headless-browser

Headless Browser (OpenClaw Browser Tool)

Use this skill when the user asks to:

• open a URL and extract visible text
• take a screenshot
• navigate JS-heavy sites

Policy / constraints

• Do not attempt to bypass logins, paywalls, or bot protections.
• Do not use stealth plugins or "anti-bot evasion" techniques.
• If a page is blocked, propose alternatives (official APIs, RSS, public mirrors, or ask the user to provide the content).

How to use (CLI)

Start the managed browser (if needed):

openclaw browser status
openclaw browser start

Open a page:

openclaw browser open "https://example.com"

Extract a snapshot (prefer --format md for readable output):

openclaw browser snapshot --format md --limit 200

Take a screenshot:

openclaw browser screenshot --full-page

Job search guidance

• Prefer public job boards and company career pages.
• If the user mentions LinkedIn, prefer public listings and metadata; do not attempt to access restricted pages.