AI agents adding nikud to Hebrew text often make critical errors: wrong binyan identification leads to incorrect vowel points, missing dagesh on loanwords causes mispronunciation, and over-nikuding degrades TTS quality rather than improving it.
Author: @shaharsha
Hebrew nikud (vowel points) reference for AI agents. Correct nikud rules for verb conjugations (binyanim), dagesh, gender suffixes, homographs, and common mistakes. Use before adding nikud to Hebrew text, especially for TTS.
npx skills-il add openclaw/skills/shaharsha/hebrew-nikudA reference guide for adding selective nikud to Hebrew text. Designed for AI agents that need accurate pronunciation hints (e.g., for TTS).
Only add nikud when you're 100% certain it's correct. Wrong nikud is worse than no nikud -- the TTS model will read your mistake literally instead of guessing correctly from context.
When in doubt -- don't nikud. Let the TTS model guess from context.
Covers all 13 Hebrew vowel symbols including Patach, Kamatz, Segol, Tzere, Hiriq, Holam, Kubutz, Shuruk, and Shva with detailed rules.
Detailed coverage of Begedkefet letters, dagesh lene vs forte, and common dagesh examples for TTS with focus on Pe/Fe, Bet/Vet, and Kaf/Khaf.
Complete conjugation tables for all 7 verb patterns: Pa'al, Pi'el, Hif'il, Hitpa'el, Nif'al, Pu'al, and Huf'al with common confusion warnings.
Supported Agents
I have a Hebrew paragraph that will be read aloud by a TTS engine. Add selective nikud only where pronunciation is ambiguous. Focus on dagesh in begedkefet letters, homographs, and foreign names. Do not over-nikud.
Check the nikud on these Hebrew verbs. For each verb, identify the correct binyan and verify the vowel points match the conjugation pattern. Flag any errors where the wrong binyan nikud was applied.
I have a Hebrew text containing foreign names and loanwords. Add dagesh where needed to ensure correct pronunciation (P not F, B not V, K not Kh). List each word you changed and explain why.
Trust Score
Write 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, formal vs informal register, gendered language handling, and Hebrew SEO best practices. Do NOT use for Hebrew NLP/ML tasks (use hebrew-nlp-toolkit) or translation (use a translation skill).
Process 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.
Generate 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).
Want to build your own skill? Try the Skill Creator · Submit a Skill