doc-to-qra
Convert a document (PDF, URL, text) into Q&A pairs stored in memory.
Trouvez la capacité idéale pour votre agent.
Convert a document (PDF, URL, text) into Q&A pairs stored in memory.
Intelligent partial document reading for large files. Use when asked to find information in documents, search PDFs, extract content from large files, or when you need to answer questions about documents that may be too large to read entirely. Triggers on "read document", "find in document", "search PDF", "extract from", "docling", or when working with .docling.json files.
Convert any file to markdown format using the markitdown library. Use this skill when users need to convert documents (PDF, DOCX, XLSX, PPTX, images, HTML, CSV, JSON, XML, audio files, etc.) into markdown format for easier reading, editing, or integration into markdown-based workflows.
Simple report generation without Google Cloud - uses Gmail App Password or local file export (PDF, Excel, Word-compatible formats)
Export Obsidian notes to professional PDFs with configurable dimensions, clickable internal links, auto-generated TOC, and PDF bookmarks. Supports single note and batch export modes. Has device presets for Supernote Nomad, reMarkable, and Kindle. Use when user wants to create PDFs from their notes for sharing, printing, e-readers, or archival.
This skill should be used when implementing IPC (Inter-Process Communication) channels for PDF operations in Electron. Triggers on requests to create PDF merge, edit, or convert functionality, implement preload APIs, or set up Main-Renderer communication for file operations.
Process candidate resume PDFs to extract Name, Gender, Nationality and URR status
PDFや論文タイトルから論文情報を調べ、Microsoft Wordの引用管理機能(資料文献)にコピペできる形式で出力する。対応種類:論文/レポート、書籍、雑誌/定期刊行物の記事(ジャーナル)、Webサイト。「論文を引用形式に変換」「参考文献をWordフォーマットに」「この論文の引用情報を取得」「PDFから引用情報を抽出」「ジャーナル論文をWord形式に」などの依頼時に使用。
Export to PDF/HTML/markdown. Use when distributing documentation, creating presentations, or archiving design docs.
Parallel PDF to MP3 conversion using MiniMax. Convert multiple PDF chapters to audio simultaneously using parallel subagents. Use when: (1) User says 'generate mp3 for the story of [STORY_NAME]', (2) User says '为故事[STORY_NAME]生成mp3', (3) User says '为故事[STORY_NAME]第[X]章生成mp3', (4) User says 'generate mp3 for story of [STORY_NAME], chapter [X]', (5) Converting a range of PDFs like 'story-[01-05].pdf' to MP3, (6) Batch audiobook creation from PDF chapters.
Use when working with "PDF", "Excel", "Word", "PowerPoint", "XLSX", "DOCX", "PPTX", "spreadsheets", "presentations", "extract text", "merge documents", "convert documents", or asking about "office document manipulation"
Extract content from any document using the Preset-First Agentic Pipeline. Auto-detects format and document type (scientific papers, requirements specs, etc.). Supports PDF, DOCX, HTML, XML, PPTX, XLSX, EPUB, Markdown, images. Use when user says "extract this", "convert to markdown", "process pdf", or provides a document.
Extract structured information from integrated circuit and component datasheets (PDF files or URLs) and generate consistent markdown summaries. Use when the user requests to extract, summarize, analyze, or document information from IC/component datasheets, or when they provide a datasheet and want structured documentation. Triggers on phrases like "extract this datasheet", "summarize this datasheet", "analyze [component name]", "document this IC", or when working with datasheets for hardware design.
Document revision workflow tool (CLI: `rev`). Use when working with Word documents containing reviewer comments, importing track changes to markdown, replying to reviewer comments, building PDF/DOCX outputs, generating response letters, validating citations/DOIs, or any document revision task.
Create, fix, and refine deterministic receipt/invoice parsers in curlys-books, including vendor detection, OCR text extraction routing (pdfplumber for text PDFs → AWS Textract fallback; images → Textract), golden fixture creation, and updates to the vendor dispatcher/registry. Use when adding a new vendor parser, debugging mis-detections, improving totals/tax/date/line extraction, or deciding when to rely on Claude Vision fallback for vendors without a tested parser.