[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BVX7X2E5NTGF2KG3HTH0QP":3,"skill-same:01M7BVX7X2E5NTGF2KG3HTH0QP":79},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M7BVX7X2E5NTGF2KG3HTH0QP","layout-analyzer",null,">","om-scogo\u002Fskillsh-scraper","om-scogo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160466840?v=4","01M79AWB6DFVCQ7RK70CS34B96","Om Achrekar","01M79AWB6ZM9SKR8KDH1WSSM22",0,"MIT","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fclaude-office-skills-skills\u002Flayout-analyzer\u002FSkill.md",[],[],"2026-11-15 14:19:17",false,"---\n# ═══════════════════════════════════════════════════════════════════════════════\n# CLAUDE OFFICE SKILL - Enhanced Metadata v2.0\n# ═══════════════════════════════════════════════════════════════════════════════\n\n# Basic Information\nname: layout-analyzer\ndescription: \">\"\nversion: \"1.0\"\nauthor: claude-office-skills\nlicense: MIT\n\n# Categorization\ncategory: parsing\ntags:\n  - layout\n  - analysis\n  - structure\n  - surya\ndepartment: All\n\n# AI Model Compatibility\nmodels:\n  recommended:\n    - claude-sonnet-4\n    - claude-opus-4\n  compatible:\n    - claude-3-5-sonnet\n    - gpt-4\n    - gpt-4o\n\n# MCP Tools Integration\nmcp:\n  server: office-mcp\n  tools:\n    - analyze_document_structure\n\n# Skill Capabilities\ncapabilities:\n  - layout_detection\n  - structure_analysis\n\n# Language Support\nlanguages:\n  - en\n  - zh\n---\n\n# Layout Analyzer Skill\n\n## Overview\n\nThis skill enables document layout analysis using **surya** - an advanced document understanding system. Detect text blocks, tables, figures, headings, and determine reading order in complex documents.\n\n## How to Use\n\n1. Provide the document image or PDF\n2. Specify what layout elements to detect\n3. I'll analyze the structure and return detected regions\n\n**Example prompts:**\n- \"Analyze the layout of this document page\"\n- \"Detect all tables and text blocks in this image\"\n- \"Determine the reading order for this PDF page\"\n- \"Find headings and paragraphs in this document\"\n\n## Domain Knowledge\n\n### surya Fundamentals\n\n```python\nfrom surya.detection import DetectionPredictor\nfrom surya.layout import LayoutPredictor\nfrom surya.reading_order import ReadingOrderPredictor\nfrom PIL import Image\n\n# Load image\nimage = Image.open(\"document.png\")\n\n# Detect layout elements\nlayout_predictor = LayoutPredictor()\nlayout_result = layout_predictor([image])\n```\n\n### Layout Element Types\n\n| Element | Description |\n|---------|-------------|\n| Text | Regular paragraph text |\n| Title | Document\u002Fsection titles |\n| Section-header | Section headings |\n| List-item | Bulleted\u002Fnumbered items |\n| Table | Tabular data |\n| Figure | Images\u002Fdiagrams |\n| Caption | Figure\u002Ftable captions |\n| Footnote | Footnotes |\n| Formula | Mathematical equations |\n| Page-header | Headers |\n| Page-footer | Footers |\n\n### Text Detection\n\n```python\nfrom surya.detection import DetectionPredictor\nfrom PIL import Image\n\n# Initialize detector\ndetector = DetectionPredictor()\n\n# Load image\nimage = Image.open(\"document.png\")\n\n# Detect text regions\nresults = detector([image])\n\n# Access results\nfor page_result in results:\n    for bbox in page_result.bboxes:\n        print(f\"Text region: {bbox.bbox}\")\n        print(f\"Confidence: {bbox.confidence}\")\n```\n\n### Layout Analysis\n\n```python\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image\n\n# Initialize layout predictor\nlayout_predictor = LayoutPredictor()\n\n# Analyze layout\nimage = Image.open(\"document.png\")\nlayout_results = layout_predictor([image])\n\n# Process results\nfor page_result in layout_results:\n    for element in page_result.bboxes:\n        print(f\"Type: {element.label}\")\n        print(f\"Bbox: {element.bbox}\")\n        print(f\"Confidence: {element.confidence}\")\n```\n\n### Reading Order Detection\n\n```python\nfrom surya.reading_order import ReadingOrderPredictor\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image\n\n# Get layout first\nlayout_predictor = LayoutPredictor()\nimage = Image.open(\"document.png\")\nlayout_results = layout_predictor([image])\n\n# Determine reading order\nreading_order_predictor = ReadingOrderPredictor()\norder_results = reading_order_predictor([image], layout_results)\n\n# Access ordered elements\nfor page_result in order_results:\n    for i, element in enumerate(page_result.ordered_bboxes):\n        print(f\"{i+1}. {element.label}: {element.bbox}\")\n```\n\n### OCR with Layout\n\n```python\nfrom surya.ocr import OCRPredictor\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image\n\n# Initialize predictors\nocr_predictor = OCRPredictor()\nlayout_predictor = LayoutPredictor()\n\n# Load image\nimage = Image.open(\"document.png\")\n\n# Get layout\nlayout_results = layout_predictor([image])\n\n# Run OCR\nocr_results = ocr_predictor([image])\n\n# Combine results\nfor layout, ocr in zip(layout_results, ocr_results):\n    for layout_elem in layout.bboxes:\n        print(f\"Element: {layout_elem.label}\")\n        \n        # Find OCR text within this layout element\n        for text_line in ocr.text_lines:\n            if boxes_overlap(layout_elem.bbox, text_line.bbox):\n                print(f\"  Text: {text_line.text}\")\n```\n\n### Processing PDFs\n\n```python\nfrom surya.layout import LayoutPredictor\nfrom pdf2image import convert_from_path\n\ndef analyze_pdf_layout(pdf_path):\n    \"\"\"Analyze layout of all pages in PDF.\"\"\"\n    \n    # Convert PDF to images\n    images = convert_from_path(pdf_path)\n    \n    # Initialize predictor\n    layout_predictor = LayoutPredictor()\n    \n    # Analyze all pages\n    results = layout_predictor(images)\n    \n    document_structure = []\n    \n    for page_num, page_result in enumerate(results):\n        page_elements = []\n        \n        for element in page_result.bboxes:\n            page_elements.append({\n                'type': element.label,\n                'bbox': element.bbox,\n                'confidence': element.confidence\n            })\n        \n        document_structure.append({\n            'page': page_num + 1,\n            'elements': page_elements\n        })\n    \n    return document_structure\n\nstructure = analyze_pdf_layout(\"document.pdf\")\n```\n\n### Visualization\n\n```python\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image, ImageDraw, ImageFont\n\ndef visualize_layout(image_path, output_path):\n    \"\"\"Visualize detected layout elements.\"\"\"\n    \n    image = Image.open(image_path)\n    layout_predictor = LayoutPredictor()\n    results = layout_predictor([image])\n    \n    # Create drawing context\n    draw = ImageDraw.Draw(image)\n    \n    # Color mapping for element types\n    colors = {\n        'Text': 'blue',\n        'Title': 'red',\n        'Table': 'green',\n        'Figure': 'purple',\n        'Section-header': 'orange',\n        'List-item': 'cyan',\n    }\n    \n    for element in results[0].bboxes:\n        bbox = element.bbox\n        color = colors.get(element.label, 'gray')\n        \n        # Draw rectangle\n        draw.rectangle(bbox, outline=color, width=2)\n        \n        # Add label\n        draw.text((bbox[0], bbox[1] - 15), \n                  f\"{element.label} ({element.confidence:.2f})\",\n                  fill=color)\n    \n    image.save(output_path)\n    return output_path\n```\n\n## Best Practices\n\n1. **Use High-Quality Images**: 150+ DPI for best results\n2. **Preprocess if Needed**: Deskew rotated documents\n3. **Validate Results**: Check confidence scores\n4. **Handle Multi-page**: Process pages individually\n5. **Combine with OCR**: Get text within detected regions\n\n## Common Patterns\n\n### Document Structure Extraction\n```python\ndef extract_document_structure(image_path):\n    \"\"\"Extract hierarchical document structure.\"\"\"\n    \n    from surya.layout import LayoutPredictor\n    from surya.reading_order import ReadingOrderPredictor\n    \n    image = Image.open(image_path)\n    \n    # Get layout\n    layout_predictor = LayoutPredictor()\n    layout_results = layout_predictor([image])\n    \n    # Get reading order\n    order_predictor = ReadingOrderPredictor()\n    order_results = order_predictor([image], layout_results)\n    \n    structure = {\n        'title': None,\n        'sections': [],\n        'tables': [],\n        'figures': []\n    }\n    \n    current_section = None\n    \n    for element in order_results[0].ordered_bboxes:\n        if element.label == 'Title':\n            structure['title'] = element\n        elif element.label == 'Section-header':\n            current_section = {'header': element, 'content': []}\n            structure['sections'].append(current_section)\n        elif element.label == 'Table':\n            structure['tables'].append(element)\n        elif element.label == 'Figure':\n            structure['figures'].append(element)\n        elif current_section and element.label in ['Text', 'List-item']:\n            current_section['content'].append(element)\n    \n    return structure\n```\n\n### Table Region Extraction\n```python\ndef extract_table_regions(image_path):\n    \"\"\"Extract table regions from document.\"\"\"\n    \n    from surya.layout import LayoutPredictor\n    \n    image = Image.open(image_path)\n    layout_predictor = LayoutPredictor()\n    results = layout_predictor([image])\n    \n    tables = []\n    \n    for element in results[0].bboxes:\n        if element.label == 'Table':\n            bbox = element.bbox\n            \n            # Crop table region\n            table_image = image.crop(bbox)\n            \n            tables.append({\n                'bbox': bbox,\n                'image': table_image,\n                'confidence': element.confidence\n            })\n    \n    return tables\n```\n\n## Examples\n\n### Example 1: Academic Paper Analysis\n```python\nfrom surya.layout import LayoutPredictor\nfrom surya.reading_order import ReadingOrderPredictor\nfrom pdf2image import convert_from_path\n\ndef analyze_academic_paper(pdf_path):\n    \"\"\"Analyze structure of academic paper.\"\"\"\n    \n    images = convert_from_path(pdf_path)\n    \n    layout_predictor = LayoutPredictor()\n    order_predictor = ReadingOrderPredictor()\n    \n    paper_structure = {\n        'pages': [],\n        'element_counts': {\n            'Title': 0,\n            'Section-header': 0,\n            'Text': 0,\n            'Table': 0,\n            'Figure': 0,\n            'Formula': 0,\n            'Footnote': 0\n        }\n    }\n    \n    layout_results = layout_predictor(images)\n    order_results = order_predictor(images, layout_results)\n    \n    for page_num, (layout, order) in enumerate(zip(layout_results, order_results)):\n        page_structure = {\n            'page': page_num + 1,\n            'elements': []\n        }\n        \n        for element in order.ordered_bboxes:\n            page_structure['elements'].append({\n                'type': element.label,\n                'bbox': element.bbox,\n                'order': element.position\n            })\n            \n            # Count element types\n            if element.label in paper_structure['element_counts']:\n                paper_structure['element_counts'][element.label] += 1\n        \n        paper_structure['pages'].append(page_structure)\n    \n    return paper_structure\n\npaper = analyze_academic_paper('research_paper.pdf')\nprint(f\"Total tables: {paper['element_counts']['Table']}\")\nprint(f\"Total figures: {paper['element_counts']['Figure']}\")\n```\n\n### Example 2: Form Field Detection\n```python\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image\n\ndef detect_form_fields(image_path):\n    \"\"\"Detect form fields and labels.\"\"\"\n    \n    image = Image.open(image_path)\n    \n    layout_predictor = LayoutPredictor()\n    results = layout_predictor([image])\n    \n    form_fields = []\n    \n    for element in results[0].bboxes:\n        # Look for text elements that might be labels\n        if element.label == 'Text':\n            # Check if there's a box\u002Fline nearby (potential input field)\n            form_fields.append({\n                'type': 'potential_label',\n                'bbox': element.bbox,\n                'confidence': element.confidence\n            })\n    \n    return form_fields\n\nfields = detect_form_fields('form.png')\nprint(f\"Found {len(fields)} potential form elements\")\n```\n\n### Example 3: Multi-column Article\n```python\nfrom surya.layout import LayoutPredictor\nfrom surya.reading_order import ReadingOrderPredictor\nfrom PIL import Image\n\ndef process_multicolumn_article(image_path):\n    \"\"\"Process multi-column article layout.\"\"\"\n    \n    image = Image.open(image_path)\n    \n    layout_predictor = LayoutPredictor()\n    order_predictor = ReadingOrderPredictor()\n    \n    layout_results = layout_predictor([image])\n    order_results = order_predictor([image], layout_results)\n    \n    # Group elements by column\n    image_width = image.width\n    column_threshold = image_width \u002F 2\n    \n    columns = {\n        'left': [],\n        'right': [],\n        'full_width': []\n    }\n    \n    for element in order_results[0].ordered_bboxes:\n        bbox = element.bbox\n        element_center = (bbox[0] + bbox[2]) \u002F 2\n        element_width = bbox[2] - bbox[0]\n        \n        # Determine column\n        if element_width > column_threshold * 1.5:\n            columns['full_width'].append(element)\n        elif element_center \u003C column_threshold:\n            columns['left'].append(element)\n        else:\n            columns['right'].append(element)\n    \n    return {\n        'layout': 'multi-column',\n        'columns': columns,\n        'reading_order': order_results[0].ordered_bboxes\n    }\n\narticle = process_multicolumn_article('newspaper_page.png')\nprint(f\"Left column: {len(article['columns']['left'])} elements\")\nprint(f\"Right column: {len(article['columns']['right'])} elements\")\n```\n\n## Limitations\n\n- Handwritten layouts may be inaccurate\n- Very small text regions may be missed\n- Complex nested layouts challenging\n- GPU recommended for batch processing\n- Multi-language support varies\n\n## Installation\n\n```bash\npip install surya-ocr\n\n# For PDF processing\npip install pdf2image\n```\n\n## Resources\n\n- [surya GitHub](https:\u002F\u002Fgithub.com\u002FVikParuchuri\u002Fsurya)\n- [Model Documentation](https:\u002F\u002Fgithub.com\u002FVikParuchuri\u002Fsurya#models)\n- [Examples](https:\u002F\u002Fgithub.com\u002FVikParuchuri\u002Fsurya\u002Ftree\u002Fmaster\u002Fexamples)\n","# Layout Analyzer Skill\n\n## Overview\n\nThis skill enables document layout analysis using **surya** - an advanced document understanding system. Detect text blocks, tables, figures, headings, and determine reading order in complex documents.\n\n## How to Use\n\n1. Provide the document image or PDF\n2. Specify what layout elements to detect\n3. I'll analyze the structure and return detected regions\n\n**Example prompts:**\n- \"Analyze the layout of this document page\"\n- \"Detect all tables and text blocks in this image\"\n- \"Determine the reading order for this PDF page\"\n- \"Find headings and paragraphs in this document\"\n\n## Domain Knowledge\n\n### surya Fundamentals\n\n```python\nfrom surya.detection import DetectionPredictor\nfrom surya.layout import LayoutPredictor\nfrom surya.reading_order import ReadingOrderPredictor\nfrom PIL import Image\n\n# Load image\nimage = Image.open(\"document.png\")\n\n# Detect layout elements\nlayout_predictor = LayoutPredictor()\nlayout_result = layout_predictor([image])\n```\n\n### Layout Element Types\n\n| Element | Description |\n|---------|-------------|\n| Text | Regular paragraph text |\n| Title | Document\u002Fsection titles |\n| Section-header | Section headings |\n| List-item | Bulleted\u002Fnumbered items |\n| Table | Tabular data |\n| Figure | Images\u002Fdiagrams |\n| Caption | Figure\u002Ftable captions |\n| Footnote | Footnotes |\n| Formula | Mathematical equations |\n| Page-header | Headers |\n| Page-footer | Footers |\n\n### Text Detection\n\n```python\nfrom surya.detection import DetectionPredictor\nfrom PIL import Image\n\n# Initialize detector\ndetector = DetectionPredictor()\n\n# Load image\nimage = Image.open(\"document.png\")\n\n# Detect text regions\nresults = detector([image])\n\n# Access results\nfor page_result in results:\n    for bbox in page_result.bboxes:\n        print(f\"Text region: {bbox.bbox}\")\n        print(f\"Confidence: {bbox.confidence}\")\n```\n\n### Layout Analysis\n\n```python\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image\n\n# Initialize layout predictor\nlayout_predictor = LayoutPredictor()\n\n# Analyze layout\nimage = Image.open(\"document.png\")\nlayout_results = layout_predictor([image])\n\n# Process results\nfor page_result in layout_results:\n    for element in page_result.bboxes:\n        print(f\"Type: {element.label}\")\n        print(f\"Bbox: {element.bbox}\")\n        print(f\"Confidence: {element.confidence}\")\n```\n\n### Reading Order Detection\n\n```python\nfrom surya.reading_order import ReadingOrderPredictor\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image\n\n# Get layout first\nlayout_predictor = LayoutPredictor()\nimage = Image.open(\"document.png\")\nlayout_results = layout_predictor([image])\n\n# Determine reading order\nreading_order_predictor = ReadingOrderPredictor()\norder_results = reading_order_predictor([image], layout_results)\n\n# Access ordered elements\nfor page_result in order_results:\n    for i, element in enumerate(page_result.ordered_bboxes):\n        print(f\"{i+1}. {element.label}: {element.bbox}\")\n```\n\n### OCR with Layout\n\n```python\nfrom surya.ocr import OCRPredictor\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image\n\n# Initialize predictors\nocr_predictor = OCRPredictor()\nlayout_predictor = LayoutPredictor()\n\n# Load image\nimage = Image.open(\"document.png\")\n\n# Get layout\nlayout_results = layout_predictor([image])\n\n# Run OCR\nocr_results = ocr_predictor([image])\n\n# Combine results\nfor layout, ocr in zip(layout_results, ocr_results):\n    for layout_elem in layout.bboxes:\n        print(f\"Element: {layout_elem.label}\")\n        \n        # Find OCR text within this layout element\n        for text_line in ocr.text_lines:\n            if boxes_overlap(layout_elem.bbox, text_line.bbox):\n                print(f\"  Text: {text_line.text}\")\n```\n\n### Processing PDFs\n\n```python\nfrom surya.layout import LayoutPredictor\nfrom pdf2image import convert_from_path\n\ndef analyze_pdf_layout(pdf_path):\n    \"\"\"Analyze layout of all pages in PDF.\"\"\"\n    \n    # Convert PDF to images\n    images = convert_from_path(pdf_path)\n    \n    # Initialize predictor\n    layout_predictor = LayoutPredictor()\n    \n    # Analyze all pages\n    results = layout_predictor(images)\n    \n    document_structure = []\n    \n    for page_num, page_result in enumerate(results):\n        page_elements = []\n        \n        for element in page_result.bboxes:\n            page_elements.append({\n                'type': element.label,\n                'bbox': element.bbox,\n                'confidence': element.confidence\n            })\n        \n        document_structure.append({\n            'page': page_num + 1,\n            'elements': page_elements\n        })\n    \n    return document_structure\n\nstructure = analyze_pdf_layout(\"document.pdf\")\n```\n\n### Visualization\n\n```python\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image, ImageDraw, ImageFont\n\ndef visualize_layout(image_path, output_path):\n    \"\"\"Visualize detected layout elements.\"\"\"\n    \n    image = Image.open(image_path)\n    layout_predictor = LayoutPredictor()\n    results = layout_predictor([image])\n    \n    # Create drawing context\n    draw = ImageDraw.Draw(image)\n    \n    # Color mapping for element types\n    colors = {\n        'Text': 'blue',\n        'Title': 'red',\n        'Table': 'green',\n        'Figure': 'purple',\n        'Section-header': 'orange',\n        'List-item': 'cyan',\n    }\n    \n    for element in results[0].bboxes:\n        bbox = element.bbox\n        color = colors.get(element.label, 'gray')\n        \n        # Draw rectangle\n        draw.rectangle(bbox, outline=color, width=2)\n        \n        # Add label\n        draw.text((bbox[0], bbox[1] - 15), \n                  f\"{element.label} ({element.confidence:.2f})\",\n                  fill=color)\n    \n    image.save(output_path)\n    return output_path\n```\n\n## Best Practices\n\n1. **Use High-Quality Images**: 150+ DPI for best results\n2. **Preprocess if Needed**: Deskew rotated documents\n3. **Validate Results**: Check confidence scores\n4. **Handle Multi-page**: Process pages individually\n5. **Combine with OCR**: Get text within detected regions\n\n## Common Patterns\n\n### Document Structure Extraction\n```python\ndef extract_document_structure(image_path):\n    \"\"\"Extract hierarchical document structure.\"\"\"\n    \n    from surya.layout import LayoutPredictor\n    from surya.reading_order import ReadingOrderPredictor\n    \n    image = Image.open(image_path)\n    \n    # Get layout\n    layout_predictor = LayoutPredictor()\n    layout_results = layout_predictor([image])\n    \n    # Get reading order\n    order_predictor = ReadingOrderPredictor()\n    order_results = order_predictor([image], layout_results)\n    \n    structure = {\n        'title': None,\n        'sections': [],\n        'tables': [],\n        'figures': []\n    }\n    \n    current_section = None\n    \n    for element in order_results[0].ordered_bboxes:\n        if element.label == 'Title':\n            structure['title'] = element\n        elif element.label == 'Section-header':\n            current_section = {'header': element, 'content': []}\n            structure['sections'].append(current_section)\n        elif element.label == 'Table':\n            structure['tables'].append(element)\n        elif element.label == 'Figure':\n            structure['figures'].append(element)\n        elif current_section and element.label in ['Text', 'List-item']:\n            current_section['content'].append(element)\n    \n    return structure\n```\n\n### Table Region Extraction\n```python\ndef extract_table_regions(image_path):\n    \"\"\"Extract table regions from document.\"\"\"\n    \n    from surya.layout import LayoutPredictor\n    \n    image = Image.open(image_path)\n    layout_predictor = LayoutPredictor()\n    results = layout_predictor([image])\n    \n    tables = []\n    \n    for element in results[0].bboxes:\n        if element.label == 'Table':\n            bbox = element.bbox\n            \n            # Crop table region\n            table_image = image.crop(bbox)\n            \n            tables.append({\n                'bbox': bbox,\n                'image': table_image,\n                'confidence': element.confidence\n            })\n    \n    return tables\n```\n\n## Examples\n\n### Example 1: Academic Paper Analysis\n```python\nfrom surya.layout import LayoutPredictor\nfrom surya.reading_order import ReadingOrderPredictor\nfrom pdf2image import convert_from_path\n\ndef analyze_academic_paper(pdf_path):\n    \"\"\"Analyze structure of academic paper.\"\"\"\n    \n    images = convert_from_path(pdf_path)\n    \n    layout_predictor = LayoutPredictor()\n    order_predictor = ReadingOrderPredictor()\n    \n    paper_structure = {\n        'pages': [],\n        'element_counts': {\n            'Title': 0,\n            'Section-header': 0,\n            'Text': 0,\n            'Table': 0,\n            'Figure': 0,\n            'Formula': 0,\n            'Footnote': 0\n        }\n    }\n    \n    layout_results = layout_predictor(images)\n    order_results = order_predictor(images, layout_results)\n    \n    for page_num, (layout, order) in enumerate(zip(layout_results, order_results)):\n        page_structure = {\n            'page': page_num + 1,\n            'elements': []\n        }\n        \n        for element in order.ordered_bboxes:\n            page_structure['elements'].append({\n                'type': element.label,\n                'bbox': element.bbox,\n                'order': element.position\n            })\n            \n            # Count element types\n            if element.label in paper_structure['element_counts']:\n                paper_structure['element_counts'][element.label] += 1\n        \n        paper_structure['pages'].append(page_structure)\n    \n    return paper_structure\n\npaper = analyze_academic_paper('research_paper.pdf')\nprint(f\"Total tables: {paper['element_counts']['Table']}\")\nprint(f\"Total figures: {paper['element_counts']['Figure']}\")\n```\n\n### Example 2: Form Field Detection\n```python\nfrom surya.layout import LayoutPredictor\nfrom PIL import Image\n\ndef detect_form_fields(image_path):\n    \"\"\"Detect form fields and labels.\"\"\"\n    \n    image = Image.open(image_path)\n    \n    layout_predictor = LayoutPredictor()\n    results = layout_predictor([image])\n    \n    form_fields = []\n    \n    for element in results[0].bboxes:\n        # Look for text elements that might be labels\n        if element.label == 'Text':\n            # Check if there's a box\u002Fline nearby (potential input field)\n            form_fields.append({\n                'type': 'potential_label',\n                'bbox': element.bbox,\n                'confidence': element.confidence\n            })\n    \n    return form_fields\n\nfields = detect_form_fields('form.png')\nprint(f\"Found {len(fields)} potential form elements\")\n```\n\n### Example 3: Multi-column Article\n```python\nfrom surya.layout import LayoutPredictor\nfrom surya.reading_order import ReadingOrderPredictor\nfrom PIL import Image\n\ndef process_multicolumn_article(image_path):\n    \"\"\"Process multi-column article layout.\"\"\"\n    \n    image = Image.open(image_path)\n    \n    layout_predictor = LayoutPredictor()\n    order_predictor = ReadingOrderPredictor()\n    \n    layout_results = layout_predictor([image])\n    order_results = order_predictor([image], layout_results)\n    \n    # Group elements by column\n    image_width = image.width\n    column_threshold = image_width \u002F 2\n    \n    columns = {\n        'left': [],\n        'right': [],\n        'full_width': []\n    }\n    \n    for element in order_results[0].ordered_bboxes:\n        bbox = element.bbox\n        element_center = (bbox[0] + bbox[2]) \u002F 2\n        element_width = bbox[2] - bbox[0]\n        \n        # Determine column\n        if element_width > column_threshold * 1.5:\n            columns['full_width'].append(element)\n        elif element_center \u003C column_threshold:\n            columns['left'].append(element)\n        else:\n            columns['right'].append(element)\n    \n    return {\n        'layout': 'multi-column',\n        'columns': columns,\n        'reading_order': order_results[0].ordered_bboxes\n    }\n\narticle = process_multicolumn_article('newspaper_page.png')\nprint(f\"Left column: {len(article['columns']['left'])} elements\")\nprint(f\"Right column: {len(article['columns']['right'])} elements\")\n```\n\n## Limitations\n\n- Handwritten layouts may be inaccurate\n- Very small text regions may be missed\n- Complex nested layouts challenging\n- GPU recommended for batch processing\n- Multi-language support varies\n\n## Installation\n\n```bash\npip install surya-ocr\n\n# For PDF processing\npip install pdf2image\n```\n\n## Resources\n\n- [surya GitHub](https:\u002F\u002Fgithub.com\u002FVikParuchuri\u002Fsurya)\n- [Model Documentation](https:\u002F\u002Fgithub.com\u002FVikParuchuri\u002Fsurya#models)\n- [Examples](https:\u002F\u002Fgithub.com\u002FVikParuchuri\u002Fsurya\u002Ftree\u002Fmaster\u002Fexamples)\n",{"mcp":24,"name":5,"tags":28,"author":33,"models":34,"license":15,"version":42,"category":43,"languages":44,"department":47,"description":7,"capabilities":48},{"tools":25,"server":27},[26],"analyze_document_structure","office-mcp",[29,30,31,32],"layout","analysis","structure","surya","claude-office-skills",{"compatible":35,"recommended":39},[36,37,38],"claude-3-5-sonnet","gpt-4","gpt-4o",[40,41],"claude-sonnet-4","claude-opus-4","1.0","parsing",[45,46],"en","zh","All",[49,50],"layout_detection","structure_analysis","main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Fclaude-office-skills-skills\u002Flayout-analyzer",1,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper","https:\u002F\u002Fgithub.com\u002Fom-scogo","SDE-1 @ Scogo ","2026-07-18 12:22:46",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill layout-analyzer",{"tool":65,"command":66},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill layout-analyzer",{"tool":68,"command":69},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill layout-analyzer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fclaude-office-skills-skills\u002Flayout-analyzer\u002FSkill.md",true,[73],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"metadata.json","REFERENCE","参考文档",480,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fclaude-office-skills-skills\u002Flayout-analyzer\u002Fmetadata.json",[80,87,92,99,104,111],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7D6MC9FAAEV4CMNYX8W7JTG","arxiv-search","Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":88,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7D4ZTCS4DR3CE4JY06X84T2","working-with-legacy-code","Safely change and test untested codebases using Feathers' \"Working Effectively with Legacy Code\". Use when the user mentions \"legacy code\", \"no tests\", \"untested codebase\", \"how do I test this\", \"seams\", \"characterization tests\", \"golden master\", \"sprout method\", \"afraid to change this code\", \"monster method\", \"dependency breaking\", or \"inherited a messy codebase\". Also trigger when changing code without tests safely, getting a class under test when constructors, statics, or singletons block it, adding features to tangled modules, or planning incremental test coverage for an old codebase. Covers the legacy-code change algorithm, seams, characterization tests, sprout\u002Fwrap, and dependency-breaking techniques. For refactoring code that already has tests, see refactoring-patterns. For day-to-day code quality, see clean-code.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002Fworking-with-legacy-code\u002FSKILL.md",[],[],{"skillNo":100,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7D4ZB4CJBFW5JE67CPH2QRV","web-typography","Select, pair, and implement typefaces for web projects. Use when the user mentions \"font pairing\", \"which typeface\", \"line height\", \"responsive typography\", \"web font loading\", \"type hierarchy\", \"variable fonts\", \"FOUT\u002FFOIT\", \"typographic scale\", or \"the text is hard to read\". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002Fweb-typography\u002FSKILL.md",[],[],{"skillNo":112,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]