agent-browser

Automate browser navigation, form filling, and data extraction via CLI commands.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/blackjiro/dotfiles --skill agent-browser-blackjiro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/blackjiro/dotfiles/tree/main/dot_claude/skills/agent-browser
Command: npx skills add https://github.com/blackjiro/dotfiles --skill agent-browser-blackjiro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates repetitive browser interactions such as web testing, form filling, taking screenshots, and data extraction, reducing manual workload.

Core Features & Use Cases

  • Automated browsing for web testing and data capture
  • Snapshot and interact with elements using refs
  • Form filling and submission across web forms
  • Screenshots, navigation, and data extraction from pages
  • Use Case: automate login flows and extract data from dashboards

Quick Start

Start by opening a URL, taking a snapshot, and performing actions using element refs. For example: agent-browser open https://example.com agent-browser snapshot -i agent-browser click @e1 agent-browser fill @e1 "text" agent-browser wait --load networkidle

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 form filling and submission without manual input?

Browser automation for web testing uses a CLI workflow to navigate URLs, take snapshots, and interact with elements using refs. It exposes deterministic commands to click, fill, and wait for network idle states, ensuring reliable automated test execution.

Can I extract data from a web dashboard after an automated login flow?

Yes, you can automate login flows and extract data from dashboards by navigating to the login page, filling credentials using element refs, and taking snapshots to capture the dashboard information after network idle.

Does CLI-based browser automation require any external dependencies?

No external dependencies are required for this CLI-based browser automation. The workflow is self-contained, exposing navigate, snapshot, and interaction commands with element refs to drive deterministic browser operations directly.

How do I capture screenshots and snapshots during automated web navigation?

To capture screenshots and snapshots during web navigation, use the snapshot command with element refs to identify page elements. This enables precise interaction and data extraction from the captured page state.

What is the best way to ensure deterministic browser automation when interacting with dynamic pages?

To ensure deterministic browser automation on dynamic pages, use the wait command with networkidle conditions after navigation and interactions. This guarantees the page has fully loaded before taking snapshots or performing element interactions.