{
  "schemaVersion": "1.0",
  "item": {
    "slug": "browser-auto-download",
    "name": "browser-auto-download",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Aaronxx/browser-auto-download",
    "canonicalUrl": "https://clawhub.ai/Aaronxx/browser-auto-download",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/browser-auto-download",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browser-auto-download",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CHANGELOG.md",
      "CONTRIBUTING.md",
      "package.json",
      "QUICKSTART.md",
      "README.md",
      "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",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/browser-auto-download"
    },
    "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/browser-auto-download",
    "agentPageUrl": "https://openagent3.xyz/skills/browser-auto-download/agent",
    "manifestUrl": "https://openagent3.xyz/skills/browser-auto-download/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/browser-auto-download/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": "Browser Auto Download v4.1.0 (Enhanced)",
        "body": "Download files from dynamic webpages with intelligent detection and multi-step navigation."
      },
      {
        "title": "Key Features",
        "body": "Auto-download capture: Detects downloads triggered automatically on page load\nMulti-step navigation: Finds and navigates to platform-specific pages (PC/Desktop versions)\nPlatform auto-detection: Windows x64/ARM64, macOS Intel/Apple Silicon, Linux\nEvent listening: Captures all download events without requiring button clicks\nSmart fallback: Tries multiple strategies (auto-download, navigation, clicking)"
      },
      {
        "title": "When to Use",
        "body": "Use this skill for:\n\nAuto-download sites: Downloads start automatically when page loads\nMulti-step flows: Homepage - click \"PC version\" - download page\nDynamic content: Download links generated via JavaScript\nInteractive downloads: Requires clicking buttons or navigating UI\n\nNOT for: Direct file URLs (use curl/wget instead)"
      },
      {
        "title": "Option 1: Automatic (Recommended)",
        "body": "python skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://example.com/download\"\n\nThe script will:\n\nCheck for auto-downloads on page load\nLook for platform-specific page links (PC/Desktop version)\nNavigate if needed\nTry clicking download buttons as fallback"
      },
      {
        "title": "Option 2: Built-in Shortcuts",
        "body": "# WeChat DevTools\npython skills/browser-auto-download/scripts/auto_download.py --wechat\n\n# Meitu Xiuxiu\npython skills/browser-auto-download/scripts/auto_download.py --meitu"
      },
      {
        "title": "Option 3: Python Module",
        "body": "from skills.browser-auto-download.scripts.auto_download import auto_download\n\nresult = auto_download(\n    url=\"https://example.com/download\",\n    auto_select=True,   # Platform detection\n    auto_navigate=True  # Multi-step navigation\n)\n\nif result:\n    print(f\"Downloaded: {result['path']}\")"
      },
      {
        "title": "Three-Stage Strategy",
        "body": "Stage 1: Auto-Download Detection\n\nPage loads - Check for downloads - Success?\n    Yes:                    No:\n    Save file               Go to Stage 2\n\nStage 2: Multi-Step Navigation\n\nLook for \"PC/Desktop\" link - Navigate - Check downloads - Success?\n    Yes:                        No:\n    Save file                  Go to Stage 3\n\nStage 3: Button Clicking\n\nTry multiple selectors - Click - Wait for download - Save"
      },
      {
        "title": "Platform-Specific Page Detection",
        "body": "Automatically finds links like:\n\n\"meitu for PC\" - pc.meitu.com\n\"Desktop version\" - desktop.example.com\n\"Windows Download\" - windows.example.com\n\nKeywords: pc, desktop, windows, mac, download, 电脑, 桌面, 客户端"
      },
      {
        "title": "Auto-Download Sites (Best Case)",
        "body": "# Sites that trigger download on page load\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://pc.meitu.com/en/pc?download=pc\""
      },
      {
        "title": "Multi-Step Navigation",
        "body": "# Homepage - PC version - Download\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://xiuxiu.meitu.com/\" \\\n  --auto-navigate  # Enable (default: True)"
      },
      {
        "title": "Manual Selector (Fallback)",
        "body": "# If auto-detection fails\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://example.com/download\" \\\n  --selector \"button:has-text('Download for free')\""
      },
      {
        "title": "Disable Features",
        "body": "# Don't navigate to platform pages\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://example.com\" \\\n  --no-auto-navigate\n\n# Don't detect platform\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://example.com\" \\\n  --no-auto-select"
      },
      {
        "title": "Platform Detection",
        "body": "SystemArchitectureKeywords UsedWindowsAMD64/x86_64windows, win64, x64, 64-bit, pcWindowsx86/i686windows, win32, x86, 32-bit, pcmacOSARM64 (M1/M2/M3)macos, arm64, apple siliconmacOSx86_64 (Intel)macos, x64, intelLinuxx86_64linux, x64, amd64"
      },
      {
        "title": "Troubleshooting",
        "body": "Download not starting:\n\nUse --headless (default: False) to observe the process\nCheck stderr for auto-download messages\nTry --no-auto-navigate if navigation is causing issues\nUse --selector to manually specify button\n\nWrong version downloaded:\n\nCheck platform detection in stderr output\nUse --no-auto-select and manually specify --selector\nVerify the site offers multiple versions\n\nNavigation going to wrong page:\n\nDisable with --no-auto-navigate\nThe site may not have platform-specific pages\n\nFile not saved:\n\nCheck write permissions in output directory\nEnsure sufficient disk space\nWait for large files (up to 3 minutes)"
      },
      {
        "title": "stderr (Progress)",
        "body": "Starting browser (visible)...\nOpening: https://example.com\nChecking for auto-downloads...\nChecking for platform-specific page link...\nFound platform page: https://pc.example.com\nNavigating to platform page...\nDownload detected: software_v2.1.0_win64.exe\nSaving: software_v2.1.0_win64.exe\n\nSUCCESS!\nFile: C:\\Users\\User\\Downloads\\software_v2.1.0_win64.exe\nSize: 231.9 MB"
      },
      {
        "title": "stdout (JSON result)",
        "body": "{\n  \"path\": \"C:\\\\Users\\\\User\\\\Downloads\\\\software_v2.1.0_win64.exe\",\n  \"filename\": \"software_v2.1.0_win64.exe\",\n  \"size_bytes\": 243209941,\n  \"size_mb\": 231.9,\n  \"platform\": \"Windows AMD64\"\n}"
      },
      {
        "title": "Meitu Xiuxiu (Multi-step + Auto-download)",
        "body": "from auto_download import quick_download_meitu\n\nresult = quick_download_meitu()\n# Flow: Homepage - PC page link - Navigate - Auto-download"
      },
      {
        "title": "WeChat DevTools (Button click)",
        "body": "from auto_download import quick_download_wechat_devtools\n\nresult = quick_download_wechat_devtools()\n# Flow: Homepage - Click \"Stable Windows 64\" - Download"
      },
      {
        "title": "Generic Software (Mixed)",
        "body": "result = auto_download(\n    url=\"https://example.com/downloads\",\n    auto_select=True,    # Detect Windows 64-bit\n    auto_navigate=True   # Find \"Desktop version\" link\n)"
      },
      {
        "title": "Requirements",
        "body": "pip install playwright\nplaywright install chromium"
      },
      {
        "title": "Custom Platform Keywords",
        "body": "Modify get_system_preference() in the script to add custom keywords."
      },
      {
        "title": "Integration with Scripts",
        "body": "import subprocess\nimport json\n\nresult = subprocess.run([\n    'python', 'skills/browser-auto-download/scripts/auto_download.py',\n    '--url', 'https://example.com/download'\n], capture_output=True, text=True)\n\nif result.returncode == 0:\n    data = json.loads(result.stdout)\n    print(f\"Downloaded: {data['path']}\")  # Use the file"
      },
      {
        "title": "Batch Downloads",
        "body": "urls = [\n    \"https://example1.com/download\",\n    \"https://example2.com/download\",\n    \"https://example3.com/download\"\n]\n\nfor url in urls:\n    result = auto_download(url)\n    if result:\n        print(f\"Success: {result['filename']}\")"
      }
    ],
    "body": "Browser Auto Download v4.1.0 (Enhanced)\n\nDownload files from dynamic webpages with intelligent detection and multi-step navigation.\n\nKey Features\nAuto-download capture: Detects downloads triggered automatically on page load\nMulti-step navigation: Finds and navigates to platform-specific pages (PC/Desktop versions)\nPlatform auto-detection: Windows x64/ARM64, macOS Intel/Apple Silicon, Linux\nEvent listening: Captures all download events without requiring button clicks\nSmart fallback: Tries multiple strategies (auto-download, navigation, clicking)\nWhen to Use\n\nUse this skill for:\n\nAuto-download sites: Downloads start automatically when page loads\nMulti-step flows: Homepage - click \"PC version\" - download page\nDynamic content: Download links generated via JavaScript\nInteractive downloads: Requires clicking buttons or navigating UI\n\nNOT for: Direct file URLs (use curl/wget instead)\n\nQuick Start\nOption 1: Automatic (Recommended)\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://example.com/download\"\n\n\nThe script will:\n\nCheck for auto-downloads on page load\nLook for platform-specific page links (PC/Desktop version)\nNavigate if needed\nTry clicking download buttons as fallback\nOption 2: Built-in Shortcuts\n# WeChat DevTools\npython skills/browser-auto-download/scripts/auto_download.py --wechat\n\n# Meitu Xiuxiu\npython skills/browser-auto-download/scripts/auto_download.py --meitu\n\nOption 3: Python Module\nfrom skills.browser-auto-download.scripts.auto_download import auto_download\n\nresult = auto_download(\n    url=\"https://example.com/download\",\n    auto_select=True,   # Platform detection\n    auto_navigate=True  # Multi-step navigation\n)\n\nif result:\n    print(f\"Downloaded: {result['path']}\")\n\nHow It Works\nThree-Stage Strategy\n\nStage 1: Auto-Download Detection\n\nPage loads - Check for downloads - Success?\n    Yes:                    No:\n    Save file               Go to Stage 2\n\n\nStage 2: Multi-Step Navigation\n\nLook for \"PC/Desktop\" link - Navigate - Check downloads - Success?\n    Yes:                        No:\n    Save file                  Go to Stage 3\n\n\nStage 3: Button Clicking\n\nTry multiple selectors - Click - Wait for download - Save\n\nPlatform-Specific Page Detection\n\nAutomatically finds links like:\n\n\"meitu for PC\" - pc.meitu.com\n\"Desktop version\" - desktop.example.com\n\"Windows Download\" - windows.example.com\n\nKeywords: pc, desktop, windows, mac, download, 电脑, 桌面, 客户端\n\nExamples\nAuto-Download Sites (Best Case)\n# Sites that trigger download on page load\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://pc.meitu.com/en/pc?download=pc\"\n\nMulti-Step Navigation\n# Homepage - PC version - Download\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://xiuxiu.meitu.com/\" \\\n  --auto-navigate  # Enable (default: True)\n\nManual Selector (Fallback)\n# If auto-detection fails\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://example.com/download\" \\\n  --selector \"button:has-text('Download for free')\"\n\nDisable Features\n# Don't navigate to platform pages\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://example.com\" \\\n  --no-auto-navigate\n\n# Don't detect platform\npython skills/browser-auto-download/scripts/auto_download.py \\\n  --url \"https://example.com\" \\\n  --no-auto-select\n\nPlatform Detection\nSystem\tArchitecture\tKeywords Used\nWindows\tAMD64/x86_64\twindows, win64, x64, 64-bit, pc\nWindows\tx86/i686\twindows, win32, x86, 32-bit, pc\nmacOS\tARM64 (M1/M2/M3)\tmacos, arm64, apple silicon\nmacOS\tx86_64 (Intel)\tmacos, x64, intel\nLinux\tx86_64\tlinux, x64, amd64\nTroubleshooting\n\nDownload not starting:\n\nUse --headless (default: False) to observe the process\nCheck stderr for auto-download messages\nTry --no-auto-navigate if navigation is causing issues\nUse --selector to manually specify button\n\nWrong version downloaded:\n\nCheck platform detection in stderr output\nUse --no-auto-select and manually specify --selector\nVerify the site offers multiple versions\n\nNavigation going to wrong page:\n\nDisable with --no-auto-navigate\nThe site may not have platform-specific pages\n\nFile not saved:\n\nCheck write permissions in output directory\nEnsure sufficient disk space\nWait for large files (up to 3 minutes)\nOutput Format\nstderr (Progress)\nStarting browser (visible)...\nOpening: https://example.com\nChecking for auto-downloads...\nChecking for platform-specific page link...\nFound platform page: https://pc.example.com\nNavigating to platform page...\nDownload detected: software_v2.1.0_win64.exe\nSaving: software_v2.1.0_win64.exe\n\nSUCCESS!\nFile: C:\\Users\\User\\Downloads\\software_v2.1.0_win64.exe\nSize: 231.9 MB\n\nstdout (JSON result)\n{\n  \"path\": \"C:\\\\Users\\\\User\\\\Downloads\\\\software_v2.1.0_win64.exe\",\n  \"filename\": \"software_v2.1.0_win64.exe\",\n  \"size_bytes\": 243209941,\n  \"size_mb\": 231.9,\n  \"platform\": \"Windows AMD64\"\n}\n\nReal-World Examples\nMeitu Xiuxiu (Multi-step + Auto-download)\nfrom auto_download import quick_download_meitu\n\nresult = quick_download_meitu()\n# Flow: Homepage - PC page link - Navigate - Auto-download\n\nWeChat DevTools (Button click)\nfrom auto_download import quick_download_wechat_devtools\n\nresult = quick_download_wechat_devtools()\n# Flow: Homepage - Click \"Stable Windows 64\" - Download\n\nGeneric Software (Mixed)\nresult = auto_download(\n    url=\"https://example.com/downloads\",\n    auto_select=True,    # Detect Windows 64-bit\n    auto_navigate=True   # Find \"Desktop version\" link\n)\n\nRequirements\npip install playwright\nplaywright install chromium\n\nAdvanced Usage\nCustom Platform Keywords\n\nModify get_system_preference() in the script to add custom keywords.\n\nIntegration with Scripts\nimport subprocess\nimport json\n\nresult = subprocess.run([\n    'python', 'skills/browser-auto-download/scripts/auto_download.py',\n    '--url', 'https://example.com/download'\n], capture_output=True, text=True)\n\nif result.returncode == 0:\n    data = json.loads(result.stdout)\n    print(f\"Downloaded: {data['path']}\")  # Use the file\n\nBatch Downloads\nurls = [\n    \"https://example1.com/download\",\n    \"https://example2.com/download\",\n    \"https://example3.com/download\"\n]\n\nfor url in urls:\n    result = auto_download(url)\n    if result:\n        print(f\"Success: {result['filename']}\")"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Aaronxx/browser-auto-download",
    "publisherUrl": "https://clawhub.ai/Aaronxx/browser-auto-download",
    "owner": "Aaronxx",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/browser-auto-download",
    "downloadUrl": "https://openagent3.xyz/downloads/browser-auto-download",
    "agentUrl": "https://openagent3.xyz/skills/browser-auto-download/agent",
    "manifestUrl": "https://openagent3.xyz/skills/browser-auto-download/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/browser-auto-download/agent.md"
  }
}