{
  "schemaVersion": "1.0",
  "item": {
    "slug": "paddleocr-doc-parsing-v2",
    "name": "PaddleOCR Document Parsing V2",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/hioTEC/paddleocr-doc-parsing-v2",
    "canonicalUrl": "https://clawhub.ai/hioTEC/paddleocr-doc-parsing-v2",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/paddleocr-doc-parsing-v2",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=paddleocr-doc-parsing-v2",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.json",
      "scripts/paddleocr_parse.py",
      "scripts/paddleocr_parse.sh"
    ],
    "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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.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/paddleocr-doc-parsing-v2"
    },
    "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/paddleocr-doc-parsing-v2",
    "agentPageUrl": "https://openagent3.xyz/skills/paddleocr-doc-parsing-v2/agent",
    "manifestUrl": "https://openagent3.xyz/skills/paddleocr-doc-parsing-v2/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/paddleocr-doc-parsing-v2/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": "PaddleOCR Document Parsing",
        "body": "Parse images and PDF files using PaddleOCR's API. Supports both synchronous and asynchronous parsing modes with structured output."
      },
      {
        "title": "Resource Links",
        "body": "ResourceLinkOfficial Websitehttps://www.paddleocr.comAPI Documentationhttps://ai.baidu.com/ai-doc/AISTUDIO/Cmkz2m0maGitHubhttps://github.com/PaddlePaddle/PaddleOCR"
      },
      {
        "title": "Key Features",
        "body": "Multi-format support: PDF and image files (JPG, PNG, BMP, TIFF)\nTwo parsing modes:\n\nSync mode: Fast response for small files (<600s timeout)\nAsync mode: For large files with progress polling\n\n\nLayout analysis: Automatic detection of text blocks, tables, formulas\nMulti-language: Support for 110+ languages\nStructured output: Markdown format with preserved document structure"
      },
      {
        "title": "Setup",
        "body": "Visit PaddleOCR to obtain your API credentials\nSet environment variables:\n\nexport PADDLEOCR_ACCESS_TOKEN=\"your_token_here\"\nexport PADDLEOCR_API_URL=\"https://your-endpoint.aistudio-app.com/layout-parsing\"\n\n# Optional: For async mode\nexport PADDLEOCR_JOB_URL=\"https://your-job-endpoint.aistudio-app.com/api/v2/ocr/jobs\"\nexport PADDLEOCR_MODEL=\"PaddleOCR-VL-1.5\""
      },
      {
        "title": "Sync Mode (Default)",
        "body": "For small files and quick processing:\n\n# Parse local image\n{baseDir}/paddleocr_parse.sh document.jpg\n\n# Parse PDF\n{baseDir}/paddleocr_parse.sh -t pdf document.pdf\n\n# Parse from URL\n{baseDir}/paddleocr_parse.sh https://example.com/document.jpg\n\n# Save output to file\n{baseDir}/paddleocr_parse.sh -o result.json document.jpg\n\n# Verbose output\n{baseDir}/paddleocr_parse.sh -v document.jpg"
      },
      {
        "title": "Async Mode",
        "body": "For large files with progress tracking:\n\n# Parse large PDF with async mode\n{baseDir}/paddleocr_parse.sh --async large-document.pdf\n\n# Parse from URL with async mode\n{baseDir}/paddleocr_parse.sh --async -t pdf https://example.com/doc.pdf\n\n# Save async result to file\n{baseDir}/paddleocr_parse.sh --async -o result.json document.pdf"
      },
      {
        "title": "Using Python Script Directly",
        "body": "# Sync mode\npython3 {baseDir}/paddleocr_parse.py document.jpg\n\n# Async mode\npython3 {baseDir}/paddleocr_parse.py --async-mode document.pdf\n\n# With output file\npython3 {baseDir}/paddleocr_parse.py -o result.json --async-mode document.pdf"
      },
      {
        "title": "Response Structure",
        "body": "{\n  \"logId\": \"unique_request_id\",\n  \"errorCode\": 0,\n  \"errorMsg\": \"Success\",\n  \"result\": {\n    \"layoutParsingResults\": [\n      {\n        \"prunedResult\": [...],\n        \"markdown\": {\n          \"text\": \"# Document Title\\n\\nParagraph content...\",\n          \"images\": {}\n        },\n        \"outputImages\": [...],\n        \"inputImage\": \"http://input-image\"\n      }\n    ],\n    \"dataInfo\": {...}\n  }\n}\n\nImportant Fields:\n\nprunedResult - Contains detailed layout element information including positions, categories, etc.\nmarkdown - Stores the document content converted to Markdown format with preserved structure and formatting."
      },
      {
        "title": "Mode Selection Guide",
        "body": "Use CaseRecommended ModeSmall images (< 10MB)SyncSingle page PDFsSyncLarge PDFs (> 10MB)AsyncMulti-page documentsAsyncBatch processingAsyncQuick text extractionSync"
      },
      {
        "title": "Error Handling",
        "body": "The script will exit with code 1 and print error message for:\n\nMissing required environment variables\nFile not found\nAPI authentication failures\nInvalid JSON responses\nAPI error codes (non-zero)"
      },
      {
        "title": "Quota Information",
        "body": "See official documentation: https://ai.baidu.com/ai-doc/AISTUDIO/Xmjclapam"
      }
    ],
    "body": "PaddleOCR Document Parsing\n\nParse images and PDF files using PaddleOCR's API. Supports both synchronous and asynchronous parsing modes with structured output.\n\nResource Links\nResource\tLink\nOfficial Website\thttps://www.paddleocr.com\nAPI Documentation\thttps://ai.baidu.com/ai-doc/AISTUDIO/Cmkz2m0ma\nGitHub\thttps://github.com/PaddlePaddle/PaddleOCR\nKey Features\nMulti-format support: PDF and image files (JPG, PNG, BMP, TIFF)\nTwo parsing modes:\nSync mode: Fast response for small files (<600s timeout)\nAsync mode: For large files with progress polling\nLayout analysis: Automatic detection of text blocks, tables, formulas\nMulti-language: Support for 110+ languages\nStructured output: Markdown format with preserved document structure\nSetup\nVisit PaddleOCR to obtain your API credentials\nSet environment variables:\nexport PADDLEOCR_ACCESS_TOKEN=\"your_token_here\"\nexport PADDLEOCR_API_URL=\"https://your-endpoint.aistudio-app.com/layout-parsing\"\n\n# Optional: For async mode\nexport PADDLEOCR_JOB_URL=\"https://your-job-endpoint.aistudio-app.com/api/v2/ocr/jobs\"\nexport PADDLEOCR_MODEL=\"PaddleOCR-VL-1.5\"\n\nUsage Examples\nSync Mode (Default)\n\nFor small files and quick processing:\n\n# Parse local image\n{baseDir}/paddleocr_parse.sh document.jpg\n\n# Parse PDF\n{baseDir}/paddleocr_parse.sh -t pdf document.pdf\n\n# Parse from URL\n{baseDir}/paddleocr_parse.sh https://example.com/document.jpg\n\n# Save output to file\n{baseDir}/paddleocr_parse.sh -o result.json document.jpg\n\n# Verbose output\n{baseDir}/paddleocr_parse.sh -v document.jpg\n\nAsync Mode\n\nFor large files with progress tracking:\n\n# Parse large PDF with async mode\n{baseDir}/paddleocr_parse.sh --async large-document.pdf\n\n# Parse from URL with async mode\n{baseDir}/paddleocr_parse.sh --async -t pdf https://example.com/doc.pdf\n\n# Save async result to file\n{baseDir}/paddleocr_parse.sh --async -o result.json document.pdf\n\nUsing Python Script Directly\n# Sync mode\npython3 {baseDir}/paddleocr_parse.py document.jpg\n\n# Async mode\npython3 {baseDir}/paddleocr_parse.py --async-mode document.pdf\n\n# With output file\npython3 {baseDir}/paddleocr_parse.py -o result.json --async-mode document.pdf\n\nResponse Structure\n{\n  \"logId\": \"unique_request_id\",\n  \"errorCode\": 0,\n  \"errorMsg\": \"Success\",\n  \"result\": {\n    \"layoutParsingResults\": [\n      {\n        \"prunedResult\": [...],\n        \"markdown\": {\n          \"text\": \"# Document Title\\n\\nParagraph content...\",\n          \"images\": {}\n        },\n        \"outputImages\": [...],\n        \"inputImage\": \"http://input-image\"\n      }\n    ],\n    \"dataInfo\": {...}\n  }\n}\n\n\nImportant Fields:\n\nprunedResult - Contains detailed layout element information including positions, categories, etc.\nmarkdown - Stores the document content converted to Markdown format with preserved structure and formatting.\nMode Selection Guide\nUse Case\tRecommended Mode\nSmall images (< 10MB)\tSync\nSingle page PDFs\tSync\nLarge PDFs (> 10MB)\tAsync\nMulti-page documents\tAsync\nBatch processing\tAsync\nQuick text extraction\tSync\nError Handling\n\nThe script will exit with code 1 and print error message for:\n\nMissing required environment variables\nFile not found\nAPI authentication failures\nInvalid JSON responses\nAPI error codes (non-zero)\nQuota Information\n\nSee official documentation: https://ai.baidu.com/ai-doc/AISTUDIO/Xmjclapam"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/hioTEC/paddleocr-doc-parsing-v2",
    "publisherUrl": "https://clawhub.ai/hioTEC/paddleocr-doc-parsing-v2",
    "owner": "hioTEC",
    "version": "1.0.4",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/paddleocr-doc-parsing-v2",
    "downloadUrl": "https://openagent3.xyz/downloads/paddleocr-doc-parsing-v2",
    "agentUrl": "https://openagent3.xyz/skills/paddleocr-doc-parsing-v2/agent",
    "manifestUrl": "https://openagent3.xyz/skills/paddleocr-doc-parsing-v2/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/paddleocr-doc-parsing-v2/agent.md"
  }
}