{
  "schemaVersion": "1.0",
  "item": {
    "slug": "selenium-browser",
    "name": "Selenium Browser",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/andreybespalov89/selenium-browser",
    "canonicalUrl": "https://clawhub.ai/andreybespalov89/selenium-browser",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/selenium-browser",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=selenium-browser",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/setup.md",
      "scripts/launch_browser.py"
    ],
    "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",
      "slug": "selenium-browser",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-08T14:54:34.487Z",
      "expiresAt": "2026-05-15T14:54:34.487Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=selenium-browser",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=selenium-browser",
        "contentDisposition": "attachment; filename=\"selenium-browser-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "selenium-browser"
      },
      "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/selenium-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/selenium-browser",
    "agentPageUrl": "https://openagent3.xyz/skills/selenium-browser/agent",
    "manifestUrl": "https://openagent3.xyz/skills/selenium-browser/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/selenium-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": "Usage",
        "body": "The skill triggers on any message that contains Chrome, browser, Selenium, screenshot, or open.\n\nselenium-browser <URL> [--headless] [--proxy=<url>]"
      },
      {
        "title": "Command flow",
        "body": "Launch Chrome (or Chromium) under Selenium.\nNavigate to <URL>.\nTake a screenshot of the loaded page.\nSave the image in /home/main/clawd/diffusion_pdfs/ and report the path back to the chat.\nIf anything fails, send an error message."
      },
      {
        "title": "scripts/launch_browser.py",
        "body": "#!/usr/bin/env python3\nimport os\nimport sys\nimport time\nimport base64\nfrom selenium import webdriver\nfrom selenium.webdriver.chrome.service import Service\nfrom selenium.webdriver.chrome.options import Options\n\n# CLI parsing\nimport argparse\nparser = argparse.ArgumentParser(description=\"Launch Selenium Chrome and take a screenshot.\")\nparser.add_argument(\"url\", help=\"URL to open\")\nparser.add_argument(\"--headless\", action=\"store_true\", help=\"Run Chrome headless\")\nparser.add_argument(\"--proxy\", help=\"Proxy URL (e.g., http://proxy:3128)\")\nargs = parser.parse_args()\n\n# Prepare Chrome options\nchrome_options = Options()\nif args.headless:\n    chrome_options.add_argument(\"--headless\")\nchrome_options.add_argument(\"--disable-gpu\")\nchrome_options.add_argument(\"--no-sandbox\")\nchrome_options.add_argument(\"--disable-dev-shm-usage\")\nif args.proxy:\n    chrome_options.add_argument(f\"--proxy-server={args.proxy}\")\n\n# Locate binaries\nchrome_bin = os.getenv(\"CHROME_BIN\", \"/usr/bin/google-chrome\")\nchromedriver_path = os.getenv(\"CHROMEDRIVER_PATH\", \"/usr/local/bin/chromedriver\")\n\nservice = Service(executable_path=chromedriver_path)\n\n# Start browser\ntry:\n    driver = webdriver.Chrome(service=service, options=chrome_options)\nexcept Exception as e:\n    print(f\"❌ Failed to start Chrome: {e}\", file=sys.stderr)\n    sys.exit(1)\n\n# Navigate and wait for page load\ntry:\n    driver.get(args.url)\n    time.sleep(5)  # simple wait; can replace with WebDriverWait for better reliability\nexcept Exception as e:\n    print(f\"❌ Navigation error: {e}\", file=sys.stderr)\n    driver.quit()\n    sys.exit(1)\n\n# Take screenshot\nscreenshot_path = os.path.join(os.getenv(\"HOME\", \"/tmp\"), \"screenshot.png\")\ntry:\n    driver.save_screenshot(screenshot_path)\nexcept Exception as e:\n    print(f\"❌ Screenshot error: {e}\", file=sys.stderr)\n    driver.quit()\n    sys.exit(1)\n\n# Clean up\ndriver.quit()\n\n# Output a JSON object that OpenClaw can parse for the reply\nprint({\"status\": \"ok\", \"screenshot\": screenshot_path})"
      },
      {
        "title": "scripts/_env.sh",
        "body": "# Optional: set paths to Chrome/Chromedriver if not in standard locations\n# export CHROME_BIN=\"/opt/google/chrome/google-chrome\"\n# export CHROMEDRIVER_PATH=\"/usr/local/bin/chromedriver\""
      },
      {
        "title": "References",
        "body": "Selenium docs\nChromeDriver download page"
      },
      {
        "title": "How the skill reports",
        "body": "The skill runs the Python script and captures its stdout as a JSON payload.  OpenClaw parses the JSON and sends a message back:\n\n✅ Screenshot saved: /home/main/clawd/diffusion_pdfs/screenshot.png\n\nIf the script prints an error, the skill forwards the error text."
      },
      {
        "title": "Installation notes",
        "body": "Make sure chromedriver is in /usr/local/bin/chromedriver or set CHROMEDRIVER_PATH.\nMake sure google-chrome (or chromium) is in /usr/bin/google-chrome or set CHROME_BIN.\nInstall Python dependencies: pip install selenium (inside the virtual env you use for the skill).\n\npip install selenium"
      },
      {
        "title": "Logging & timeouts",
        "body": "The script uses a 5‑second static wait after navigation; replace with Selenium's WebDriverWait for dynamic waits.\n\nIf you encounter timeouts, adjust the time.sleep(5) value or use WebDriverWait(driver, 20).until(...).\n\nFeel free to tweak the script to fit your environment (proxy, authentication, etc.)."
      }
    ],
    "body": "Usage\n\nThe skill triggers on any message that contains Chrome, browser, Selenium, screenshot, or open.\n\nselenium-browser <URL> [--headless] [--proxy=<url>]\n\nCommand flow\nLaunch Chrome (or Chromium) under Selenium.\nNavigate to <URL>.\nTake a screenshot of the loaded page.\nSave the image in /home/main/clawd/diffusion_pdfs/ and report the path back to the chat.\nIf anything fails, send an error message.\nScripts\nscripts/launch_browser.py\n#!/usr/bin/env python3\nimport os\nimport sys\nimport time\nimport base64\nfrom selenium import webdriver\nfrom selenium.webdriver.chrome.service import Service\nfrom selenium.webdriver.chrome.options import Options\n\n# CLI parsing\nimport argparse\nparser = argparse.ArgumentParser(description=\"Launch Selenium Chrome and take a screenshot.\")\nparser.add_argument(\"url\", help=\"URL to open\")\nparser.add_argument(\"--headless\", action=\"store_true\", help=\"Run Chrome headless\")\nparser.add_argument(\"--proxy\", help=\"Proxy URL (e.g., http://proxy:3128)\")\nargs = parser.parse_args()\n\n# Prepare Chrome options\nchrome_options = Options()\nif args.headless:\n    chrome_options.add_argument(\"--headless\")\nchrome_options.add_argument(\"--disable-gpu\")\nchrome_options.add_argument(\"--no-sandbox\")\nchrome_options.add_argument(\"--disable-dev-shm-usage\")\nif args.proxy:\n    chrome_options.add_argument(f\"--proxy-server={args.proxy}\")\n\n# Locate binaries\nchrome_bin = os.getenv(\"CHROME_BIN\", \"/usr/bin/google-chrome\")\nchromedriver_path = os.getenv(\"CHROMEDRIVER_PATH\", \"/usr/local/bin/chromedriver\")\n\nservice = Service(executable_path=chromedriver_path)\n\n# Start browser\ntry:\n    driver = webdriver.Chrome(service=service, options=chrome_options)\nexcept Exception as e:\n    print(f\"❌ Failed to start Chrome: {e}\", file=sys.stderr)\n    sys.exit(1)\n\n# Navigate and wait for page load\ntry:\n    driver.get(args.url)\n    time.sleep(5)  # simple wait; can replace with WebDriverWait for better reliability\nexcept Exception as e:\n    print(f\"❌ Navigation error: {e}\", file=sys.stderr)\n    driver.quit()\n    sys.exit(1)\n\n# Take screenshot\nscreenshot_path = os.path.join(os.getenv(\"HOME\", \"/tmp\"), \"screenshot.png\")\ntry:\n    driver.save_screenshot(screenshot_path)\nexcept Exception as e:\n    print(f\"❌ Screenshot error: {e}\", file=sys.stderr)\n    driver.quit()\n    sys.exit(1)\n\n# Clean up\ndriver.quit()\n\n# Output a JSON object that OpenClaw can parse for the reply\nprint({\"status\": \"ok\", \"screenshot\": screenshot_path})\n\nscripts/_env.sh\n# Optional: set paths to Chrome/Chromedriver if not in standard locations\n# export CHROME_BIN=\"/opt/google/chrome/google-chrome\"\n# export CHROMEDRIVER_PATH=\"/usr/local/bin/chromedriver\"\n\nReferences\nSelenium docs\nChromeDriver download page\nHow the skill reports\n\nThe skill runs the Python script and captures its stdout as a JSON payload. OpenClaw parses the JSON and sends a message back:\n\n✅ Screenshot saved: /home/main/clawd/diffusion_pdfs/screenshot.png\n\n\nIf the script prints an error, the skill forwards the error text.\n\nInstallation notes\nMake sure chromedriver is in /usr/local/bin/chromedriver or set CHROMEDRIVER_PATH.\nMake sure google-chrome (or chromium) is in /usr/bin/google-chrome or set CHROME_BIN.\nInstall Python dependencies: pip install selenium (inside the virtual env you use for the skill).\npip install selenium\n\nLogging & timeouts\n\nThe script uses a 5‑second static wait after navigation; replace with Selenium's WebDriverWait for dynamic waits.\n\nIf you encounter timeouts, adjust the time.sleep(5) value or use WebDriverWait(driver, 20).until(...).\n\nFeel free to tweak the script to fit your environment (proxy, authentication, etc.)."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/andreybespalov89/selenium-browser",
    "publisherUrl": "https://clawhub.ai/andreybespalov89/selenium-browser",
    "owner": "andreybespalov89",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/selenium-browser",
    "downloadUrl": "https://openagent3.xyz/downloads/selenium-browser",
    "agentUrl": "https://openagent3.xyz/skills/selenium-browser/agent",
    "manifestUrl": "https://openagent3.xyz/skills/selenium-browser/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/selenium-browser/agent.md"
  }
}