Convert OSCAL documents between formats (JSON, YAML, XML) and to human-readable formats like Markdown or plain text. Use for document transformation, reporting, and making OSCAL data accessible to non-technical stakeholders.
Analyzes legacy RPG (Report Program Generator) programs to assist with migration to modern Java applications. Extracts business logic from RPG III/IV/ILE, identifies data structures, file operations, and dependencies. Generates migration reports and creates Java implementation strategies. Use when working with AS/400 or IBM i system migration, RPG analysis, legacy system modernization, or when users mention RPG to Java conversion, analyzing .rpg/.RPG/.rpgle files, working with data specifications, or planning Java service implementations from RPG programs.
GPU-optimized OCR using Surya. Use when: (1) Extracting text from images/screenshots, (2) Processing PDFs with embedded images, (3) Multi-language document OCR, (4) Layout analysis and table detection. Supports 90+ languages with 2x accuracy over Tesseract.
Convert LaTeX to Markdown format. Use when the user asks to convert, transform, or change LaTeX files to Markdown, or mentions converting .tex files to .md files.
Extract clean article content from URLs (blog posts, articles, tutorials). Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.
Create and manipulate professional PDF documents with formatting, images, and metadata
Use when creating or improving educational concept files - includes curriculum research for new concepts, always updates translations before validation
Mathpix OCR for LaTeX extraction with balanced ternary checkpoints
Package language-specific subsets of claudefiles
Convert Markdown to LaTeX format. Use when the user asks to convert, transform, or change Markdown files to LaTeX, or mentions converting .md files to .tex files.
文档重排序服务（Reranker）。基于深度学习模型对检索候选结果进行细粒度相关性打分与重新排序，显著提升检索结果的精准度（Top-K 准确率）。
Expert guidance for fetching and parsing web content from URLs, handling various content sizes, JavaScript-rendered sites, and working around tool limitations. Use when fetching articles, documentation, social media posts, or any web content for translation, analysis, or archiving.
Stream long-form content to markdown files with resume capability. Writes content incrementally with section markers, enabling recovery if context limits are hit. Use when generating long documents (over 1000 lines), B-SPEC or specification writing, multi-section reports, any task where context compaction may occur mid-generation, or when user explicitly requests streaming output. Commands: init, write, status, resume, finalize, repair.
Translates English blog posts to Traditional Chinese while preserving Markdown format and frontmatter structure. Use this when asked to translate posts to zh-hant or create Chinese versions.
对项目的 i18n JSON 文件 (zh-CN.json, en.json) 进行 key 字典序排序。当用户需要整理、排序国际化翻译文件，或者在添加新翻译后需要保持 key 顺序一致时使用此 skill。
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Gmail メッセージ本文を表示する。「メール本文」「Gmail 本文を見たい」「メッセージ内容を表示」「メールを開いて」「Gmail を読む」「本文を見せて」「内容確認」などで起動。`/shiiman-google:gmail-read` を実行して本文を取得する。
Translate text between languages while preserving meaning and context
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Extracts key specifications from component datasheet PDFs for maker projects. Use when user shares a datasheet PDF URL, asks about component specs, needs pin assignments, I2C addresses, timing requirements, or register maps. Downloads and parses PDF to extract essentials. Complements datasheet-parser for quick lookups.
Extract HEAL matrix content from PowerPoint slides and save as formatted text files matching N2 HEAL format
Download WhatsApp voice notes, transcribe them, and correct common mining site mis-transcriptions (max 300 chars)
