skills.rest
Sheshiyer
SheshiyerCOMMUNITY
Explore all skills by this author →
Website𝕏@witnessalchemstGitHub

agent-browser

Automate browser interactions via Playwright with @e element refs.

4|1|Updated Feb 10, 2026
Search Tags:#playwright#web-testing#browser-automation#automation-scripting#inference-sh#agent-refs
One-click install
npx skills add https://github.com/Sheshiyer/brandmint-oracle-aleph --skill agent-browser-sheshiyer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Sheshiyer/brandmint-oracle-aleph/tree/main/skills/external/inference-sh/upstream/ab546d072f1e/tools/utilities/agentic-browser
Command: npx skills add https://github.com/Sheshiyer/brandmint-oracle-aleph --skill agent-browser-sheshiyer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI agents often require browser automation to interact with web apps, gather data, or test flows, but building stable, ref-based interactions can be error-prone and time-consuming.

Core Features & Use Cases

  • Compact element refs (@eN) for reliable interactions with Playwright-driven automation
  • Session-based navigation, form interaction, screenshots, and optional video capture
  • Use cases include data extraction, UI testing, and agent-driven web exploration

Quick Start

Open a new browser session with a URL and start automating interactions using the agent-browser functions via the inference.sh CLI.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate web tasks for AI agents using Playwright?▼

Open a browser session with a target URL via the inference.sh CLI, then use agent-browser functions like open, snapshot, interact, execute, and close to drive Playwright automation and capture screenshots or video.

How do element refs work for browser automation in Playwright?▼

It uses the @e element-ref system to assign compact identifiers to page elements, allowing AI agents to reliably interact with them during Playwright automation sessions for data extraction and UI testing.

Can I capture screenshots and video during web automation testing?▼

Yes, the automation workflow supports capturing outputs through screenshots or optional video recording during sessions, providing visual artifacts for debugging, UI testing, and agent-driven web exploration.

Does browser automation with inference.sh support UI testing and data extraction?▼

Yes, it supports data extraction, UI testing, and agent-driven web exploration by leveraging Playwright integration and the inference.sh CLI to navigate pages and interact with elements via compact @e refs.

What are the limitations of using @e refs for AI agent web interactions?▼

The @e element-ref system relies on Playwright integration and the inference.sh CLI, meaning it is tailored for inference.sh agent workflows and may not be suitable for general browser automation outside this specific environment.

Related Skills

Explore More Software Engineering Skills→
browserbasebrowserbase
3.7k

Browser Automation

Automate browser interactions with persistent Playwright sessions via CLI commands.

Official
Advanced
archibatearchibate
6

slack

Automate Slack web workspace interactions to read messages and extract channel metadata.

Community
Intermediate
gugug168gugug168

e2e-testing

Automate Playwright end-to-end testing workflows with Page Object Model and CI/CD integration.

Community
Intermediate
JingyueCongJingyueCong

browser-automation

Design stable selectors, waits, and interaction workflows for Playwright and Puppeteer.

Community
Advanced