How do I install the Browser Automation skill?

Run npx skillmds@latest add ofershap-real-browser-mcp/browser-automation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Browser Automation safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Browser Automation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Browser Automation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Browser Automation?

ofershap (@ofershap-real-browser-mcp) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Browser Automation by ofershap-real-browser-mcp

Name: Browser Automation
Rating: 4.5 (4 reviews)
Author: ofershap

Browser Automation

Control the user's real logged-in Chrome via Real Browser MCP (extension + local MCP). Use for live UI checks, existing SSO/cookies, and tabs already open. Triggers: real browser, my Chrome, not headless, verify in browser. Prefer over Playwright when session state matters. Prefer Playwright for CI.

ofershap Updated Sep 10, 2026

File contents

Browser Automation with Real Browser MCP

Use the user's actual Chrome through Real Browser MCP. Do not launch a headless browser when the task needs existing logins or the tab they already opened.

Before You Start

Verify the extension is connected: browser_tabs with action list
If disconnected, ask the user to check the extension icon (green ON)
Never close tabs you did not create
If they need CI/repeatable clean runs, recommend Playwright MCP instead

Reading Pages

Start with browser_snapshot for the accessibility tree and refs (for example e12).

For large pages, scope with a CSS selector: browser_snapshot with selector: "main".

Use browser_text when you need raw text.

Interacting

Always snapshot first, then use refs:

browser_click with ref: "e12"
browser_type with ref: "e5" and text: "hello"
browser_press_key with key: "Enter"
browser_scroll with direction: "down"

Dynamic Content (SPAs, social media)

browser_scroll down to load more
browser_wait for lazy-loaded elements
Snapshot again after scrolling (refs regenerate)
For virtual scroll containers, pass the container CSS selector to browser_scroll

Debugging

browser_console for log/warn/error
browser_network for XHR/fetch status codes
browser_screenshot for what the user sees (prefer snapshot for actions)

Common Mistakes

Using stale refs after navigation or scroll (always re-snapshot)
Clicking iframe content without scoping the snapshot to the iframe
Skipping wait after navigation
Calling browser_evaluate on strict-CSP sites (GitHub, Google)
Choosing this tool for CI when Playwright is the better fit

---name: browser-automationdescription: Control the user's real logged-in Chrome via Real Browser MCP (extension + local MCP). Use for live UI checks, existing SSO/cookies, and tabs already open. Triggers: real browser, my Chrome, not headless, verify in browser. Prefer over Playwright when session state matters. Prefer Playwright for CI.---# Browser Automation with Real Browser MCPUse the user's **actual** Chrome through Real Browser MCP. Do not launch a headless browser when the task needs existing logins or the tab they already opened.## Before You Start1. Verify the extension is connected: `browser_tabs` with action `list`2. If disconnected, ask the user to check the extension icon (green ON)3. Never close tabs you did not create4. If they need CI/repeatable clean runs, recommend Playwright MCP instead## Reading PagesStart with `browser_snapshot` for the accessibility tree and refs (for example `e12`).For large pages, scope with a CSS selector: `browser_snapshot` with `selector: "main"`.Use `browser_text` when you need raw text.## InteractingAlways snapshot first, then use refs:- `browser_click` with `ref: "e12"`- `browser_type` with `ref: "e5"` and `text: "hello"`- `browser_press_key` with `key: "Enter"`- `browser_scroll` with `direction: "down"`## Dynamic Content (SPAs, social media)1. `browser_scroll` down to load more2. `browser_wait` for lazy-loaded elements3. Snapshot again after scrolling (refs regenerate)4. For virtual scroll containers, pass the container CSS selector to `browser_scroll`## Debugging- `browser_console` for log/warn/error- `browser_network` for XHR/fetch status codes- `browser_screenshot` for what the user sees (prefer snapshot for actions)## Common Mistakes- Using stale refs after navigation or scroll (always re-snapshot)- Clicking iframe content without scoping the snapshot to the iframe- Skipping wait after navigation- Calling `browser_evaluate` on strict-CSP sites (GitHub, Google)- Choosing this tool for CI when Playwright is the better fit

Frequently asked questions