skills.rest
llm011
llm011OFFICIAL
Explore all skills by this author →
GitHub

dev-browser

Automate Playwright browser workflows with conditional logic and batch scraping.

9|Updated Jun 11, 2026
Search Tags:#browser automation#web scraping#form automation#playwright#batch processing#data aggregation
One-click install
npx skills add https://github.com/llm011/ethan-agent --skill dev-browser-llm011
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dev-browser
Source: https://github.com/llm011/ethan-agent/tree/main/ethan/defaults/skills/dev-browser
Command: npx skills add https://github.com/llm011/ethan-agent --skill dev-browser-llm011

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the manual effort of performing complex, multi-step browser interactions, especially when tasks require iteration, conditional logic, or data aggregation across multiple pages.

Core Features & Use Cases

  • Full Playwright Automation: Navigate, click, fill forms, inspect content, evaluate page scripts, and capture screenshots through the browser.
  • Batch Processing: Loop through URLs or records, apply conditions, and combine results into structured output.
  • Persistent Sessions: Reuse named browser pages and optionally connect to an existing Chrome session with its current login state.
  • Use Case: Collect product titles and prices from multiple item pages, aggregate the results into JSON, and save a screenshot of the completed workflow.

Quick Start

Use the dev-browser skill to automate the multi-page workflow, collect the requested structured data, and return only the aggregated results.

Frequently Asked Questions about dev-browser

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

FAQPage Schema
How do I automate multi-step browser workflows with Playwright?▼

Multi-step browser workflows are automated by applying Playwright-based navigation, form interactions, and conditional logic within a single script to process pages and aggregate structured results.

Can I reuse existing Chrome login sessions for web scraping?▼

Yes, you can connect to an existing Chrome session with its current login state, or reuse persistent named browser pages to maintain authentication across multiple scraping and automation tasks.

What is the best way to batch scrape data across multiple web pages?▼

Batch scraping is handled by looping through URLs or records, applying conditional logic, and combining the extracted content into structured output like JSON for multi-page data collection.

Do I need the dev-browser executable to run form automation scripts?▼

Yes, running form automation and complex workflows requires the dev-browser executable, which operates a QuickJS sandbox to support persistent pages, screenshots, and temporary file access.

How does conditional logic work during web page navigation?▼

Conditional logic is applied during web page navigation by evaluating page scripts and inspecting content to determine branching actions, enabling dynamic multi-step workflows and batch processing.

When should I not use browser automation for data aggregation?▼

Browser automation for data aggregation is not ideal for simple, static HTML extraction where lightweight HTTP requests suffice, as it carries the overhead of running full browser sessions.

Related Skills

Explore More Software Engineering Skills→
roycolumbia-coderoycolumbia-code

dev-browser

Execute Playwright browser automation scripts within a QuickJS sandbox.

Community
Advanced
ShenSeanChenShenSeanChen
16

WhatsApp Chat Parser

Parse WhatsApp chat exports into structured JSON data.

Community
Basic
eddmanneddmann
2

playwright

Render dynamic web pages with Playwright to capture HTML, text, and screenshots.

Community
Intermediate
zhayujiezhayujie
46.4k

web-fetch

Fetch web page HTML and extract title and readable text.

Community
Basic