skills.rest
tarang-tj
tarang-tjCOMMUNITY
Explore all skills by this author →
Website𝕏@btwitstjGitHub

ck:agent-browser

Automate browser interactions for AI agents using snapshot and refs workflows.

Updated Aug 27, 2026
Search Tags:#cli#snapshot#refs#browser-automation#agent-browser#cloud-testing
One-click install
npx skills add https://github.com/tarang-tj/syllabus-ai --skill ck-agent-browser-tarang-tj
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ck:agent-browser
Source: https://github.com/tarang-tj/syllabus-ai/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/tarang-tj/syllabus-ai --skill ck-agent-browser-tarang-tj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI agents often struggle with interacting with dynamic web pages while maintaining context over long autonomous sessions. This skill provides a robust, CLI-driven browser automation workflow that uses snapshot + refs to keep context lean and reliable.

Core Features & Use Cases

  • Snapshot + refs: generate stable references to interactive elements for repeatable actions.
  • Context-efficient sessions: long-running automation with reduced context footprint, built-in video recording, and cloud testing support.
  • Cloud/browser testing: supports Browserbase for CI/CD and scalable parallel runs.

Quick Start

Open a URL with agent-browser, take a snapshot with refs, and then perform interactions using those refs.

Frequently Asked Questions about ck:agent-browser

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

FAQPage Schema
How do I keep AI agent context lean during long browser automation sessions?▼

To keep AI agent context lean during long browser automation sessions, use a CLI-driven snapshot and refs workflow that generates stable references to interactive elements, reducing the context footprint while maintaining reliable actions.

What is the snapshot and refs approach for browser automation?▼

The snapshot and refs approach for browser automation captures a web page state and generates stable references to interactive elements. Agents then perform repeatable actions using these refs without needing full page context.

How do I automate end-to-end web tasks with a CLI interface?▼

Automate end-to-end web tasks with a CLI interface by opening a URL, taking a snapshot to generate element refs, and executing interactions using those refs. This enables self-verifying workflows for AI agents.

Does agent-browser support cloud testing and parallel CI/CD runs?▼

Yes, browser automation supports cloud testing and parallel CI/CD runs through optional Browserbase integration. This allows scalable execution of autonomous sessions across multiple browsers.

Can I run self-verifying web automation workflows across different browsers?▼

Yes, you can run self-verifying web automation workflows across different browsers. The CLI-driven approach enforces a snapshot and refs workflow, supporting reliable cross-browser cloud testing and long autonomous sessions.

Related Skills

Explore More Software Engineering Skills→
congthang12312congthang12312

agent-browser

Automate browser tasks via CLI with context-aware snapshots.

Community
Advanced
ZeliperZeliper

spawn-test-case

Spawn test-case-agent after a successful commit to generate test cases.

Community
Intermediate
Fl2vioFl2vio
1

browser

Automate web browser tasks using AI-optimized snapshots and element refs.

Community
Advanced
MICHAEL-BODOMICHAEL-BODO
2

browser-automation

Automate browser interactions for web testing and scraping with Playwright and Puppeteer.

Community
Intermediate