{
  "schemaVersion": "1.0",
  "item": {
    "slug": "azure-doc-ocr",
    "name": "Azure Document OCR",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Li-Hongmin/azure-doc-ocr",
    "canonicalUrl": "https://clawhub.ai/Li-Hongmin/azure-doc-ocr",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/azure-doc-ocr",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=azure-doc-ocr",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/models.md",
      "scripts/batch_ocr.py",
      "scripts/ocr_extract.py"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/azure-doc-ocr"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/azure-doc-ocr",
    "agentPageUrl": "https://openagent3.xyz/skills/azure-doc-ocr/agent",
    "manifestUrl": "https://openagent3.xyz/skills/azure-doc-ocr/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/azure-doc-ocr/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Azure Document Intelligence OCR",
        "body": "Extract text and structured data from documents using Azure Document Intelligence REST API."
      },
      {
        "title": "1. Environment Setup",
        "body": "Set your Azure Document Intelligence credentials:\n\nexport AZURE_DOC_INTEL_ENDPOINT=\"https://your-resource.cognitiveservices.azure.com\"\nexport AZURE_DOC_INTEL_KEY=\"your-api-key\""
      },
      {
        "title": "2. Single File OCR",
        "body": "# Basic text extraction from PDF\npython scripts/ocr_extract.py document.pdf\n\n# Extract with layout (tables, structure)\npython scripts/ocr_extract.py document.pdf --model prebuilt-layout --format markdown\n\n# Process invoice\npython scripts/ocr_extract.py invoice.pdf --model prebuilt-invoice --format json\n\n# OCR from URL\npython scripts/ocr_extract.py --url \"https://example.com/document.pdf\"\n\n# Save output to file\npython scripts/ocr_extract.py document.pdf --output result.txt\n\n# Extract specific pages\npython scripts/ocr_extract.py document.pdf --pages 1-3,5"
      },
      {
        "title": "3. Batch Processing",
        "body": "# Process all documents in a folder\npython scripts/batch_ocr.py ./documents/\n\n# Custom output directory and format\npython scripts/batch_ocr.py ./documents/ --output-dir ./extracted/ --format markdown\n\n# Use layout model with 8 workers\npython scripts/batch_ocr.py ./documents/ --model prebuilt-layout --workers 8\n\n# Filter specific extensions\npython scripts/batch_ocr.py ./documents/ --ext .pdf,.png"
      },
      {
        "title": "Model Selection Guide",
        "body": "Document TypeRecommended ModelUse CaseGeneral textprebuilt-readPure text extraction, any documentStructured docsprebuilt-layoutTables, forms, paragraphs, figuresInvoicesprebuilt-invoiceVendor info, line items, totalsReceiptsprebuilt-receiptMerchant, items, totals, datesIDs/Passportsprebuilt-idDocumentIdentity documentsBusiness cardsprebuilt-businessCardContact informationW-2 formsprebuilt-tax.us.w2US tax documentsInsurance cardsprebuilt-healthInsuranceCard.usHealth insurance info\n\nSee references/models.md for detailed model documentation."
      },
      {
        "title": "Supported Input Formats",
        "body": "PDF: .pdf (including scanned PDFs)\nImages: .png, .jpg, .jpeg, .tiff, .bmp\nURLs: Direct links to documents"
      },
      {
        "title": "Output Formats",
        "body": "text: Plain text concatenation of all extracted content\nmarkdown: Structured output with headers and tables (best with layout model)\njson: Raw API response with full extraction details"
      },
      {
        "title": "Features",
        "body": "Handwriting Recognition: Extracts handwritten text alongside printed text\nCJK Support: Full support for Chinese, Japanese, Korean characters\nTable Extraction: Preserves table structure (use layout model)\nMulti-page Processing: Handles documents with multiple pages\nConcurrent Processing: Batch script supports parallel processing\nURL Input: Process documents directly from URLs"
      },
      {
        "title": "Environment Variables",
        "body": "VariableRequiredDescriptionAZURE_DOC_INTEL_ENDPOINTYesAzure Document Intelligence endpoint URLAZURE_DOC_INTEL_KEYYesAPI subscription key"
      },
      {
        "title": "Error Handling",
        "body": "Invalid credentials: Check endpoint URL and API key\nUnsupported format: Ensure file extension matches supported types\nTimeout: Large documents may need longer processing (max 300s)\nRate limiting: Reduce concurrent workers for batch processing"
      },
      {
        "title": "Extract text from scanned PDF",
        "body": "python scripts/ocr_extract.py scanned_contract.pdf --model prebuilt-read"
      },
      {
        "title": "Process invoices with structured output",
        "body": "python scripts/ocr_extract.py invoice.pdf --model prebuilt-invoice --format json --output invoice_data.json"
      },
      {
        "title": "Batch process with layout analysis",
        "body": "python scripts/batch_ocr.py ./reports/ --model prebuilt-layout --format markdown --workers 4"
      },
      {
        "title": "Extract specific pages from large document",
        "body": "python scripts/ocr_extract.py large_doc.pdf --pages 1,3-5,10 --format text"
      }
    ],
    "body": "Azure Document Intelligence OCR\n\nExtract text and structured data from documents using Azure Document Intelligence REST API.\n\nQuick Start\n1. Environment Setup\n\nSet your Azure Document Intelligence credentials:\n\nexport AZURE_DOC_INTEL_ENDPOINT=\"https://your-resource.cognitiveservices.azure.com\"\nexport AZURE_DOC_INTEL_KEY=\"your-api-key\"\n\n2. Single File OCR\n# Basic text extraction from PDF\npython scripts/ocr_extract.py document.pdf\n\n# Extract with layout (tables, structure)\npython scripts/ocr_extract.py document.pdf --model prebuilt-layout --format markdown\n\n# Process invoice\npython scripts/ocr_extract.py invoice.pdf --model prebuilt-invoice --format json\n\n# OCR from URL\npython scripts/ocr_extract.py --url \"https://example.com/document.pdf\"\n\n# Save output to file\npython scripts/ocr_extract.py document.pdf --output result.txt\n\n# Extract specific pages\npython scripts/ocr_extract.py document.pdf --pages 1-3,5\n\n3. Batch Processing\n# Process all documents in a folder\npython scripts/batch_ocr.py ./documents/\n\n# Custom output directory and format\npython scripts/batch_ocr.py ./documents/ --output-dir ./extracted/ --format markdown\n\n# Use layout model with 8 workers\npython scripts/batch_ocr.py ./documents/ --model prebuilt-layout --workers 8\n\n# Filter specific extensions\npython scripts/batch_ocr.py ./documents/ --ext .pdf,.png\n\nModel Selection Guide\nDocument Type\tRecommended Model\tUse Case\nGeneral text\tprebuilt-read\tPure text extraction, any document\nStructured docs\tprebuilt-layout\tTables, forms, paragraphs, figures\nInvoices\tprebuilt-invoice\tVendor info, line items, totals\nReceipts\tprebuilt-receipt\tMerchant, items, totals, dates\nIDs/Passports\tprebuilt-idDocument\tIdentity documents\nBusiness cards\tprebuilt-businessCard\tContact information\nW-2 forms\tprebuilt-tax.us.w2\tUS tax documents\nInsurance cards\tprebuilt-healthInsuranceCard.us\tHealth insurance info\n\nSee references/models.md for detailed model documentation.\n\nSupported Input Formats\nPDF: .pdf (including scanned PDFs)\nImages: .png, .jpg, .jpeg, .tiff, .bmp\nURLs: Direct links to documents\nOutput Formats\ntext: Plain text concatenation of all extracted content\nmarkdown: Structured output with headers and tables (best with layout model)\njson: Raw API response with full extraction details\nFeatures\nHandwriting Recognition: Extracts handwritten text alongside printed text\nCJK Support: Full support for Chinese, Japanese, Korean characters\nTable Extraction: Preserves table structure (use layout model)\nMulti-page Processing: Handles documents with multiple pages\nConcurrent Processing: Batch script supports parallel processing\nURL Input: Process documents directly from URLs\nEnvironment Variables\nVariable\tRequired\tDescription\nAZURE_DOC_INTEL_ENDPOINT\tYes\tAzure Document Intelligence endpoint URL\nAZURE_DOC_INTEL_KEY\tYes\tAPI subscription key\nError Handling\nInvalid credentials: Check endpoint URL and API key\nUnsupported format: Ensure file extension matches supported types\nTimeout: Large documents may need longer processing (max 300s)\nRate limiting: Reduce concurrent workers for batch processing\nExamples\nExtract text from scanned PDF\npython scripts/ocr_extract.py scanned_contract.pdf --model prebuilt-read\n\nProcess invoices with structured output\npython scripts/ocr_extract.py invoice.pdf --model prebuilt-invoice --format json --output invoice_data.json\n\nBatch process with layout analysis\npython scripts/batch_ocr.py ./reports/ --model prebuilt-layout --format markdown --workers 4\n\nExtract specific pages from large document\npython scripts/ocr_extract.py large_doc.pdf --pages 1,3-5,10 --format text"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Li-Hongmin/azure-doc-ocr",
    "publisherUrl": "https://clawhub.ai/Li-Hongmin/azure-doc-ocr",
    "owner": "Li-Hongmin",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/azure-doc-ocr",
    "downloadUrl": "https://openagent3.xyz/downloads/azure-doc-ocr",
    "agentUrl": "https://openagent3.xyz/skills/azure-doc-ocr/agent",
    "manifestUrl": "https://openagent3.xyz/skills/azure-doc-ocr/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/azure-doc-ocr/agent.md"
  }
}