Hebrew Nlp Toolkit
Verified93/100Guide 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.
Trust score 93/100 (Verified) · 1,059+ installs · 2 GitHub contributors · MIT license
Natural language processing for Hebrew remains a significant technical challenge. Hebrew is a morphologically rich language with unvocalized script, making tasks like entity extraction, sentiment analysis, and part-of-speech tagging far more complex than in English. Available models are scattered and not always well documented.
skills-ilnpx skills-il add skills-il/localization@v1.2.0-hebrew-nlp-toolkit --skill hebrew-nlp-toolkit -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
- When tokenizing and morphologically processing Hebrew text
- When performing Named Entity Recognition (NER) on Hebrew to extract names, places, organizations
- When using Hebrew BERT models like DictaBERT or AlephBERT for embeddings
- When restoring nikud (diacritization) to unvocalized Hebrew text with Dicta Nakdan
- When handling Hebrew morphology challenges (binyanim, inflections, smichut)
Try These Prompts
How do I use DictaBERT for sentiment analysis of Hebrew texts? Provide a complete Python code example.
How do I perform named entity recognition (NER) in Hebrew using DictaBERT NER? I want to identify people, places, and organizations in text.
How do I restore nikud (diacritization) to unvocalized Hebrew text? Show me both the Dicta Nakdan model and the hosted API option.
What are the best ivrit.ai tools for Hebrew speech-to-text conversion? How do I integrate them into a Python project?
Frequently Asked Questions
Changelog
Added nikud restoration, hosted Dicta APIs and alternative frameworks; corrected the DictaLM 3.0 base-model lineage and tech-report link.
May 14, 2026
Corrected DictaLM 3.0 sizes (24B, 12B Nemotron, 1.7B), verified HuggingFace model IDs, fixed VRAM requirements, added Reference Links section, and included NeoDictaBERT bilingual embeddings.
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-ilImplement Israeli web accessibility compliance per IS 5568 standard, anchored to WCAG 2.0 AA (IS 5568 adds some 2.1-aligned criteria; sources differ), for Hebrew RTL applications. Use when user asks about Israeli accessibility law, "negishot" (accessibility), IS 5568, "teken negishot" (accessibility standard), "nachim" (disabilities), who is exempt from website accessibility, enforcement and penalties, the accessibility coordinator role, Hebrew screen reader support, RTL ARIA patterns, or accessibility audit for Israeli websites. Covers mandatory legal requirements under the Equal Rights for Persons with Disabilities Act, revenue-based exemption tiers, the two enforcement tracks (civil damages and the Commission administrative penalty) and the 60-day cure period, the accessibility coordinator role, Hebrew screen reader compatibility, and RTL-specific ARIA patterns. Do NOT use for general WCAG guidance without Israeli context (use standard a11y resources instead).
Use at your own risk. Terms of Use · Security
Want to build your own skill? Try the Skill Creator · Submit a Skill