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

agent-browser Browser Automation

A command reference that lets Claude drive a real browser with the agent-browser CLI for navigation, form filling, screenshots and data extraction.

AutomationIntermediate★ 67,531⑂ 5,507AI score 9/10Last updated: Aug 9, 2026

What it does

This skill teaches Claude to operate a real browser through the agent-browser CLI.

  • Core workflow: open a URL → snapshot -i to list interactive elements with refs like @e1 → act with click/fill/select → re-snapshot after navigation or DOM changes.
  • Broad command coverage: clicking, typing, keyboard/mouse control, drag & drop, uploads; reading text, attributes and computed styles; state checks; waits (element, text, URL pattern, networkidle); screenshots, PDF and video recording; snapshot and pixel diffs; console logs, page errors, traces and profiling.
  • Sessions and auth: state save/load to reuse logins, --session for parallel browsers, --profile for persistent profiles, header-based auth and an encrypted credential vault so the model never sees passwords.
  • Environment control: viewport, device emulation, geolocation, offline mode, color scheme; cookies and local/session storage; request routing and mocking; tabs, iframes, dialogs; CDP connections; cloud providers (Browserbase, Browser Use, Kernel) and iOS Simulator.

Who it's for

  • Front-end developers and QA engineers automating E2E checks or visual regressions
  • Automation builders who need repeatable tasks or data extraction behind logins
  • Teams that want quick UI diffs, console error checks and performance profiles around releases

Example uses

  1. Automated form submission: open the form page, run snapshot -i to get refs for email/password/submit, then fill, click, and wait --load networkidle to verify the result.
  2. Reuse a logged-in session: log in once and state save auth.json; later runs just state load auth.json and jump straight to the dashboard.
  3. Pre/post-deploy comparison: diff url https://v1.com https://v2.com --screenshot to report both accessibility-tree and pixel differences in one step.

· · · 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/code-yeongyu/oh-my-openagent/HEAD/packages/omo-opencode/src/features/builtin-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 packages/omo-opencode/src/features/builtin-skills/agent-browser folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/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/code-yeongyu/oh-my-openagent.git && mkdir -p ~/.claude/skills/agent-browser && cp -r oh-my-openagent/packages/omo-opencode/src/features/builtin-skills/agent-browser/* ~/.claude/skills/agent-browser/ && bun add -g agent-browser && agent-browser install

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

  1. Open a terminal and check Bun with bun --version; install it from https://bun.sh if missing.
  2. Install the CLI globally: bun add -g agent-browser
  3. Download the browser engine: agent-browser install (on Linux use agent-browser install --with-deps if system libraries are missing).
  4. Get the skill files: git clone https://github.com/code-yeongyu/oh-my-openagent.git
  5. Copy them into your Claude skills folder: mkdir -p ~/.claude/skills/agent-browser && cp -r oh-my-openagent/packages/omo-opencode/src/features/builtin-skills/agent-browser/* ~/.claude/skills/agent-browser/
  6. Restart Claude Code and test with a prompt like "open example.com and take a screenshot" to confirm the skill triggers.
  7. Add --headed when you want to watch the browser, and store repeated flags in an agent-browser.json file at your project root.
View source on GitHub ↗License: NOASSERTION