skills.rest
KYRIE66nb
KYRIE66nbCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser interactions via inference.sh using compact @e element refs.

Updated Apr 8, 2026
Search Tags:#automation#testing#agent#playwright#browser#data-extraction#web-scraping
One-click install
npx skills add https://github.com/KYRIE66nb/codex-omx-public-config --skill agent-browser-kyrie66nb
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/KYRIE66nb/codex-omx-public-config/tree/main/home/.agents/skills/agent-browser
Command: npx skills add https://github.com/KYRIE66nb/codex-omx-public-config --skill agent-browser-kyrie66nb

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI agents need reliable, repeatable browser interactions without brittle hand-crafted prompts. This Skill provides a structured interface to drive a headless browser via inference.sh, returning compact element refs and supporting end-to-end workflows.

Core Features & Use Cases

  • Compact element refs (e.g., @e1) for reliable interactions like click, fill, navigate, and extract content.
  • Multi-function control: open, snapshot, interact, screenshot, execute, and close to manage sessions across pages.
  • Use cases include web automation, data extraction, testing, research, and automated browsing for agent-powered workflows.

Quick Start

Open a page, snapshot to obtain element refs, then interact with an element to navigate or fill a form.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser actions for AI agents without brittle prompts?▼

You can automate browser actions for AI agents by using a structured interface to drive a headless browser, returning compact element references for reliable interactions like clicking, filling, and navigating. This replaces hand-crafted prompts with repeatable workflows.

How does web scraping with compact element refs work?▼

Web scraping with compact element refs works by taking a snapshot of the page to obtain identifiers like @e1, then interacting with those specific elements to click, fill forms, or extract data. This ensures reliable, targeted data extraction.

Can I use Playwright for automated browser testing with AI agents?▼

Yes, you can use Playwright for automated browser testing with AI agents. The skill supports testing workflows by enabling navigation, form filling, clicking, and screenshots across end-to-end browser sessions.

What functions are needed to manage a headless browser session for web automation?▼

Managing a headless browser session for web automation requires functions to open, snapshot, interact, screenshot, execute, and close. These controls manage the browser across pages for testing and data extraction.

Does browser automation for AI agents support video recording?▼

Yes, browser automation for AI agents supports optional video recording. You can record your automated browser sessions alongside taking screenshots for testing and research workflows.

Related Skills

Explore More Software Engineering Skills→
hendripermanahendripermana

agent-browser

Drive a headless browser via inference.sh for web navigation and element interaction.

Community
Advanced
shynlee04shynlee04

web-search

Search the web and extract content via Tavily and Exa using the inference.sh CLI.

Community
Intermediate
8b-is8b-is

agent-browser

Automate browser navigation, element interaction, and data extraction via CLI.

Official
Advanced
MCERQUAMCERQUA
1

playwright-cli

Automate browser tasks with Playwright using snapshot-based element targeting and JSON output.

Community
Intermediate