{
  "schemaVersion": "1.0",
  "item": {
    "slug": "wiseocr",
    "name": "WiseOCR",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/wisediag/wiseocr",
    "canonicalUrl": "https://clawhub.ai/wisediag/wiseocr",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/wiseocr",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=wiseocr",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "requirements.txt",
      "scripts/wiseocr.py",
      "SKILL.md"
    ],
    "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "wiseocr",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-11T02:41:07.565Z",
      "expiresAt": "2026-05-18T02:41:07.565Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=wiseocr",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=wiseocr",
        "contentDisposition": "attachment; filename=\"wiseocr-1.0.28.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "wiseocr"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/wiseocr"
    },
    "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/wiseocr",
    "agentPageUrl": "https://openagent3.xyz/skills/wiseocr/agent",
    "manifestUrl": "https://openagent3.xyz/skills/wiseocr/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/wiseocr/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "⚠️ Privacy Warning",
        "body": "IMPORTANT - READ BEFORE INSTALLING:\n\nThis skill uploads your files to WiseDiag's cloud servers for OCR processing.\n\nDo NOT use with sensitive or confidential documents unless:\n\nYou trust WiseDiag's data handling policies\nYou accept that file contents will be transmitted and processed remotely\n\nFor sensitive documents, use offline/local OCR tools instead."
      },
      {
        "title": "WiseOCR Skill (powered by WiseDiag)",
        "body": "Convert PDF files into Markdown format. The script handles API authentication, file upload, OCR processing, and saves the result automatically."
      },
      {
        "title": "⚠️ IMPORTANT: How to Use This Skill",
        "body": "You MUST use the provided script to process files. Do NOT call any API or HTTP endpoint directly.\n\nThe script scripts/wiseocr.py handles everything:\n\nAPI authentication (reads WISEDIAG_API_KEY from environment)\nPDF upload and OCR processing\nSaves the Markdown result to WiseOCR/{filename}.md"
      },
      {
        "title": "🔑 API Key Setup (Required)",
        "body": "Get your API key:\n👉 https://console.wisediag.com/apiKeyManage\n\nexport WISEDIAG_API_KEY=your_api_key"
      },
      {
        "title": "Installation",
        "body": "pip install -r requirements.txt"
      },
      {
        "title": "Usage",
        "body": "To process a PDF file, run:\n\ncd scripts\npython wiseocr.py -i /path/to/input.pdf -n original_filename\n\nIMPORTANT: Always pass -n with the original filename (without extension) so the output file is named correctly. If the uploaded file has been renamed (e.g. to ocr_input.pdf), -n ensures the output uses the user's original filename.\n\nThe script will automatically save the result to WiseOCR/{name}.md.\n\nExample:\n\npython wiseocr.py -i /tmp/ocr_input.pdf -n medical_report\n# Output saved to: WiseOCR/medical_report.md\n\nWith custom output directory:\n\npython wiseocr.py -i /path/to/input.pdf -n medical_report -o /custom/output/dir"
      },
      {
        "title": "Arguments",
        "body": "FlagDescription-i, --inputInput PDF file path (required)-n, --nameOriginal filename without extension for output (recommended)-o, --outputOutput directory (default: ./WiseOCR)--dpiPDF rendering DPI, 72-600 (default: 200)"
      },
      {
        "title": "Output",
        "body": "After the script runs, the Markdown file is saved automatically:\n\nDefault: WiseOCR/{name}.md\nThe file is named using the -n parameter (e.g. -n report → report.md), or falls back to the input filename\nNo additional saving is needed — the file is already on disk"
      },
      {
        "title": "Data Privacy",
        "body": "What happens to your files:\n\nFiles are uploaded to WiseDiag's OCR API (https://openapi.wisediag.com)\nFiles are processed on WiseDiag servers\nProcessing results are returned to you\nFiles are not permanently stored on WiseDiag servers\n\nFor sensitive documents, use offline/local OCR tools instead."
      },
      {
        "title": "License",
        "body": "MIT"
      }
    ],
    "body": "⚠️ Privacy Warning\n\nIMPORTANT - READ BEFORE INSTALLING:\n\nThis skill uploads your files to WiseDiag's cloud servers for OCR processing.\n\nDo NOT use with sensitive or confidential documents unless:\n\nYou trust WiseDiag's data handling policies\nYou accept that file contents will be transmitted and processed remotely\n\nFor sensitive documents, use offline/local OCR tools instead.\n\nWiseOCR Skill (powered by WiseDiag)\n\nConvert PDF files into Markdown format. The script handles API authentication, file upload, OCR processing, and saves the result automatically.\n\n⚠️ IMPORTANT: How to Use This Skill\n\nYou MUST use the provided script to process files. Do NOT call any API or HTTP endpoint directly.\n\nThe script scripts/wiseocr.py handles everything:\n\nAPI authentication (reads WISEDIAG_API_KEY from environment)\nPDF upload and OCR processing\nSaves the Markdown result to WiseOCR/{filename}.md\n🔑 API Key Setup (Required)\n\nGet your API key: 👉 https://console.wisediag.com/apiKeyManage\n\nexport WISEDIAG_API_KEY=your_api_key\n\nInstallation\npip install -r requirements.txt\n\nUsage\n\nTo process a PDF file, run:\n\ncd scripts\npython wiseocr.py -i /path/to/input.pdf -n original_filename\n\n\nIMPORTANT: Always pass -n with the original filename (without extension) so the output file is named correctly. If the uploaded file has been renamed (e.g. to ocr_input.pdf), -n ensures the output uses the user's original filename.\n\nThe script will automatically save the result to WiseOCR/{name}.md.\n\nExample:\n\npython wiseocr.py -i /tmp/ocr_input.pdf -n medical_report\n# Output saved to: WiseOCR/medical_report.md\n\n\nWith custom output directory:\n\npython wiseocr.py -i /path/to/input.pdf -n medical_report -o /custom/output/dir\n\nArguments\nFlag\tDescription\n-i, --input\tInput PDF file path (required)\n-n, --name\tOriginal filename without extension for output (recommended)\n-o, --output\tOutput directory (default: ./WiseOCR)\n--dpi\tPDF rendering DPI, 72-600 (default: 200)\nOutput\n\nAfter the script runs, the Markdown file is saved automatically:\n\nDefault: WiseOCR/{name}.md\nThe file is named using the -n parameter (e.g. -n report → report.md), or falls back to the input filename\nNo additional saving is needed — the file is already on disk\nData Privacy\n\nWhat happens to your files:\n\nFiles are uploaded to WiseDiag's OCR API (https://openapi.wisediag.com)\nFiles are processed on WiseDiag servers\nProcessing results are returned to you\nFiles are not permanently stored on WiseDiag servers\n\nFor sensitive documents, use offline/local OCR tools instead.\n\nLicense\n\nMIT"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wisediag/wiseocr",
    "publisherUrl": "https://clawhub.ai/wisediag/wiseocr",
    "owner": "wisediag",
    "version": "1.0.9",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/wiseocr",
    "downloadUrl": "https://openagent3.xyz/downloads/wiseocr",
    "agentUrl": "https://openagent3.xyz/skills/wiseocr/agent",
    "manifestUrl": "https://openagent3.xyz/skills/wiseocr/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/wiseocr/agent.md"
  }
}