jikime-tool-agent-browser

Automate browser interactions for web testing, form filling, screenshots, and data extraction.

5|1|Updated Jan 24, 2026
One-click install
npx skills add https://github.com/jikime/jikime-adk --skill jikime-tool-agent-browser
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: jikime-tool-agent-browser
Source: https://github.com/jikime/jikime-adk/tree/main/templates/.claude/skills/jikime-tool-agent-browser
Command: npx skills add https://github.com/jikime/jikime-adk --skill jikime-tool-agent-browser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates complex browser interactions, streamlining web testing, data extraction, and form filling processes.

Core Features & Use Cases

  • Web Navigation: Open, close, and navigate between web pages.
  • Element Interaction: Click, fill forms, check/uncheck boxes, and select dropdown options using semantic locators or element references.
  • Data Extraction: Extract text, HTML, attributes, and other element properties.
  • Screenshots & PDF: Capture full-page screenshots or save pages as PDFs.
  • Use Case: Automate the process of logging into a web application, filling out a multi-step form, and capturing a screenshot of the final confirmation page.

Quick Start

Use the agent-browser skill to open the URL 'https://example.com'.

Frequently Asked Questions about jikime-tool-agent-browser

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

FAQPage Schema
How do I automate web scraping and extract text or HTML from web pages?

Automate web scraping by navigating to URLs and using element interaction to extract text, HTML, attributes, and properties. It supports data extraction via semantic locators and element references for reliable scraping.

Can I automate form filling and handle multi-step web interactions end to end?

Yes, automate form filling by clicking, checking boxes, and selecting dropdown options using semantic locators. It handles multi-step web interactions including logging in, filling forms, and capturing confirmation screenshots.

Does this browser automation tool support network interception and video recording?

Yes, browser automation includes network interception and video recording capabilities. It manages browser state and integrates with cloud browser providers and custom executables for diverse testing scenarios.

What is the best way to capture full-page screenshots or save web pages as PDFs?

The best way to capture full-page screenshots or save pages as PDFs is using built-in browser interaction commands. It navigates to the target URL and directly renders the page content to image or PDF format.

How does e2e testing work with semantic locators and element references?

E2e testing works by navigating web pages and interacting with elements via semantic locators or refs. It automates state management, clicks, and form inputs to verify application flows across different browser environments.