Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
hamsterider-m avatar

Browser Plus

  • 1 installs
  • Updated April 17, 2026
  • hamsterider-m/personal-skills

Automates browser actions by routing between a native browser tool and Vercel agent-browser based on the target element type.

About

Provides a unified browser-automation API that detects element types and routes rich-text editors to keyboard simulation and plain inputs to native fill. A developer uses it when scripting web form filling, clicking, or typing into editors that resist standard DOM manipulation.

  • Auto-routes rich-text editors to agent-browser and plain inputs to native fill
  • Composite actions like one-click tweet posting

Browser Plus by the numbers

  • 1 all-time installs (skills.sh)
  • Ranked #1,983 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
  • Data as of Aug 2, 2026 (Skillselion catalog sync)
npx skills add https://github.com/hamsterider-m/personal-skills --skill browser-plus

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs1
Last updatedApril 17, 2026
Repositoryhamsterider-m/personal-skills

What it does

Automates browser actions by routing between a native browser tool and Vercel agent-browser based on the target element type.

Files

SKILL.mdMarkdownGitHub ↗

Browser Plus

Intelligent browser automation that routes between OpenClaw native browser tool and Vercel agent-browser based on element type detection.

Overview

Browser Plus provides a unified API for browser automation that intelligently selects the best execution strategy:

  • Rich text editors (contenteditable, tweet textarea, etc.) → Uses agent-browser keyboard simulation for real key events
  • Plain inputs (text fields, password fields, etc.) → Uses native browser fill for faster execution

Quick Start

const browserPlus = require('./skills/browser-plus');

// Auto-routes based on element type
await browserPlus.type({ ref: '@e12', text: 'Hello World' });

// One-click Twitter posting
await browserPlus.tweet({ text: 'My automated tweet!' });

Core API

type(options)

Types text into an element with automatic routing.

await browserPlus.type({
  ref: '@e12',           // Element reference (required)
  text: 'Hello World',   // Text to type (required)
  forceNative: false,    // Force native browser (optional)
  forceAgent: false      // Force agent-browser (optional)
});

click(options)

Clicks an element.

await browserPlus.click({
  ref: '@e12',           // Element reference (required)
  forceAgent: false      // Use agent-browser (optional)
});

Composite Actions

tweet(options)

One-click Twitter posting.

await browserPlus.tweet({
  text: 'My tweet content',
  media: ['/path/to/image.jpg']  // Optional media attachments
});

How It Works

1. Element Detection: Analyzes the target element to determine its type 2. Strategy Selection:

  • Rich text editors → agent-browser (real key events)
  • Plain inputs → native browser (faster)

3. Execution: Routes to the appropriate adapter

Scripts

  • scripts/detectors.js - Element type detection utilities
  • scripts/adapters/native-browser.js - OpenClaw browser wrapper
  • scripts/adapters/agent-browser.js - Vercel agent-browser CLI wrapper
  • scripts/composite/tweet.js - Twitter posting composite action

Related skills

Automation & Workflowsintegrationsfrontend

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.