skills.rest
ulpi-io
ulpi-ioOFFICIAL
Explore all skills by this author →
GitHub

browse

Automate browser and native app UI interactions across Chromium and native runners.

13|Updated Mar 15, 2026
Search Tags:#automation#testing#cli#playwright#native-app#headless#browser-automation
One-click install
npx skills add https://github.com/ulpi-io/browse --skill browse-ulpi-io
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/ulpi-io/browse/tree/main/skill/browse
Command: npx skills add https://github.com/ulpi-io/browse --skill browse-ulpi-io

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser and native-app automation tasks for AI agents. It enables agents to navigate pages, interact with UI, extract data, and validate end-to-end flows without manual setup.

Core Features & Use Cases

  • Persistent Chromium daemon via Playwright for fast, reusable sessions
  • Snapshot-based element refs and supported commands (goto, text, click, fill, screenshot) across web and native apps
  • Cross-platform automation: web browsers and native apps (iOS/Android/macOS)

Quick Start

Install the browse CLI, start a session, navigate to a URL with goto, then inspect with text or take a screenshot.

Frequently Asked Questions about browse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web browser tasks for an AI agent?▼

You can automate web browser tasks for AI agents by using a persistent Chromium daemon via Playwright, enabling agents to execute commands like goto, click, and fill for end-to-end web navigation and UI interaction.

Can I use Playwright to automate native app testing on iOS and Android?▼

Yes, cross-platform automation supports native apps across iOS, Android, and macOS, using snapshot-based element refs to interact with native runners alongside standard web browser automation.

What is snapshot-based element interaction in browser automation?▼

Snapshot-based element interaction allows browser automation to reference UI elements through snapshots, ensuring reliable execution of commands like text extraction, clicking, and filling across web and native app runtimes.

How do I start a headless browser automation session from the CLI?▼

To start a headless browser automation session, install the browse CLI, initiate a persistent Chromium daemon, navigate to a URL using the goto command, then inspect the page using text or screenshot commands.

Does browser automation work with multiple runtimes without manual setup?▼

Yes, browser automation works across multiple runtimes by maintaining a persistent Chromium daemon via Playwright, allowing fast, reusable sessions for AI agents without requiring manual environment setup.

What are the limitations of using a persistent Chromium daemon for automation?▼

While a persistent Chromium daemon enables fast, reusable sessions, limitations include dependency on Playwright for Chromium control and reliance on snapshot-based refs, which may require specific commands like goto, text, click, fill, and screenshot for interaction.

Related Skills

Explore More Software Engineering Skills→
matsuyoshi30matsuyoshi30

browser-use

Automate browser interactions via a persistent daemon with CDP connectivity.

Community
Advanced
InternScienceInternScience
52

gjf-to-xyz

Parse Gaussian gjf input files and convert them to XYZ format.

Official
Intermediate
dpalferydpalfery

browser-testing

Automate web UI testing and end-to-end validation with Playwright MCP.

Community
Advanced
0xHarbs0xHarbs
1

browse

Automate web browsing for Claude Code workflows via a headless Chromium daemon.

Community
Advanced