skills.rest
JoseMas68
JoseMas68COMMUNITY
Explore all skills by this author →
GitHub

ck:agent-browser

Automate browser interactions for AI agents with snapshot-based element referencing.

Updated Aug 23, 2026
Search Tags:#cli#browser automation#ai agent#snapshot#video recording#session persistence#cloud browsers
One-click install
npx skills add https://github.com/JoseMas68/CRMDev --skill ck-agent-browser
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ck:agent-browser
Source: https://github.com/JoseMas68/CRMDev/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/JoseMas68/CRMDev --skill ck-agent-browser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI agents often need to interact with web pages, fill forms, and extract data, but traditional browser tools generate huge token footprints and require complex scripting, making autonomous workflows inefficient.

Core Features & Use Cases

  • Snapshot‑based element referencing reduces context size dramatically.
  • Session persistence lets agents retain authentication across runs.
  • Video recording and PDF export aid debugging and reporting.
  • Cloud browser support (Browserbase) enables headless CI/CD execution.
  • Ideal for autonomous testing, data extraction, multi‑tab workflows, and long‑running AI‑driven browsing tasks.

Quick Start

Ask the agent to open a page, snapshot interactive elements, fill the form, click submit, and wait for the dashboard to load.

Frequently Asked Questions about ck:agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser interactions for AI agents without excessive token usage?▼

AI-driven browser automation minimizes token cost by using snapshot-based element referencing, which reduces context size dramatically. This allows agents to navigate, manipulate, and extract web data efficiently without generating huge token footprints.

Can I retain authentication and session persistence across multiple browser automation runs?▼

Yes, session persistence lets AI agents retain authentication across multiple browser automation runs. This feature supports long-running browsing tasks and multi-tab workflows by maintaining state between headless or cloud browser executions.

Does browser automation work with headless cloud browsers for CI/CD pipelines?▼

Browser automation supports headless cloud browsers via Browserbase integration, enabling autonomous testing and execution within CI/CD pipelines. It provides video recording and PDF export to aid debugging and reporting for these automated runs.

What is the best way to extract data and fill forms autonomously on web pages?▼

The best way to extract data and fill forms is using snapshot-based element referencing. The agent opens a page, snapshots interactive elements, fills the form, clicks submit, and waits for the dashboard to load, all with minimal token cost.

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

Snapshot-based element referencing captures interactive elements on a web page to reduce context size. AI agents use these snapshots to accurately target and manipulate forms or extract data without loading the entire page DOM into context.

Related Skills

Explore More Software Engineering Skills→
obulaiobulai
1

obul-browserbase

Create and manage pay-per-use headless browser sessions via Browserbase.

Official
Intermediate
ramirlmramirlm

video-bug-prompt

Extract frames from bug videos and generate PDF and Markdown bug reports.

Community
Advanced
reececoakes99reececoakes99

playwrights

Automate multi-browser testing and web scraping with Python Playwright.

Community
Intermediate
MemTensorMemTensor
10.7k

browserwing-executor

Automate browser interactions via HTTP API for navigation, element manipulation, and data extraction.

Official
Advanced