skills.rest
gsd-build
gsd-buildOFFICIAL
Explore all skills by this author →
GitHub

agent-browser

Automate browser actions and data collection via a CLI.

7.8k|770|Updated Mar 11, 2026
Search Tags:#automation#testing#ai#agents#scripting#browser#web
One-click install
npx skills add https://github.com/gsd-build/gsd-2 --skill agent-browser-gsd-build
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/gsd-build/gsd-2/tree/main/src/resources/skills/agent-browser
Command: npx skills add https://github.com/gsd-build/gsd-2 --skill agent-browser-gsd-build

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation for AI agents to interact with websites, enabling deterministic actions across navigation, forms, and data capture.

Core Features & Use Cases

  • Programmatic browser control via a CLI to open pages, fill forms, click elements, take screenshots, and extract data.
  • Snapshot-driven refs simplify AI prompts, support robust automation across sessions, and enable testing and QA workflows.
  • Use cases include automated login flows, form submissions, data extraction, visual validation, and cross-site testing.

Quick Start

Open a target website with agent-browser open, take a snapshot to identify element refs, and begin automating common web tasks.

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 like form submissions and logins for AI agents?▼

Browser automation for AI agents is executed via a CLI that opens pages, fills forms, clicks elements, and captures screenshots. This enables deterministic actions across navigation, form submissions, and data extraction workflows.

What is snapshot-driven web testing and how does it support cross-site automation?▼

Snapshot-driven refs simplify AI prompts and support robust cross-site testing automation. They identify page element references to enable reliable web testing, visual validation, and page state comparison across multiple sessions.

How do I extract data and capture screenshots from web pages programmatically?▼

Data extraction and screenshot capture are performed by opening a target website with the CLI and taking a snapshot. This identifies element refs to begin automating common web tasks and collecting page data deterministically.

Does browser automation require specific dependencies or environment setup to function?▼

Browser automation requires a SKILL.md frontmatter with a name and description, and clearly defines dependencies and components. It optionally includes references and assets directories to enable safe execution and discovery without external dependencies.

Are there limitations when using CLI browser control for visual validation across sessions?▼

Visual validation across sessions relies on snapshot-driven refs for robust automation, but CLI browser control is limited to deterministic page interactions like opening pages, clicking elements, and capturing defined page states.

Related Skills

Explore More Software Engineering Skills→
apifyapify
239

Template for a customizable Skill Unit.

Official
Basic
jie023jie023
36

test-function

Automate web application functional testing with Playwright and MCP tooling.

Community
Advanced
NguyenvanleNguyenvanle

agent-browser

Drive browser automation for AI agents via CLI commands.

Community
Advanced
platonaiplatonai
1.1k

browser4-cli

Automate browser interactions for web testing, form filling, screenshots, and data extraction.

Community
Advanced