Hebrew Ocr Forms
Verified93/100Process 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 93/100 (Verified) · 216+ 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-ilPlan domestic travel in Israel with local transportation, accommodations, national parks, and cultural considerations. Use when user asks about traveling in Israel, Israeli hotel chains, bus routes, Israel Railways, Rav-Kav card, national parks, tiyul b'aretz, Dead Sea, Eilat, or trip planning within Israel. Covers Egged/Dan/Kavim buses, train schedules, Rashut HaTeva sites, Shabbat travel restrictions, and seasonal advice.
Author: skills-ilWrite and edit professional content in Hebrew including marketing copy, UX text, articles, emails, and social media posts. Use when user asks to write in Hebrew, "ktov b'ivrit", create Hebrew marketing content, edit Hebrew text, write Hebrew UX copy, or optimize Hebrew content for SEO. Covers grammar rules, register from formal to dugri, mixed Hebrew/English, gendered language, nikud and numerals, and Hebrew SEO best practices. Do NOT use for Hebrew NLP/ML tasks (use hebrew-nlp-toolkit) or translation (use a translation skill).
Author: skills-ilGenerate professional Hebrew documents including PDF, DOCX, and PPTX with full RTL support and proper Hebrew typography. Use when user asks to create Hebrew PDF, generate Israeli business documents, "lehafik heshbonit", "litstor hozeh", build Hebrew Word document, create Hebrew PowerPoint, or produce Israeli templates such as Heshbonit Mas (tax invoice), Hozeh (contract), Hatza'at Mechir (proposal), or Protokol (meeting minutes). Covers reportlab, WeasyPrint, python-docx, and pptxgenjs with bidi paragraph support. Do NOT use for OCR or reading existing documents (use hebrew-ocr-forms instead).
Use at your own risk. Terms of Use · Security
Want to build your own skill? Try the Skill Creator · Submit a Skill