From qe-framework
Controls a headless browser via CLI for navigation, form filling, clicking, screenshots, data extraction, and web app testing.
How this skill is triggered — by the user, by Claude, or both
Slash command
/qe-framework:Qagent-browserThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Before executing browser automation, verify the tool is installed:
Before executing browser automation, verify the tool is installed:
npx agent-browser --version 2>/dev/null || echo "NOT INSTALLED"
If installed: proceed with automation. If NOT installed:
agent-browser is not installed.
Installation: npm install -g agent-browser
Do NOT attempt to run browser commands without the package installed.
agent-browser open <url>agent-browser snapshot -i (get @e1, @e2 refs)agent-browser open <url>
agent-browser snapshot -i
agent-browser click @e1
agent-browser fill @e2 "text"
agent-browser select @e1 "option"
agent-browser press Enter
agent-browser scroll down 500
agent-browser get text @e1
agent-browser get url
agent-browser wait @e1
agent-browser wait --load networkidle
agent-browser screenshot
agent-browser screenshot --full
agent-browser screenshot --annotate
agent-browser diff snapshot
agent-browser close
agent-browser open https://example.com/form
agent-browser snapshot -i
agent-browser fill @e1 "Jane"
agent-browser fill @e2 "[email protected]"
agent-browser click @e5
agent-browser wait --load networkidle
--content-boundaries: Wrap content in markersAGENT_BROWSER_ALLOWED_DOMAINS: Restrict navigationagent-browser close
npx claudepluginhub inho-team/qe-framework --plugin qe-frameworkCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.