documents▌

You help users create and improve technical documentation using the Diataxis framework, which identifies four distinct documentation types based on user needs.

Dual-engine OCR for extracting text from scanned PDFs and images with local or cloud processing. \n \n Supports RapidOCR (local, free, no API key) and SiliconFlow API (cloud-based, high precision) with automatic fallback when local engine fails \n Handles scanned PDFs and multiple image formats (JPG, PNG, BMP, GIF, TIFF, WEBP) with Chinese and English text recognition \n Preserves text order and structure; automatically converts PDF pages to images for processing \n Batch processing capability f

PDF OCR技能用于从影印版PDF文件和图片文件中提取文字内容。该技能支持两种OCR引擎：

Access LangGraph documentation to build stateful agents and multi-agent workflows. \n \n Fetches official LangGraph Python docs covering state machines, graph-based agent design, and human-in-the-loop patterns \n Prioritizes relevant documentation by query type: implementation guides for how-to questions, concept pages for theory, tutorials for end-to-end examples, and API references for technical details \n Automatically selects 2–4 most relevant documentation URLs and retrieves their content t

本技能提供党政机关公文写作的完整指南，涵盖格式规范、常用模板、写作技巧和质量检查，确保公文格式正确、语言规范、结构清晰。

Convert PDF files to Markdown with automatic detection of native text vs scanned documents. \n \n Supports three conversion modes: auto-detect (default), native text extraction, and OCR for scanned PDFs \n Fast JavaScript-based processing with no system dependencies; returns JSON output with page count and conversion mode \n Handles basic table structure preservation and works cross-platform on Windows, macOS, and Linux \n OCR for scanned documents requires optional tesseract.js setup; complex m

Professional document creation, editing, and analysis across Word, PDF, PowerPoint, and Excel formats. \n \n Four specialized sub-skills handle distinct document types: docx for Word documents with tracked changes and comments, pdf for text/table extraction and document merging, pptx for presentation creation and layout management, and xlsx for spreadsheet manipulation and formulas \n Supports both creation from scratch and editing of existing files, with language-specific libraries (docx-js for

Retrieve current documentation and code examples for any library using the Context7 CLI.

Natural-language PDF editing through command-line instructions on specific pages. \n \n Accepts plain-English edit commands targeting individual PDF pages, such as text changes, corrections, and formatting adjustments \n Requires the nano-pdf CLI tool installed via uv or pip \n Page numbering may vary by version; verify output carefully as results can be off-by-one depending on configuration \n

Extract text, tables, and metadata from PDF documents with character-level precision. \n \n Supports text extraction with layout preservation, word-level positioning, and character-level access including font and size metadata \n Includes advanced table detection with customizable strategies (lines, text, explicit) and tolerance tuning for complex layouts \n Provides visual debugging via image rendering with overlays for characters, words, lines, and detected table boundaries \n Handles cropping