whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
sentencepiece
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
ocr-document-processor
Extract text from images and scanned PDFs using OCR. Supports 100+ languages, table detection, structured output (markdown/JSON), and batch processing.
translation
Translate text between languages while preserving meaning and context
language-tutor
Teach languages with lessons, practice exercises, and conversation practice
skill-creator
Create/improve self-healing Claude Code skills with Knowledge Framework and version tracking. Use when user says "create skill", "improve skill", "update skill", "fix skill error", "создай скил", "улучши скил", or works with SKILL.md and SKILL_RELEASE_LOG.md files.
tomique-linkedin-copywriter
Create engaging LinkedIn posts in Tomáš Vince's personal writing style for Cloud Architecture, IoT, AI automation topics. Supports Slovak and English, converts article URLs or experiences into professional, human-sounding posts with hooks, insights, and CTAs. Use when creating LinkedIn content that sounds authentic, motivational, and thought-leadership oriented.
chinese-output
在输出包含中文字符与中文标点符号、编写中文文档、根据中文文档生成中文的交互回应、回复用户用中文提出的问题或任务、需要进行中文与非中文混排操作等涉及中文文字与标点符号的使用的场景中，必须使用本 Skill 以获得专业的中文字符的操作指导与行为规范引导。
writing-assistant
Refine texts in any language: perfect grammar and spelling, paraphrase ideas, avoid AI detection while maintaining authentic voice. Detects grammatical patterns that signal cognitive states or structural issues—acting as a sensory system for deeper strategic insights.
kirby-i18n-workflows
Manage Kirby multi-language workflows, translations, and localized labels. Use when dealing with languages, translation keys, placeholders, or importing/exporting translations.
extracting-keywords
Extract keywords from documents using YAKE algorithm with support for 34 languages (Arabic to Chinese). Use when users request keyword extraction, key terms, topic identification, content summarization, or document analysis. Includes domain-specific stopwords for AI/ML and life sciences. Optional deeper extraction mode (n=2+n=3 combined) for comprehensive coverage.
jta
Translate JSON i18n files to multiple languages with AI-powered quality optimization. Use when user mentions translating JSON, i18n files, internationalization, locale files, or needs to convert language files to other languages.
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
website-maintainer
Use this skill when working on the Repomix documentation website in `website/` directory, including VitePress configuration, multi-language content, or translation workflows.
