Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

browser-act Browser Automation

A gateway skill for the browser-act CLI: fetch JS-rendered pages, keep logged-in sessions, automate forms, capture screenshots and network responses.

AutomationIntermediate★ 6,037⑂ 304AI score 8/10Last updated: Aug 24, 2026

What it does

  • Drives a real browser engine to fetch JavaScript-rendered content, acting as a stronger replacement for built-in fetch/curl on pages that come back empty.
  • Session management with per-browser isolated profiles, so multiple accounts can run in parallel, plus user-configured proxy support.
  • Complex interaction: clicking, typing, selecting, file upload, extracting content that loads on scroll/click, screenshots, and XHR/fetch/HAR capture.
  • A Confirmation Gate protocol that requires explicit user approval before creating or deleting browsers and before sensitive actions like login, form submission, or uploads.
  • States that cookies, sessions, credentials, and page content stay local; the only outbound payload is the captcha challenge image when captcha solving is requested.

Who it's for

  • Anyone repeatedly scraping SPAs or sites behind a login.
  • QA and design reviewers who need real screenshots to verify layout and styling.
  • Ops/marketing teams juggling several accounts in parallel.
  • Requires Python 3.12+ and the uv package manager on your machine.

Example uses

  1. "Log into this dashboard and pull last month's report table" → authenticated session plus DOM extraction.
  2. "Screenshot the new landing page at mobile width and tell me what breaks" → viewport captures for rendering checks.
  3. "Open these 20 product URLs in parallel and collect price and stock" → multi-browser parallel runs with scroll-loaded content extraction.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/browser-act/skills/HEAD/browser-act/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the browser-act folder from the GitHub repo browser-act/skills into my ~/.claude/skills/browser-act/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/browser-act/skills.git /tmp/ba-skills && mkdir -p ~/.claude/skills && cp -r /tmp/ba-skills/browser-act ~/.claude/skills/ && uv tool install browser-act-cli --python 3.12

⚠ This is a third-party skill. Check the source repository before installing.

  1. Install Python 3.12+ and the uv package manager (macOS/Linux: curl -LsSf https://astral.sh/uv/install.sh | sh).
  2. Install the CLI: uv tool install browser-act-cli --python 3.12
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Clone the repo: git clone https://github.com/browser-act/skills.git
  5. Copy the skill: cp -r skills/browser-act ~/.claude/skills/
  6. Restart Claude Code and try a prompt like "use browser-act to fetch this URL".
  7. On activation the skill runs browser-act get-skills core to pull version-matched instructions. Approve the prompts when it asks to create a browser or perform a login.
View source on GitHub ↗License: MIT