Agent skill

headless-browser

Browse JS-heavy sites and extract text/snapshots using OpenClaw's built-in browser tool (no stealth).

Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/headless-browser

Metadata

Additional technical details for this skill

openclaw
{
    "emoji": "\ud83c\udf10",
    "requires": {
        "bins": [
            "openclaw"
        ]
    }
}

SKILL.md

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):

bash
openclaw browser status
openclaw browser start

Open a page:

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

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

bash
openclaw browser snapshot --format md --limit 200

Take a screenshot:

bash
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.

Expand your agent's capabilities with these related and highly-rated skills.

Didn't find tool you were looking for?

Be as detailed as possible for better results