Hebrew Ocr Forms
Verified92/100Process and extract data from scanned Israeli government forms using OCR. Supports Tabu (land registry), Tax Authority forms, Bituach Leumi documents, and other official Israeli paperwork. Use when user asks to OCR Hebrew documents, extract data from Israeli forms, "lesarek tofes", parse Tabu extract, read scanned tax form, or process Israeli government documents. Includes Hebrew OCR configuration, field extraction patterns, and RTL text handling. Do NOT use for handwritten Hebrew recognition (requires specialized models) or non-Israeli form processing.
Trust score 92/100 (Verified) · 160+ installs · 2 GitHub contributors · MIT license
Israeli government forms still arrive in large volumes as scans and unstructured PDFs, with handwriting, stamps, and dense Hebrew text. Standard OCR tools struggle with Hebrew due to script direction, similar-looking characters, and low-quality scans. The result is hours of manual data entry and frequent errors.
skills-ilnpx skills-il add skills-il/localization@v1.2.0-hebrew-ocr-forms --skill hebrew-ocr-forms -a claude-codeInstall on Claude.ai, Claude Desktop, ChatGPT, Manus, or other platforms
- 1. Click "Download ZIP" to download the skill files.
- 2. Open Claude Desktop and go to Customize > Skills.
- 3. Click "+" and select "Upload a skill", then upload the ZIP file.
- 4. Start a new conversation. The skill will activate automatically when relevant.
When to Apply
- Extracting data from scanned Israeli forms (Tabu extract, Tofes 106, ishur nikui)
- Batch-processing PDFs or images of Hebrew government documents, including multi-page PDFs
- Detecting TIN, Israeli ID (teudat zehut), or gush/chelka from printed text
- Choosing a Hebrew OCR engine (local Tesseract vs a cloud Vision API vs Claude Vision)
- Validating extracted fields (Israeli ID check digit, date format)
Try These Prompts
How do I scan an income tax form 106 and extract its data: salary, withheld tax, and deductions, into a JSON structure?
How do I extract data from a scanned Tabu (land registry) document? I need to retrieve property owners, block and parcel numbers, liens, and registrations.
How do I validate that a scanned government document (such as an ID card or business license) is authentic and that the extracted data is accurate?
Frequently Asked Questions
Changelog
Updated the Claude Vision model, wired the previously dead contrast-enhance flag, and added final-form letter, nikud, digit-order and multi-page PDF handling.
May 14, 2026
Added OCR engine comparison (Tesseract vs Google Cloud Vision, AWS Textract, Azure Read, Claude Vision) and Reference Links. Added enriched content.
Apr 14, 2026
Related Skills
Author: skills-ilImplement comprehensive Hebrew internationalization (i18n) patterns for web and mobile applications. Use when user asks about Hebrew localization, "beinle'umiyut", i18n for Israeli apps, Hebrew plural forms, Hebrew date formatting, RTL CSS logical properties, bidirectional text handling, React/Vue/Angular/Next.js RTL integration, Tailwind CSS RTL, or next-intl setup. Covers Hebrew pluralization rules, date and number formatting for Israel, RTL-first CSS, Tailwind RTL utilities, and bidi text algorithms. Do NOT use for NLP or content writing (use hebrew-nlp-toolkit or hebrew-content-writer instead).
Author: skills-ilComprehensive guide to finding rental apartments in Israel through Yad2, Madlan, Facebook groups, and real estate agents. Use when relocating to Israel, searching for a rental apartment, negotiating with landlords, or navigating broker fees and lease agreements. Covers 2026 market prices by city, Hebrew listing terminology, viewing checklists, required documents, and neighborhood evaluation criteria. Do NOT use for purchasing property or commercial real estate.
Author: skills-ilGuide developers in using Hebrew NLP models and tools including DictaLM, DictaBERT, AlephBERT, and ivrit.ai. Use when user asks about Hebrew text processing, Hebrew NLP, "ivrit", Hebrew tokenization, Hebrew NER, Hebrew sentiment analysis, Hebrew speech-to-text, or needs to process Hebrew language text programmatically. Covers model selection, preprocessing, and Hebrew-specific NLP challenges. Do NOT use for Arabic NLP (different tools) or general English NLP tasks.
Use at your own risk. Terms of Use · Security
Want to build your own skill? Try the Skill Creator · Submit a Skill