From remix-browser
Use Chrome, use the browser, open a website, browse the web, go to a URL, take a screenshot of a page, test a web app, check a website, fill out forms, scrape a webpage, interact with a web page, debug a UI, inspect the DOM, run JavaScript in the browser, monitor network requests, or automate any browser task. Headless Chrome automation via CDP.
How this skill is triggered — by the user, by Claude, or both
Slash command
/remix-browser:browseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use the remix-browser MCP tools (prefixed `mcp__remix-browser__`) for all browser tasks.
Use the remix-browser MCP tools (prefixed mcp__remix-browser__) for all browser tasks.
How to use run_script effectively:
run_script for ALL browser interactions — it's much faster than individual tool calls.[ref=eN] refs immediately.page.snapshot(), use [ref=eN] selectors with page.click('[ref=e0]'), page.type('[ref=e1]', 'text'), etc.run_script to learn the UI and selectors. Then batch all remaining repetitive work into a single run_script with a loop.page.wait(ms) inside scripts for timing — don't use Bash sleep.page.waitForNetworkIdle({timeout:30000, idle:500}) to wait for all network requests to complete.Snapshot format (ARIA roles):
heading, link, textbox, button, combobox, checkbox, radio, etc.[ref=eN] — headings and landmarks appear for context without refs.[checked], [disabled], [expanded], [required]When to use granular tools instead:
click, type_text, etc.).snapshot separately.Available tools:
navigate, go_back, go_forward, reload, get_page_infofind_elements, get_text, get_html, wait_forsnapshotclick, type_text, hover, select_option, press_key, scrollscreenshotexecute_js, read_consolenetwork_enable, get_network_lognew_tab, close_tab, list_tabsrun_scriptnpx claudepluginhub hkd987/remix-browser --plugin remix-browserControls a live Chrome browser via puppeteer-core for automation, testing, and performance auditing. Use for clicking, typing, screenshots, DOM/AX tree, network interception, HAR export, Lighthouse audits, and device emulation.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.