{
  "schemaVersion": "1.0",
  "item": {
    "slug": "browser-automation-2",
    "name": "Browser Automation",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/femto/browser-automation-2",
    "canonicalUrl": "https://clawhub.ai/femto/browser-automation-2",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/browser-automation-2",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browser-automation-2",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "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. 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/browser-automation-2"
    },
    "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-automation-2",
    "agentPageUrl": "https://openagent3.xyz/skills/browser-automation-2/agent",
    "manifestUrl": "https://openagent3.xyz/skills/browser-automation-2/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/browser-automation-2/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": "Browser Automation (Chrome MCP Server)",
        "body": "Turn your Chrome browser into your intelligent assistant - Let AI take control of your browser."
      },
      {
        "title": "When to Use This Skill",
        "body": "Use this skill when the user:\n\nWants to automate browser tasks (clicking, filling forms, navigating)\nNeeds to take screenshots of web pages or elements\nWants to extract content from web pages\nAsks to search browsing history or manage bookmarks\nNeeds to monitor network requests\nWants AI to interact with websites using their existing login sessions"
      },
      {
        "title": "Step 1: Install the Native Bridge",
        "body": "npm install -g mcp-chrome-bridger\n# or\npnpm install -g mcp-chrome-bridger\nmcp-chrome-bridger register"
      },
      {
        "title": "Step 2: Install Chrome Extension",
        "body": "Download from GitHub Releases:\n\nDownload mcp-chrome-extension-vX.X.X.zip\nOpen Chrome → chrome://extensions/\nEnable \"Developer mode\"\nClick \"Load unpacked\" and select the extracted folder\nClick the extension icon → Click \"Connect\""
      },
      {
        "title": "Step 3: Configure MCP Client",
        "body": "Add to your MCP client configuration:\n\nStreamable HTTP (Recommended):\n\n{\n  \"mcpServers\": {\n    \"chrome-mcp-server\": {\n      \"type\": \"http\",\n      \"url\": \"http://127.0.0.1:12306/mcp\"\n    }\n  }\n}\n\nSTDIO (Alternative):\n\n{\n  \"mcpServers\": {\n    \"chrome-mcp-server\": {\n      \"command\": \"npx\",\n      \"args\": [\"mcp-chrome-bridger\", \"stdio\"]\n    }\n  }\n}"
      },
      {
        "title": "Browser Management",
        "body": "ToolDescriptionget_windows_and_tabsList all browser windows and tabschrome_navigateNavigate to URLs, control viewportchrome_switch_tabSwitch active tabchrome_close_tabsClose specific tabschrome_go_back_or_forwardBrowser history navigation"
      },
      {
        "title": "Screenshots",
        "body": "ToolDescriptionchrome_screenshotCapture full page, viewport, or specific elements"
      },
      {
        "title": "Content Analysis",
        "body": "ToolDescriptionchrome_get_web_contentExtract HTML/text from pageschrome_get_interactive_elementsFind clickable elementssearch_tabs_contentAI-powered semantic search across tabschrome_consoleCapture browser console output"
      },
      {
        "title": "Interaction",
        "body": "ToolDescriptionchrome_click_elementClick elements via CSS selectorchrome_fill_or_selectFill forms and select optionschrome_keyboardSimulate keyboard input"
      },
      {
        "title": "Data Management",
        "body": "ToolDescriptionchrome_historySearch browsing historychrome_bookmark_searchFind bookmarkschrome_bookmark_addAdd new bookmarkschrome_bookmark_deleteDelete bookmarks"
      },
      {
        "title": "Network",
        "body": "ToolDescriptionchrome_network_capture_start/stopMonitor network requestschrome_network_requestSend HTTP requests with browser cookies"
      },
      {
        "title": "Navigate and Screenshot",
        "body": "User: \"Take a screenshot of github.com\"\n\nAI uses:\n1. chrome_navigate(url: \"https://github.com\")\n2. chrome_screenshot(fullPage: true)"
      },
      {
        "title": "Fill a Form",
        "body": "User: \"Login to my account on example.com\"\n\nAI uses:\n1. chrome_navigate(url: \"https://example.com/login\")\n2. chrome_fill_or_select(selector: \"#email\", value: \"user@example.com\")\n3. chrome_fill_or_select(selector: \"#password\", value: \"...\")\n4. chrome_click_element(selector: \"button[type=submit]\")"
      },
      {
        "title": "Search History",
        "body": "User: \"Find all pages I visited about React hooks last week\"\n\nAI uses:\n1. chrome_history(text: \"React hooks\", startTime: \"1 week ago\")"
      },
      {
        "title": "Extract Content",
        "body": "User: \"What does this page say about pricing?\"\n\nAI uses:\n1. chrome_get_web_content()\n2. Analyzes the extracted content"
      },
      {
        "title": "Advantages Over Playwright",
        "body": "FeaturePlaywright MCPChrome MCP ServerBrowser InstanceNew browser processYour existing ChromeLogin SessionsNeed to re-loginUses existing sessionsUser SettingsClean environmentYour bookmarks, extensions, settingsStartup TimeSlow (launch browser)Instant (extension already loaded)Resource UsageHeavyLightweight"
      },
      {
        "title": "Multi-Client Support",
        "body": "Multiple AI clients can connect simultaneously:\n\nClaude Code\nCursor\nKiro\nAny MCP-compatible client\n\nEach client gets its own session while sharing the same Chrome browser."
      },
      {
        "title": "Extension Not Connecting",
        "body": "Check extension is enabled in chrome://extensions/\nClick extension icon → Verify \"Connected\" status\nRestart Chrome if needed"
      },
      {
        "title": "Port Already in Use",
        "body": "The server automatically handles port conflicts. If issues persist:\n\nlsof -i :12306\nkill <PID>"
      },
      {
        "title": "Resources",
        "body": "GitHub: https://github.com/femto/mcp-chrome\nnpm: https://www.npmjs.com/package/mcp-chrome-bridger\nReleases: https://github.com/femto/mcp-chrome/releases"
      }
    ],
    "body": "Browser Automation (Chrome MCP Server)\n\nTurn your Chrome browser into your intelligent assistant - Let AI take control of your browser.\n\nWhen to Use This Skill\n\nUse this skill when the user:\n\nWants to automate browser tasks (clicking, filling forms, navigating)\nNeeds to take screenshots of web pages or elements\nWants to extract content from web pages\nAsks to search browsing history or manage bookmarks\nNeeds to monitor network requests\nWants AI to interact with websites using their existing login sessions\nInstallation\nStep 1: Install the Native Bridge\nnpm install -g mcp-chrome-bridger\n# or\npnpm install -g mcp-chrome-bridger\nmcp-chrome-bridger register\n\nStep 2: Install Chrome Extension\n\nDownload from GitHub Releases:\n\nDownload mcp-chrome-extension-vX.X.X.zip\nOpen Chrome → chrome://extensions/\nEnable \"Developer mode\"\nClick \"Load unpacked\" and select the extracted folder\nClick the extension icon → Click \"Connect\"\nStep 3: Configure MCP Client\n\nAdd to your MCP client configuration:\n\nStreamable HTTP (Recommended):\n\n{\n  \"mcpServers\": {\n    \"chrome-mcp-server\": {\n      \"type\": \"http\",\n      \"url\": \"http://127.0.0.1:12306/mcp\"\n    }\n  }\n}\n\n\nSTDIO (Alternative):\n\n{\n  \"mcpServers\": {\n    \"chrome-mcp-server\": {\n      \"command\": \"npx\",\n      \"args\": [\"mcp-chrome-bridger\", \"stdio\"]\n    }\n  }\n}\n\nAvailable Tools (20+)\nBrowser Management\nTool\tDescription\nget_windows_and_tabs\tList all browser windows and tabs\nchrome_navigate\tNavigate to URLs, control viewport\nchrome_switch_tab\tSwitch active tab\nchrome_close_tabs\tClose specific tabs\nchrome_go_back_or_forward\tBrowser history navigation\nScreenshots\nTool\tDescription\nchrome_screenshot\tCapture full page, viewport, or specific elements\nContent Analysis\nTool\tDescription\nchrome_get_web_content\tExtract HTML/text from pages\nchrome_get_interactive_elements\tFind clickable elements\nsearch_tabs_content\tAI-powered semantic search across tabs\nchrome_console\tCapture browser console output\nInteraction\nTool\tDescription\nchrome_click_element\tClick elements via CSS selector\nchrome_fill_or_select\tFill forms and select options\nchrome_keyboard\tSimulate keyboard input\nData Management\nTool\tDescription\nchrome_history\tSearch browsing history\nchrome_bookmark_search\tFind bookmarks\nchrome_bookmark_add\tAdd new bookmarks\nchrome_bookmark_delete\tDelete bookmarks\nNetwork\nTool\tDescription\nchrome_network_capture_start/stop\tMonitor network requests\nchrome_network_request\tSend HTTP requests with browser cookies\nExample Usage\nNavigate and Screenshot\nUser: \"Take a screenshot of github.com\"\n\nAI uses:\n1. chrome_navigate(url: \"https://github.com\")\n2. chrome_screenshot(fullPage: true)\n\nFill a Form\nUser: \"Login to my account on example.com\"\n\nAI uses:\n1. chrome_navigate(url: \"https://example.com/login\")\n2. chrome_fill_or_select(selector: \"#email\", value: \"user@example.com\")\n3. chrome_fill_or_select(selector: \"#password\", value: \"...\")\n4. chrome_click_element(selector: \"button[type=submit]\")\n\nSearch History\nUser: \"Find all pages I visited about React hooks last week\"\n\nAI uses:\n1. chrome_history(text: \"React hooks\", startTime: \"1 week ago\")\n\nExtract Content\nUser: \"What does this page say about pricing?\"\n\nAI uses:\n1. chrome_get_web_content()\n2. Analyzes the extracted content\n\nAdvantages Over Playwright\nFeature\tPlaywright MCP\tChrome MCP Server\nBrowser Instance\tNew browser process\tYour existing Chrome\nLogin Sessions\tNeed to re-login\tUses existing sessions\nUser Settings\tClean environment\tYour bookmarks, extensions, settings\nStartup Time\tSlow (launch browser)\tInstant (extension already loaded)\nResource Usage\tHeavy\tLightweight\nMulti-Client Support\n\nMultiple AI clients can connect simultaneously:\n\nClaude Code\nCursor\nKiro\nAny MCP-compatible client\n\nEach client gets its own session while sharing the same Chrome browser.\n\nTroubleshooting\nExtension Not Connecting\nCheck extension is enabled in chrome://extensions/\nClick extension icon → Verify \"Connected\" status\nRestart Chrome if needed\nPort Already in Use\n\nThe server automatically handles port conflicts. If issues persist:\n\nlsof -i :12306\nkill <PID>\n\nResources\nGitHub: https://github.com/femto/mcp-chrome\nnpm: https://www.npmjs.com/package/mcp-chrome-bridger\nReleases: https://github.com/femto/mcp-chrome/releases"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/femto/browser-automation-2",
    "publisherUrl": "https://clawhub.ai/femto/browser-automation-2",
    "owner": "femto",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/browser-automation-2",
    "downloadUrl": "https://openagent3.xyz/downloads/browser-automation-2",
    "agentUrl": "https://openagent3.xyz/skills/browser-automation-2/agent",
    "manifestUrl": "https://openagent3.xyz/skills/browser-automation-2/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/browser-automation-2/agent.md"
  }
}