{
  "schemaVersion": "1.0",
  "item": {
    "slug": "claw-browser",
    "name": "Claw Browser",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/Canbirlik/claw-browser",
    "canonicalUrl": "https://clawhub.ai/Canbirlik/claw-browser",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/claw-browser",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claw-browser",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "browser.py",
      "requirements.txt",
      "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": "2026-04-23T16:43:11.935Z",
      "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/claw-browser"
    },
    "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/claw-browser",
    "agentPageUrl": "https://openagent3.xyz/skills/claw-browser/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claw-browser/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claw-browser/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": "🌐 Claw Browser Skill",
        "body": "This skill gives the agent \"Eyes\" to browse the web using a real\nChromium browser.\n\nUnlike simple HTTP requests, claw-browser:\n\nRenders JavaScript\nHandles dynamic content\nLoads SPA applications\nTakes real screenshots\nCan run in visible (non-headless) mode"
      },
      {
        "title": "🛠️ Installation & Setup (READ FIRST)",
        "body": "⚠️ Before using this tool, the agent MUST set up the Python\nenvironment and download browser binaries.\n\nIf venv does not exist, run this setup command block automatically:\n\n# 1. Create virtual environment\npython3 -m venv venv\n\n# 2. Activate it\nsource venv/bin/activate\n\n# 3. Install dependencies\npip install -r requirements.txt\n\n# 4. Download Chromium binaries (CRITICAL STEP)\nplaywright install chromium\n\n⚠️ The playwright install chromium step is CRITICAL.\nWithout it, the browser will NOT launch."
      },
      {
        "title": "Arguments",
        "body": "Argument                            Description\n\n--url                             The website to visit (Required)\n\n--action                          Action to perform: read or\nscreenshot"
      },
      {
        "title": "🚀 Execution Examples",
        "body": "⚠️ Always activate the virtual environment first."
      },
      {
        "title": "1️⃣ Read a Page (Headless - Default)",
        "body": "source venv/bin/activate && python browser.py --url \"https://github.com/trending\" --action read"
      },
      {
        "title": "2️⃣ Take a Screenshot of a News Site",
        "body": "source venv/bin/activate && python browser.py --url \"https://news.ycombinator.com\" --action screenshot\n\nThis saves:\n\nevidence.png"
      },
      {
        "title": "3️⃣ Visible Mode (Shows Browser UI - Great for Demos)",
        "body": "source venv/bin/activate && python browser.py --url \"https://google.com\" --action read --visible\n\nThis will launch a real Chromium window on screen."
      },
      {
        "title": "4️⃣ Visible Mode (WSL / Linux Fix) ⭐️",
        "body": "Use this if you get \"Missing X server\" or \"Display not found\" errors:\n\nexport DISPLAY=:0 && source venv/bin/activate && python browser.py --url \"[https://google.com](https://google.com)\" --action read --visible\n\nThis sets the DISPLAY variable so the browser can open on your screen."
      },
      {
        "title": "🧠 When Should the Agent Use This Skill?",
        "body": "Use claw-browser when:\n\nThe page requires JavaScript rendering\nThe site is dynamic (React, Vue, Angular, etc.)\nScreenshots are required\nThe user explicitly asks to \"open\" or \"see\" a website\nTraditional HTTP requests fail"
      },
      {
        "title": "⚡ Summary",
        "body": "claw-browser transforms your OpenClaw agent from a simple API caller\ninto a real browser-powered assistant with visual capabilities.\n\nIt enables:\n\nDynamic page interaction\nVisual verification\nDemo-ready browsing\nReal-world automation\n\nMade with ❤️ by @canbirlik"
      }
    ],
    "body": "🌐 Claw Browser Skill\n\nThis skill gives the agent \"Eyes\" to browse the web using a real Chromium browser.\n\nUnlike simple HTTP requests, claw-browser:\n\nRenders JavaScript\nHandles dynamic content\nLoads SPA applications\nTakes real screenshots\nCan run in visible (non-headless) mode\n🛠️ Installation & Setup (READ FIRST)\n\n⚠️ Before using this tool, the agent MUST set up the Python environment and download browser binaries.\n\nIf venv does not exist, run this setup command block automatically:\n\n# 1. Create virtual environment\npython3 -m venv venv\n\n# 2. Activate it\nsource venv/bin/activate\n\n# 3. Install dependencies\npip install -r requirements.txt\n\n# 4. Download Chromium binaries (CRITICAL STEP)\nplaywright install chromium\n\n\n⚠️ The playwright install chromium step is CRITICAL.\nWithout it, the browser will NOT launch.\n\n🔧 Tools & Usage\nbrowser.py\nArguments\n\nArgument Description\n\n--url The website to visit (Required)\n\n--action Action to perform: read or screenshot\n\n--visible (Optional) Runs the browser in visible mode (NOT headless). Use if the user wants to see the browser.\n🚀 Execution Examples\n\n⚠️ Always activate the virtual environment first.\n\n1️⃣ Read a Page (Headless - Default)\nsource venv/bin/activate && python browser.py --url \"https://github.com/trending\" --action read\n\n2️⃣ Take a Screenshot of a News Site\nsource venv/bin/activate && python browser.py --url \"https://news.ycombinator.com\" --action screenshot\n\n\nThis saves:\n\nevidence.png\n\n3️⃣ Visible Mode (Shows Browser UI - Great for Demos)\nsource venv/bin/activate && python browser.py --url \"https://google.com\" --action read --visible\n\n\nThis will launch a real Chromium window on screen.\n\n4️⃣ Visible Mode (WSL / Linux Fix) ⭐️\n\nUse this if you get \"Missing X server\" or \"Display not found\" errors:\n\nexport DISPLAY=:0 && source venv/bin/activate && python browser.py --url \"[https://google.com](https://google.com)\" --action read --visible\n\n\nThis sets the DISPLAY variable so the browser can open on your screen.\n\n🧠 When Should the Agent Use This Skill?\n\nUse claw-browser when:\n\nThe page requires JavaScript rendering\nThe site is dynamic (React, Vue, Angular, etc.)\nScreenshots are required\nThe user explicitly asks to \"open\" or \"see\" a website\nTraditional HTTP requests fail\n⚡ Summary\n\nclaw-browser transforms your OpenClaw agent from a simple API caller into a real browser-powered assistant with visual capabilities.\n\nIt enables:\n\nDynamic page interaction\nVisual verification\nDemo-ready browsing\nReal-world automation\n\nMade with ❤️ by @canbirlik"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Canbirlik/claw-browser",
    "publisherUrl": "https://clawhub.ai/Canbirlik/claw-browser",
    "owner": "Canbirlik",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/claw-browser",
    "downloadUrl": "https://openagent3.xyz/downloads/claw-browser",
    "agentUrl": "https://openagent3.xyz/skills/claw-browser/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claw-browser/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claw-browser/agent.md"
  }
}