skills.rest
b0nsu
b0nsuCOMMUNITY
Explore all skills by this author →
GitHub

dev-browser

Automate browser interactions with persistent page state across script executions.

Updated Aug 23, 2026
Search Tags:#automation#playwright#scripts#browser#extensions#web-automation
One-click install
npx skills add https://github.com/b0nsu/oh-my-shit-memory --skill dev-browser-b0nsu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dev-browser
Source: https://github.com/b0nsu/oh-my-shit-memory/tree/main/src/features/builtin-skills/dev-browser
Command: npx skills add https://github.com/b0nsu/oh-my-shit-memory --skill dev-browser-b0nsu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser interactions with persistent page state across script executions, enabling repeatable workflows and reducing setup time for complex tasks.

Core Features & Use Cases

  • Persistent page state across runs: pages remain available between script executions to build multi-step workflows.
  • Small, focused scripts: each script handles a single interaction (navigate, click, fill, etc.) and returns a state for the next step.
  • Two operation modes: Standalone mode (new browser instance) and Extension mode (control an existing browser).
  • Use cases: automating form filling, data extraction, testing web apps, capturing ARIA snapshots, and scripted browsing across sessions.

Quick Start

Start with a minimal script that opens a page and performs a single action, then iterate by adding more scripts for subsequent steps.

Frequently Asked Questions about dev-browser

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

FAQPage Schema
How do I automate browser interactions while keeping page state between script executions?▼

Browser automation with persistent page state keeps pages available across script runs to build multi-step workflows. Each script performs a single interaction like navigating or clicking, then returns state for the next step.

Can I control an existing browser instance instead of launching a new one for web automation?▼

Yes, web automation can operate in extension mode to control an existing browser or standalone mode to launch a new instance. Both modes expose a client API for managing pages and waiting for load.

What's the best way to automate form filling and data extraction across multiple sessions?▼

Automating form filling and data extraction across sessions requires persistent page state. Scripts handle single interactions sequentially, reducing setup time and enabling repeatable workflows for complex tasks.

Does browser automation support capturing ARIA snapshots during scripted browsing?▼

Yes, browser automation supports capturing ARIA snapshots during scripted browsing. The client API manages pages, waits for load, captures snapshots, takes screenshots, and extracts data while persisting page state.

How do I start building multi-step browser automation scripts for repeated tasks?▼

Start with a minimal script that opens a page and performs a single action, then iterate by adding more scripts for subsequent steps. Each small, focused script handles one interaction and returns state for the next step.

Related Skills

Explore More Software Engineering Skills→
ynulihaoynulihao
564

dev-browser

Automates web browsing tasks including navigation, form submission, extraction, and screenshots via Playwright and ARIA snapshots.

Community
Advanced
yigitkonuryigitkonur
11

convert-snapshot-nextjs

Convert saved HTML snapshots into buildable Next.js projects with self-hosted assets.

Community
Advanced
vimalinxvimalinx

dev-browser

Automates browser interactions while maintaining page state across script executions.

Community
Intermediate
Jia-Hong-PengJia-Hong-Peng

gstack

Automate persistent headless browser QA testing with Playwright and Chromium.

Community
Advanced