Layout Analyzer
Skill ยืนยันแล้ว>
This skill leverages the Surya library to analyze document images and PDFs, enabling the detection of various layout elements such as text blocks, tables, figures, and headings. It provides structured output detailing the detected regions, their types, and confidence scores, facilitating advanced document understanding workflows.
Scope
- warning:Description qualityThe 'description' field in the SKILL.md frontmatter is a single character ('>') and lacks meaningful information about the skill's purpose or functionality.
Invocation
- warning:Concise FrontmatterThe SKILL.md frontmatter contains a very short, uninformative description ('>') and a keyword-stuffed 'tags' field, which could hinder precise routing.
Practical Utility
- info:Edge casesThe 'Limitations' section mentions potential issues with handwritten layouts, small text, and complex nesting, but does not detail specific recovery steps.
การติดตั้ง
npx skills add claude-office-skills/skillsเรียกใช้ Vercel skills CLI (skills.sh) ผ่าน npx — ต้องติดตั้ง Node.js ในเครื่อง และมี agent ที่รองรับ skills อย่างน้อยหนึ่งตัว (Claude Code, Cursor, Codex, …) ทั้งนี้สมมติว่า repo ใช้รูปแบบ agentskills.io
ส่วนขยายที่คล้ายกัน
Document Parser Skill
92>
PaddleOCR Document Parsing
98Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.
PDF OCR Extraction
95Extract text from scanned PDFs using optical character recognition
PaddleOCR Text Recognition
95Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字, plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan, recognize text.
Office MCP Server
94MCP server with 39 tools for Word, Excel, PowerPoint, PDF, OCR operations
Smart OCR Skill
92>