skills.rest
AbhiShake1
AbhiShake1COMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser interactions via a Bash CLI with snapshot-ref workflows.

1|Updated Apr 13, 2025
Search Tags:#cli#ai-agents#data-extraction#web-scraping#browser-automation#form-filling
One-click install
npx skills add https://github.com/AbhiShake1/supersurkhet --skill agent-browser-abhishake1
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/AbhiShake1/supersurkhet/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/AbhiShake1/supersurkhet --skill agent-browser-abhishake1

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser interactions for AI agents by providing a CLI to drive web tasks.

Core Features & Use Cases

  • Open URLs, navigate pages, and manage browser sessions from a CLI.
  • Snapshot interactive references (@e1, @e2, ...) to locate and reuse page elements.
  • Interact with elements via ref-based commands (click, fill, type, select, etc.) and capture screenshots or PDFs.
  • Support for state persistence, parallel sessions, and common automation patterns (form submission, authentication, data extraction).

Quick Start

Open a URL, snapshot the page to discover element refs, then interact using those refs to automate a task.

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 scraping and form filling for AI agents using a CLI?▼

Browser automation for AI agents is achieved by using a Bash-based CLI to open URLs, snapshot interactive page elements into references like @e1, and execute ref-based commands to click, fill, and extract data.

What is the best way to manage browser sessions when automating web tasks across multiple pages?▼

Managing browser sessions during web automation is handled through the CLI's state persistence and parallel session features, allowing you to maintain authentication and navigate across multiple pages seamlessly.

How does snapshot-ref workflow function when driving web page interactions?▼

The snapshot-ref workflow discovers interactive elements on a web page and assigns them reference identifiers, which you then pass to CLI commands to accurately locate and reuse elements for clicks, typing, and form submissions.

Can I capture screenshots and PDFs while navigating pages for automated testing?▼

Capturing screenshots and PDFs during automated testing is fully supported, allowing you to document page states and verify navigation results directly through the browser CLI commands during your automation pipeline.

Do I need any external dependencies to run browser automation tasks with this CLI?▼

No external dependencies are required to run browser automation tasks, as the CLI operates independently through a Bash-based design to drive web tasks, manage sessions, and execute data extraction.

Why does my browser automation fail to locate dynamically generated page elements?▼

Browser automation may fail to locate dynamically generated elements if the page is not fully loaded; you must re-snapshot the page to discover new interactive references before issuing subsequent ref-based commands.

Related Skills

Explore More Software Engineering Skills→
8b-is8b-is

agent-browser

Automate browser navigation, element interaction, and data extraction via CLI.

Official
Advanced
expectedparrotexpectedparrot

analyze-results

Parse EDSL Results by UUID and generate Markdown, HTML, and CSV analysis packages.

Official
Intermediate
jaguarliuujaguarliuu

agent-browser

Automates browser navigation, form filling, and data extraction via CLI.

Community
Advanced
skuridinskuridin

playwright-cli

Automate browser navigation, form interaction, screenshots, and network mocking with Playwright.

Community
Intermediate