skills.rest
sumik5
sumik5COMMUNITY
Explore all skills by this author →
𝕏@shivasek5GitHub

agent-browser

Automate browser interactions from the command line with semantic locators.

1|Updated Jan 7, 2026
Search Tags:#automation#testing#cli#browser#web-automation#state-persistence#semantic-locators
One-click install
npx skills add https://github.com/sumik5/sumik-claude-plugin --skill agent-browser-sumik5
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/sumik5/sumik-claude-plugin/tree/main/skills/agent-browser
Command: npx skills add https://github.com/sumik5/sumik-claude-plugin --skill agent-browser-sumik5

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, npm, agent-browser, and includes scripts (resource) components.

What problem does it solve?

Automating complex browser tasks can be time-consuming and error-prone when done manually; this skill provides a structured CLI workflow with semantic element referencing to reliably orchestrate browser actions.

Core Features & Use Cases

  • Semantic locators (find by role/label) for robust element selection
  • State persistence (save/load auth) for session reuse
  • Network interception, device emulation, and JSON output for testing and data extraction
  • Snapshot-based references and wait controls for deterministic automation
  • Use cases include automated testing, data extraction, form filling, and end-to-end workflows across dynamic pages

Quick Start

Open a URL with agent-browser, snapshot interactive elements, then interact using the refs to perform actions.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate complex browser interactions from the command line?▼

Browser automation from the command line can be executed by orchestrating actions through structured CLI workflows that use semantic element references to reliably interact with dynamic web pages.

What are semantic locators and how do they work for web automation?▼

Semantic locators identify elements by role or label rather than fragile CSS selectors. They provide robust element selection for web automation, ensuring scripts remain stable even when page structures change dynamically.

How do I maintain authenticated sessions across multiple browser automation tasks?▼

State persistence allows you to save and load authentication states. This enables session reuse across multiple browser automation tasks without needing to log in repeatedly during each command line execution.

Can I use this browser automation skill for network interception and device emulation?▼

Yes, browser automation supports network interception and device emulation. These features allow you to monitor network requests and simulate different devices for comprehensive end-to-end testing and data extraction.

How do I ensure deterministic execution when automating dynamic web pages?▼

Deterministic execution is enforced using snapshot-based references and wait controls. This ensures browser automation actions trigger only after specific page states are reached, preventing synchronization errors on dynamic pages.

Do I need Node and npm to run this CLI browser automation tool?▼

Yes, Node and npm are required dependencies. You must install the agent-browser package via npm to set up the environment and execute structured browser automation workflows from the command line.

Related Skills

Explore More Software Engineering Skills→
Wike-CHIWike-CHI
2

acquisition-dependencies

Install and configure Python, npm, and Playwright dependencies across Linux, macOS, WSL2, and Windows.

Community
Intermediate
Pans0020Pans0020

markdown-exporter

Convert Markdown content into DOCX, PPTX, XLSX, PDF, HTML, IPYNB, MD, CSV, JSON/JSONL, XML, and extracted code files.

Community
Advanced
vaaynevaayne
52

tap-web

Automate web lookup, page reading, and content extraction via the tap CLI.

Community
Advanced
MathiasPaulenkoMathiasPaulenko

BiDiWave Network Interception

Intercept and modify HTTP traffic in WebDriver BiDi sessions.

Community
Advanced