pipeline_core/skills_library/all/browser-harness/SKILL.md

name	description
browser-harness	Use browser-harness for any web automation or scraping task.

browser-harness

Direct browser control via CDP. For setup, install, or connection problems, read https://github.com/browser-use/browser-harness/blob/main/install.md.

When Not to Use

A basic fetch of public information needs no browser. If a plain HTTP request can read it — a public page, an API, docs — use curl or your fetch tool. Use browser-harness when the task needs interaction (click, type, navigate), the user's logged-in session, JS rendering, or a bot-protected page.

Usage

browser-harness <<'PY'
print(page_info())
PY

• Invoke as browser-harness. Use heredocs for multi-line commands.
• Helpers are pre-imported. run.py calls ensure_daemon() before exec.
• First navigation is new_tab(url), not goto_url(url).

Local Chrome

browser-harness --doctor

If Chrome is not running, the harness launches it automatically. If remote debugging is not enabled, it opens chrome://inspect/#remote-debugging — ask user to tick the checkbox.

Remote Browsers

browser-harness auth login
browser-harness <<'PY'
start_remote_daemon("r7k2")
PY

Then: BU_NAME=r7k2 browser-harness <<'PY' ... PY

Key Helpers

page_info() new_tab(url) click(sel) type(sel,text) screenshot() extract(sel) evaluate(js) wait(ms) wait_for(sel) navigate(url) close_tab() switch_tab(i) tabs() scroll(dir,amt) press(key) fill_form(fields) upload_file(sel,path)

Use browser-harness <<'PY' ... PY for multi-line scripts.