skills.rest
itechmeat
itechmeatCOMMUNITY
Explore all skills by this author →
𝕏@techmeatGitHub

agent-browser

Automate headless browser navigation, form interactions, and data extraction via CLI.

22|1|Updated Jan 10, 2026
Search Tags:#CLI#sessions#headless#snapshots#refs#browser-automation#agent-browser
One-click install
npx skills add https://github.com/itechmeat/llm-code --skill agent-browser-itechmeat
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/itechmeat/llm-code/tree/main/skills/agent-browser
Command: npx skills add https://github.com/itechmeat/llm-code --skill agent-browser-itechmeat

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables AI agents to automate web tasks using a headless browser, removing repetitive manual browsing.

Core Features & Use Cases

  • Headless browser automation across commands, refs, sessions, snapshots, and streaming.
  • Manage multiple browser sessions and profiles for isolated workflows.
  • Use cases include automated navigation, form interaction, and data extraction in AI agent pipelines.

Quick Start

Install agent-browser globally and begin driving a browser with simple commands such as:

  • npm install -g agent-browser
  • agent-browser open https://example.com
  • agent-browser snapshot
  • agent-browser close

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 using a headless browser with an AI agent?▼

Headless browser automation for AI agents is achieved by using a CLI to drive navigation, form interactions, and data extraction. This Skill provides commands to open URLs, take snapshots, and manage multi-tab sessions without manual browsing.

Can I manage multiple browser sessions for isolated workflows?▼

Yes, you can manage multiple browser sessions and profiles for isolated workflows. This allows AI agents to handle concurrent navigation and data extraction tasks independently across different browser instances using the client-daemon architecture.

How do I capture visual snapshots during browser automation?▼

Visual snapshots are captured during browser automation by executing the snapshot command via the CLI. This enables AI agents to perform visual verifications of web pages across active headless browser sessions.

What is the best way to extract data from web pages in AI pipelines?▼

Data extraction in AI pipelines is handled by driving a headless browser through CLI commands to navigate and interact with web elements. The Skill automates this process, feeding extracted data directly into agent workflows for processing.

Do I need to install any dependencies to run headless browser automation?▼

Yes, you need to install the agent-browser tool and its dependencies globally using npm. Once installed, the client-daemon architecture supports both local and remote control for automating web tasks.

Can I use this for remote browser automation across different providers?▼

Remote browser automation across different providers is supported through the client-daemon architecture. This enables AI agents to control headless browsers on remote machines, extending navigation and data extraction workflows beyond local environments.

Related Skills

Explore More Software Engineering Skills→
ryanmivilleryanmiville

agent-browser

Automate browser navigation, form filling, and data scraping with Playwright.

Community
Advanced
Likas07Likas07

data-consolidation-agent

Consolidate sales data into reporting dashboards with territory, rep, and pipeline summaries.

Community
Advanced
carl10086carl10086
7

opencli-browser

Drive live Chrome sessions for web interactions, form filling, and data extraction.

Community
Advanced
NagyViktNagyVikt
2

agent-browser

Automate browser interactions and capture screenshots for UI verification.

Community
Advanced