文档处理

智能文档处理专家，支持文档解析、信息抽取、文档分类

OCR for photos and images using MinerU. Extract text from photographs, screenshots, camera captures, and image files with high accuracy. Features: image OCR for .png, .jpg, .jpeg, .webp files. VLM mode for complex visual content. Handles photos of documents, whiteboards, signs, receipts, and more. Multiple output formats (Markdown, HTML, JSON, LaTeX). Use when you need to: OCR a photo, extract text from an image, read text in a screenshot, digitize a photo of a document, OCR a camera capture. Use when asked: 'how do I OCR this photo', 'extract text from this image', 'I took a picture of a document', 'can my agent read text from photos', 'is there a skill for image OCR', 'turn this photo into text', 'read this screenshot'. Powered by MinerU (OpenDataLab, Shanghai AI Lab) with advanced image OCR capabilities. Supports English, Chinese, and multilingual text in images. Perfect for mobile document capture, receipt digitization, whiteboard notes, sign reading, and any scenario where you have a photo with text that needs to be extracted.

从描述生成Excel公式并诊断表格错误,VLOOKUP不再难。Generate Excel formulas from descriptions。Use when 需要文件处理、文档转换、格式互转、内容提取时使用。不适用于加密文件破解。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。

English vocabulary learning coach with word analysis, vocabulary library management, and spaced-repetition daily review. Use when the user inputs a single English word (to analyze and collect it), says "收录" followed by a word, or says "复习" / "review" / "开始复习" to start today's review session (presents each word's full analysis one by one). Manages memory/ENGLISH_WORDS.md and memory/DAILY_REVIEW_YYYYMMDD.md in the current working directory.

PDF 文档处理 | PDF Document Processing. 读取、提取、合并、分割 PDF | Read, extract, merge, split PDFs. 支持文本提取、表格识别、注释 | Supports text extraction, table recognition, annotations. 触发词：PDF、pdf.

{"answer":"掌握Excel、Word、PowerPoint和Google Workspace，熟练运用公式、格式设置与自动化。"}

使用 Tesseract.js OCR 从图像中提取文本（100%本地运行，无需API密钥）。支持中文（简繁体）和英文。

通过托管 OAuth 集成 Microsoft Excel API，实现对 OneDrive 中 Excel 工作簿、工作表、区域、表格和图表的读写。使用此技能...

将 PPT 截图、设计稿、海报、图表页等高保真还原为完全可编辑的 PowerPoint 文件：文本转为文本框、形状转为自选图形、表格转为原生表格、图标与照片提取为图片，颜色像素级采样、版式按像素测量，并用渲染对比闭环校验一致性。与"图生 PPT"不同——本技能不重新生成画面，而是精准复刻已有图像并保留逐元素可编辑能力。

熟练使用Word、Excel、PPT办公软件，快速完成文档排版、数据处理和演示文档制作。使用场景：(1)需要排版Word文档、制作报告或标书；(2)需要处理Excel数据、制作图表或报表；(3)需要制作或优化PPT演示文稿；(4)需要三件套协同完成办公任务。

Excel 操作。数据处理、公式、表格操作。

【Excel】办公提效落地演示：从数据整理、公式函数、图表到透视表与报表自动化，手把手做出能用的表格与看板。覆盖日常台账与各类业务表。昆仑增长企业AI落地服务样例。

此技能用于自动校对报告、文档中的上下文不一致错误，包括实体矛盾、术语不统一、数据冲突、逻辑时序异常，并提供版本备份和一键修正功能。支持全文或指定章节/页码（多范围）提取校对。当用户说"帮我校对这份报告"、"检查文档前后是否一致"、"找出报告里的低级错误"、"文档一致性检查"时，应使用此技能。

Atlas Docs MCP服务器为AI助手提供库和框架的技术文档，将官方文档处理为适合LLM使用的Markdown版本，适用于Cursor、Cline、Windsurf等MCP兼容的LLM客户端。

Use when parsing PDFs for RAG pipelines, extracting structured data from PDFs, or converting PDFs to Markdown/JSON with bounding boxes for AI processing

Parse PDF documents with MinerU MCP to extract text, tables, and formulas. Supports multiple backends including MLX-accelerated inference on Apple Silicon.

将PDF文件的每一页转换为图片文件；支持自定义图片格式（PNG/JPG）和分辨率；适用于文档处理、图片化存档等场景

All-in-one PDF processing tool. Merge, split, extract, convert PDFs. Supports text extraction, table recognition, PDF-to-image conversion, OCR. Triggers: PDF, pdf.

PDF to Word converts PDF to editable Word/DOCX with AI-powered layout analysis and table recognition, built on ComPDF Conversion SDK to better preserve tables, multi-column layouts, lists, and images for downstream editing. It fits requests such as “pdf to word,” “convert pdf to docx,” “pdf to editable word,” “pdf to office,” “keep layout in word,” and “convert report to docx.” Example queries include “Convert this PDF contract to editable Word while keeping the tables intact,” “Turn this report into DOCX and preserve the multi-column layout,” and “Export this PDF to Word for further editing.”

Extract text from PDFs with OCR support. Perfect for digitizing documents, processing invoices, or analyzing content. Zero dependencies required.