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

Agent Browser (CLI Browser Automation)

Teaches Claude to drive a browser from the command line: open pages, grab element refs via snapshot, then click, fill, screenshot and record.

AutomationIntermediate★ 252⑂ 24AI score 9/10Last updated: Aug 21, 2026

What it does

Wraps the agent-browser CLI into a clear agent workflow:

  1. agent-browser open <url> to navigate
  2. agent-browser snapshot -i to list interactive elements with refs (@e1, @e2)
  3. Act on those refs — click, fill, type, select, check, drag, upload
  4. Re-snapshot after navigation or DOM changes

It also documents screenshots/PDF export, webm video recording, network interception and response mocking, cookies and local/session storage, tabs, iframes and dialogs, device/geolocation/dark-mode emulation, saved auth state (state save/load), parallel sessions and persistent profiles.

Who it's for

  • Developers who want an agent to run web QA and regression checks
  • Anyone automating repetitive form filling or web data extraction
  • People producing screenshots or demo videos for docs and release notes

Examples

  • Automated login: snapshot to get email/password/button refs, then fill → click → wait --load networkidle, then re-snapshot to verify.
  • Reusing a session: log in once, state save auth.json, and later state load auth.json to jump straight to the dashboard.
  • Bug reproduction video: record start ./debug.webm, replay the steps, record stop to save the clip, optionally trace stop trace.zip.

· · · 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/ArabelaTso/Skills-4-SE/HEAD/skills/agent-browser/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 skills/agent-browser folder from the GitHub repo ArabelaTso/Skills-4-SE into my ~/.claude/skills/arabelatso-agent-browser/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/ArabelaTso/Skills-4-SE.git && mkdir -p ~/.claude/skills && cp -r Skills-4-SE/skills/agent-browser ~/.claude/skills/ && npm install -g agent-browser && npx playwright install chromium

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

  1. Make sure Node.js is installed (node -v).
  2. Install the CLI globally: npm install -g agent-browser
  3. Download the Playwright browser: npx playwright install chromium
  4. Clone the skill repo: git clone https://github.com/ArabelaTso/Skills-4-SE.git
  5. Copy the skill folder: mkdir -p ~/.claude/skills && cp -r Skills-4-SE/skills/agent-browser ~/.claude/skills/
  6. Verify with agent-browser open https://example.com --headed — a browser window should appear.
  7. Restart Claude Code and ask something like "open this page and fill in the login form" to trigger the skill.
View source on GitHub ↗License: Apache-2.0