dev-browser (Browser Automation)

A browser-automation skill that keeps named pages alive across script runs so Claude can navigate, fill forms, screenshot, and scrape incrementally.

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

What it does

Runs a Playwright-backed server that keeps named pages persistent, so successive small scripts share login state and scroll position.
Supports Standalone mode (fresh Chromium) and Extension mode (attaches to your real Chrome for already-authenticated sites).
For unknown layouts, getAISnapshot() returns a YAML accessibility tree with [ref=eN] handles, and selectSnapshotRef() turns a ref into a clickable element.
Codifies good habits: one action per script, log state at the end, screenshot-based debugging, waitForPageLoad/selector/URL waits, no TypeScript inside page.evaluate().
For bulk scraping, points to a reference guide on capturing and replaying paginated network requests instead of scrolling the DOM.

Who it's for

Developers who want AI-driven E2E checks of web flows without manual clicking.
Anyone automating repetitive work behind a login (form submissions, report downloads).
People scraping pages whose HTML structure they don't know in advance.

Examples

"Go to example.com, log in, and screenshot the dashboard" → creates a login page, fills the form, saves tmp/dashboard.png.
"Test whether checkout completes" → runs one script per step, printing URL/title after each to verify progress.
"Extract every item from this listing" → ARIA snapshot to understand structure, then capture the paginated API request and replay it for full data.

· · · 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/dev-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)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
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/dev-browser folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/code-yeongyu-dev-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 && cp -r oh-my-openagent/packages/skills-loader-core/src/features/builtin-skills/dev-browser ~/.claude/skills/

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

Confirm Node.js 18+ and npm are installed: node -v
Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git
Copy the skill folder: mkdir -p ~/.claude/skills && cp -r oh-my-openagent/packages/skills-loader-core/src/features/builtin-skills/dev-browser ~/.claude/skills/
Install dependencies: cd ~/.claude/skills/dev-browser && npm i (add npx playwright install chromium if browsers are missing)
Start the server in the background: ./server.sh & and wait for the Ready line.
To drive your own Chrome instead, run npm run start-extension &, then install and activate the extension from the project's releases page.
Restart Claude Code and ask something like "go to <url> and fill out the form" to trigger the skill.

View source on GitHub ↗License: NOASSERTION