# Send Selenium Browser to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "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": { "downloadUrl": "/downloads/selenium-browser", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=selenium-browser", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "references/setup.md", "scripts/launch_browser.py" ], "downloadMode": "redirect", "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." ] } }, "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" } } ``` ## Documentation ### Usage The skill triggers on any message that contains Chrome, browser, Selenium, screenshot, or open. selenium-browser [--headless] [--proxy=] ### Command flow Launch Chrome (or Chromium) under Selenium. Navigate to . Take a screenshot of the loaded page. Save the image in /home/main/clawd/diffusion_pdfs/ and report the path back to the chat. If anything fails, send an error message. ### scripts/launch_browser.py #!/usr/bin/env python3 import os import sys import time import base64 from selenium import webdriver from selenium.webdriver.chrome.service import Service from selenium.webdriver.chrome.options import Options # CLI parsing import argparse parser = argparse.ArgumentParser(description="Launch Selenium Chrome and take a screenshot.") parser.add_argument("url", help="URL to open") parser.add_argument("--headless", action="store_true", help="Run Chrome headless") parser.add_argument("--proxy", help="Proxy URL (e.g., http://proxy:3128)") args = parser.parse_args() # Prepare Chrome options chrome_options = Options() if args.headless: chrome_options.add_argument("--headless") chrome_options.add_argument("--disable-gpu") chrome_options.add_argument("--no-sandbox") chrome_options.add_argument("--disable-dev-shm-usage") if args.proxy: chrome_options.add_argument(f"--proxy-server={args.proxy}") # Locate binaries chrome_bin = os.getenv("CHROME_BIN", "/usr/bin/google-chrome") chromedriver_path = os.getenv("CHROMEDRIVER_PATH", "/usr/local/bin/chromedriver") service = Service(executable_path=chromedriver_path) # Start browser try: driver = webdriver.Chrome(service=service, options=chrome_options) except Exception as e: print(f"❌ Failed to start Chrome: {e}", file=sys.stderr) sys.exit(1) # Navigate and wait for page load try: driver.get(args.url) time.sleep(5) # simple wait; can replace with WebDriverWait for better reliability except Exception as e: print(f"❌ Navigation error: {e}", file=sys.stderr) driver.quit() sys.exit(1) # Take screenshot screenshot_path = os.path.join(os.getenv("HOME", "/tmp"), "screenshot.png") try: driver.save_screenshot(screenshot_path) except Exception as e: print(f"❌ Screenshot error: {e}", file=sys.stderr) driver.quit() sys.exit(1) # Clean up driver.quit() # Output a JSON object that OpenClaw can parse for the reply print({"status": "ok", "screenshot": screenshot_path}) ### scripts/_env.sh # Optional: set paths to Chrome/Chromedriver if not in standard locations # export CHROME_BIN="/opt/google/chrome/google-chrome" # export CHROMEDRIVER_PATH="/usr/local/bin/chromedriver" ### References Selenium docs ChromeDriver download page ### How the skill reports The skill runs the Python script and captures its stdout as a JSON payload. OpenClaw parses the JSON and sends a message back: ✅ Screenshot saved: /home/main/clawd/diffusion_pdfs/screenshot.png If the script prints an error, the skill forwards the error text. ### Installation notes Make sure chromedriver is in /usr/local/bin/chromedriver or set CHROMEDRIVER_PATH. Make sure google-chrome (or chromium) is in /usr/bin/google-chrome or set CHROME_BIN. Install Python dependencies: pip install selenium (inside the virtual env you use for the skill). pip install selenium ### Logging & timeouts The script uses a 5‑second static wait after navigation; replace with Selenium's WebDriverWait for dynamic waits. If you encounter timeouts, adjust the time.sleep(5) value or use WebDriverWait(driver, 20).until(...). Feel free to tweak the script to fit your environment (proxy, authentication, etc.). ## Trust - Source: tencent - Verification: Indexed source record - Publisher: andreybespalov89 - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-08T14:54:34.487Z - Expires at: 2026-05-15T14:54:34.487Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/selenium-browser) - [Send to Agent page](https://openagent3.xyz/skills/selenium-browser/agent) - [JSON manifest](https://openagent3.xyz/skills/selenium-browser/agent.json) - [Markdown brief](https://openagent3.xyz/skills/selenium-browser/agent.md) - [Download page](https://openagent3.xyz/downloads/selenium-browser)