Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

agent-browser Browser Automation

Drive a real browser from Claude via 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

Teaches Claude to operate a real browser through the agent-browser CLI with a crisp loop: open a page → take an accessibility snapshot to get element refs (@e1) → click, fill, and assert.

  • Navigation: open, back, reload, tabs, windows, iframes
  • Interaction: clicks, form fills, dropdowns, drag & drop, file uploads, raw keyboard/mouse
  • Inspection: text/HTML/attribute extraction, visibility and enabled checks
  • Capture: normal/full-page/annotated screenshots, PDF export, video recording, traces and CPU profiles
  • Advanced: request interception and mocking, cookie/localStorage control, snapshot and pixel diffing, saved auth state, CDP attach, cloud providers, iOS Simulator

Who it's for

  • QA engineers and frontend devs repeatedly testing login, checkout, or onboarding flows
  • Analysts and marketers who manually gather data from web pages
  • Teams that want visual regression checks between staging and production
  • Anyone automating documentation screenshots or demo recordings

Examples

  1. Signup form regression: open the page, snapshot -i for refs, fill email/password, click submit, then wait --url "**/dashboard" to confirm success.
  2. Authenticated scraping: log in once and state save auth.json; later runs just state load auth.json and pull metrics with get text.
  3. Visual regression between environments: diff url https://staging.example.com https://www.example.com --screenshot to compare structure and pixels in one command.

· · · Install guide · · ·

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/skills-loader-core/src/features/builtin-skills/agent-browser folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/code-yeongyu-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 /tmp/oma && mkdir -p ~/.claude/skills && cp -r /tmp/oma/packages/skills-loader-core/src/features/builtin-skills/agent-browser ~/.claude/skills/ && bun add -g agent-browser && agent-browser install

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

  1. Make sure you have bun or npm available.
  2. Install the CLI globally: bun add -g agent-browser (or npm i -g agent-browser).
  3. Download the browser engine: agent-browser install (use --with-deps on Linux).
  4. Fetch the skill source: git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oma.
  5. Copy the skill folder: mkdir -p ~/.claude/skills && cp -r /tmp/oma/packages/skills-loader-core/src/features/builtin-skills/agent-browser ~/.claude/skills/.
  6. Restart Claude Code and try a prompt like "take a screenshot of this page".
  7. (Recommended) Constrain access with --allowed-domains, --confirm-actions, or a ~/.agent-browser/config.json before letting it touch real accounts.
View source on GitHub ↗License: NOASSERTION