skills.rest
cmetech
cmetechCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

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

Updated May 25, 2026
Search Tags:#automation#cli#forms#web-testing#browser#refs#data-extraction
One-click install
npx skills add https://github.com/cmetech/otto-cli --skill agent-browser-cmetech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/cmetech/otto-cli/tree/main/src/resources/skills/agent-browser
Command: npx skills add https://github.com/cmetech/otto-cli --skill agent-browser-cmetech

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser interactions for AI agents and developers, enabling scripted web tasks without manual UI actions.

Core Features & Use Cases

  • Navigate websites, fill forms, click controls, and capture screenshots
  • Extract text and data from webpages, test web apps, and automate repetitive browser tasks
  • Real-world use: quickly assemble test flows or data extraction pipelines without writing repetitive code.

Quick Start

Launch agent-browser and open a page, then snapshot the page to capture element refs and interact with elements using those refs

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 interactions for web testing without manual intervention?▼

Automate browser interactions by using a CLI workflow with snapshot-based element refs to script web testing tasks. This approach enables deterministic navigation, form filling, and clicking controls without manual UI actions.

How does snapshot-based element referencing work for web automation?▼

Snapshot-based element refs work by capturing page states to identify interactive elements. You launch the automation tool, open a page, take a snapshot to capture element refs, and then interact with those specific refs.

Can I extract data from webpages using a CLI workflow?▼

Yes, you can extract data from webpages using this CLI workflow. The tool enables scripted text and data extraction from webpages, allowing you to quickly assemble data extraction pipelines without writing repetitive code.

Does browser automation support session isolation for deterministic web testing?▼

Yes, browser automation supports session isolation to ensure deterministic, auditable web testing. This feature guarantees that automated test flows and repetitive browser tasks run consistently across common web apps.

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

The best way to capture screenshots during automated web navigation is through a scripted CLI workflow. The tool handles screenshot capture natively as part of its core browser automation capabilities for AI agents and developers.

Are there limitations when using browser automation for repetitive web tasks?▼

Browser automation is designed for common web apps and basic web testing. It relies on snapshot-based element refs, so highly dynamic single-page applications may require frequent re-snapshotting to maintain accurate element references.

Related Skills

Explore More Software Engineering Skills→
zot24zot24
2

agent-browser

Control headless and real browsers via a 50+ command CLI.

Community
Advanced
marin-communitymarin-community
1.2k

add-dataset

Inspect Hugging Face dataset schemas and register them as Marin ExecutorSteps.

Official
Intermediate
jikig-aijikig-ai
12

agent-browser

Automate browser navigation, form filling, and data extraction via snapshot-based element refs.

Official
Intermediate
pth-droidpth-droid

agent-browser

Automate browser navigation, element interaction, and screenshots for web testing.

Community
Intermediate