skills.rest
souki202
souki202COMMUNITY
Explore all skills by this author →
GitHub

agent-browser

This is a JSON, not a string.

Updated Feb 21, 2026
Search Tags:#automation#testing#cli#multi-session#browser#web#data-extraction
One-click install
npx skills add https://github.com/souki202/metaclaw --skill agent-browser-souki202
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/souki202/metaclaw/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/souki202/metaclaw --skill agent-browser-souki202

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI agents often struggle to reliably interact with real websites: browsing, form filling, data capture, and verification require a robust, reusable toolset. This Skill provides a CLI-driven browser automation framework that coordinates multi-session workflows, maintains per-session state, and returns structured, lightweight refs for rapid decision making.

Core Features & Use Cases

  • Multi-session isolation across agent contexts to prevent cross-contamination of cookies and storage.
  • Ref-based interactions using compact @e references to minimize context while enabling precise actions.
  • Data extraction & screenshots to collect text, metadata, and visuals for dashboards, QA, and reporting.
  • Use Case: An agent opens a portal, logs in, navigates to a data page, extracts records, and saves results with minimal prompts.

Quick Start

Open a website using the agent-browser CLI to begin an automated web task.

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 tasks for AI agents without context bloat?▼

Automate browser tasks for AI agents by using a CLI-driven framework with Chrome DevTools Protocol. It employs compact @e element references to minimize context usage while enabling precise programmatic control over web pages.

Can I run multi-session browser automation to isolate cookies and local storage?▼

Multi-session browser automation isolates agent contexts to prevent cross-contamination of cookies and storage. It maintains per-session state independently, allowing concurrent web workflows to operate without interfering with each other.

How does CLI browser automation handle data extraction and screenshots for reporting?▼

CLI browser automation handles data extraction and screenshots by capturing text, metadata, and visuals directly from web pages. This collected data supports downstream workflows like dashboard generation, QA testing, and automated reporting.

What is the best way to automate web form filling and login workflows for agents?▼

The best way to automate web form filling and logins is using a CLI framework that coordinates multi-session workflows. An agent can open a portal, log in, navigate to data pages, and extract records with minimal prompts.

Does this browser automation tool require specific dependencies to control web pages?▼

This browser automation tool requires no external dependencies to control web pages. It operates through a CLI and the Chrome DevTools Protocol, providing a standalone framework for element interactions and data capture.

Related Skills

Explore More Software Engineering Skills→
mxyhimxyhi
467

chrome-cdp

Control local Chrome sessions via the Chrome DevTools Protocol.

Community
Intermediate
profmikegreeneprofmikegreene
1

plan-ingestion

Parses pilot plans and hypotheses into structured JSON or tabular data for downstream analysis.

Community
Intermediate
gaebalaigaebalai
2

start

Coordinate expert panel debates into structured recommendations with phase-based orchestration.

Community
Advanced
dushyantkhosladushyantkhosla

browser-tools

Automate web interactions via Chrome DevTools Protocol with Puppeteer.

Community
Advanced