skills.rest
jon890
jon890COMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser tasks for AI agents via Bash commands.

Updated Jan 30, 2026
Search Tags:#automation#cli#scripting#web-testing#browser#data-extraction
One-click install
npx skills add https://github.com/jon890/fos-blog --skill agent-browser-jon890
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/jon890/fos-blog/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/jon890/fos-blog --skill agent-browser-jon890

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation for AI agents reduces manual, repetitive web interactions by programmatically navigating pages, filling forms, clicking elements, and extracting data across websites.

Core Features & Use Cases

  • Open and navigate websites using agent-browser open and navigation commands
  • Snapshot and interact using refs to fill fields, click buttons, and verify results
  • Capture screenshots and extract page data for testing, documentation, and automation workflows
  • Use cases include automated login flows, form submission, UI testing, and multi-site data extraction

Quick Start

Open a URL with agent-browser and perform a basic navigation-and-interaction workflow.

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 testing and browser tasks from the command line?▼

Automate browser tasks using a Bash-based command interface to navigate pages, fill forms, click elements, and capture screenshots. It executes interactive commands against web pages for automated workflows.

Can I extract data from multiple websites in a single automation workflow?▼

Yes, multi-site data extraction is supported through named sessions and navigation commands. You can open URLs, snapshot page states, and extract data across different websites in one continuous workflow.

How do I fill out forms and click buttons during browser automation?▼

Use snapshots to capture page elements and generate refs, then execute commands to fill fields and click buttons using those refs. This allows precise interaction with forms and UI elements during automation.

Does browser automation work with persistent sessions and state saving?▼

Yes, optional state persistence is supported alongside named sessions. This enables you to maintain browser state across multiple commands and continue interactive workflows without losing context.

What is the best way to capture screenshots during automated web navigation?▼

Capture screenshots by executing snapshot commands during your navigation workflow. The Bash interface allows you to take page snapshots at any point for testing, documentation, or verification purposes.

Can I use this for automated login flows and UI testing?▼

Yes, automated login flows and UI testing are core use cases. Navigate to login pages, fill form fields using refs, click submit buttons, and verify results through screenshots and extracted page data.

Related Skills

Explore More Software Engineering Skills→
RxFitRxFit

browse

Automate headless browser interactions to verify web pages and test user flows.

Community
Advanced
ExuberantWitnessExuberantWitness
1

flux-result-to-claim

Extracts verifiable research claims from experimental artifacts and analysis reports into structured knowledge graph entries.

Community
Intermediate
ronakpjainronakpjain
10

playwright-firefox

Automate Firefox browser sessions for live, headless, and multi-profile testing.

Community
Intermediate
jrollinjrollin
2

core-agent-browser

Automate browser navigation, element interaction, form filling, and screenshot capture.

Community
Intermediate