documents▌

Extract text from images and scanned PDFs with support for 100+ languages, table detection, and multiple output formats. \n \n Handles PNG, JPEG, TIFF, BMP images and multi-page PDFs with per-page or full-document extraction \n Supports 100+ languages with auto-detection, language-specific packs, and multi-language document processing \n Exports to plain text, Markdown, JSON, HTML, and searchable PDFs with confidence scoring and bounding box data \n Includes intelligent preprocessing (deskew, de

To preserve ANY formatting from the source document, MUST unzip and parse XML.

Fetch current library documentation and code examples instead of relying on training data. \n \n Resolves library names to Context7 documentation IDs, then queries for setup, configuration, and API reference information \n Supports major frameworks and libraries: React, Vue, Svelte, Next.js, Express, Prisma, Supabase, Tailwind, and others \n Activates automatically for setup questions, code generation requests, and framework-specific inquiries \n Returns version-aware documentation and official

This skill enables creation, editing, and analysis of Excel spreadsheets programmatically. Claude should apply these patterns when users need to generate data reports, financial models, automate Excel workflows, or process spreadsheet data.

39 tools for Word, Excel, PowerPoint, PDF, and OCR document operations via MCP server. \n \n Covers PDF manipulation (extraction, merging, splitting, compression, OCR), spreadsheet analysis and creation, Word document generation and templating, and presentation authoring \n Includes 9 format conversion tools supporting Excel, CSV, JSON, Markdown, PDF, HTML, and batch operations \n Multi-language OCR support for English, Chinese, Japanese, Korean, French, German, and Spanish \n Built in TypeScrip

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md，其中包含认证、权限处理

Organize technical documentation into four distinct types—tutorials, how-to guides, reference, and explanations—each serving different user needs. \n \n Applies the Diátaxis framework to structure documentation by learning context: tutorials for beginners learning by doing, how-to guides for solving specific problems, reference for technical facts, and explanations for conceptual understanding \n Provides type-specific patterns including title conventions, structural templates, and validation ch

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Convert PDF files to various formats and vice versa while preserving formatting.

>-