Chinese retirement certificate photo for an Australia visa application. Run the skill on the image and receive a translated PDF with proper names in pinyin and all dates and amounts preserved. ## Quick Start Translate the attached document image 'RetirementCertificate.PNG' into English and create a bilingual PDF for my visa application.

Frequently Asked Questions about visa-doc-translate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I translate a Chinese document image to English for a visa application?▼

Provide the image file path and the skill runs OCR to extract the text, translates it into professional English, and generates a bilingual PDF. The output PDF places the original image on page one and the translation on page two.

What OCR tools can extract text from document photos?▼

The skill tries macOS Vision framework first on macOS, then falls back to EasyOCR for cross-platform use, and finally Tesseract OCR if installed. It automatically selects whichever method is available.

Can I translate HEIC images from my iPhone?▼

Yes, HEIC files are converted to PNG using the macOS sips command before processing. EXIF orientation data is also checked so the image is rotated correctly before OCR runs.

What Python libraries are needed for OCR and PDF generation?▼

Install pillow and reportlab for image handling and PDF creation. For OCR, install pyobjc-framework-Vision and pyobjc-framework-Quartz on macOS, or easyocr, or pytesseract with the tesseract binary.

Why does OCR fail or produce wrong text on my document image?▼

OCR accuracy drops when images are rotated incorrectly, low resolution, or poorly lit. The skill mitigates this by applying EXIF rotation and trying multiple OCR engines, but very blurry scans may still require a clearer photo.