AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

agent-browser Automation

Drives the agent-browser CLI so Claude can navigate sites, fill forms, capture screenshots and extract page data.

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

What it does

  • Teaches Claude to control a real browser through the agent-browser CLI.
  • Core loop: open <url> → snapshot -i (interactive elements with refs like @e1) → click/fill/press → re-snapshot after DOM changes.
  • Screenshots (full page and annotated with numbered labels), PDF export, video recording, console/error inspection, traces and CPU profiles.
  • Auth state save/load, isolated sessions and persistent profiles, cookie and localStorage control, network interception and response mocking, iframes, tabs and dialogs.
  • Snapshot/screenshot/URL diffing for regression checks, CDP attachment, cloud browser providers, and an iOS Simulator mode.

Who it's for

  • Frontend developers and QA engineers who want an agent to run E2E flows or UI regression checks.
  • Anyone automating repetitive tasks behind a login (form submissions, data collection).
  • Ops folks monitoring visual changes or console errors on production pages.

Examples

  1. Submit a login form: open the page, snapshot -i to get refs, then fill @e1, fill @e2, click @e3, wait --load networkidle.
  2. Reuse authentication: log in once, state save auth.json, then state load auth.json in later runs to skip the login flow.
  3. Compare releases: diff url https://v1.com https://v2.com --screenshot to see both structural and pixel differences.

· · · 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/skills-loader-core/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 AI 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 && mkdir -p ~/.claude/skills/agent-browser && cp oh-my-openagent/packages/skills-loader-core/src/features/builtin-skills/agent-browser/SKILL.md ~/.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 is available: bun --version. If not, install it from https://bun.sh.
  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).
  4. Create the skill folder: mkdir -p ~/.claude/skills/agent-browser
  5. Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git
  6. Copy the skill file: cp oh-my-openagent/packages/skills-loader-core/src/features/builtin-skills/agent-browser/SKILL.md ~/.claude/skills/agent-browser/
  7. Restart Claude Code and try a prompt like "open example.com and take a screenshot".
  8. Optional: store defaults such as {"headed": true} in ~/.agent-browser/config.json.
View source on GitHub ↗License: NOASSERTION