skills.rest
lofty-thoughts
lofty-thoughtsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser interactions and extract web content via CLI.

Updated Feb 21, 2026
Search Tags:#cli#session-management#screenshot#web-scraping#browser-automation#visual-testing#form-filling
One-click install
npx skills add https://github.com/lofty-thoughts/botdaddy --skill agent-browser-lofty-thoughts
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/lofty-thoughts/botdaddy/tree/main/seed/skills/agent-browser
Command: npx skills add https://github.com/lofty-thoughts/botdaddy --skill agent-browser-lofty-thoughts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Many web tasks—filling forms, navigating login flows, capturing screenshots, extracting page data, and testing UIs—are repetitive, brittle, and time-consuming when done by hand. agent-browser provides a CLI-driven, scriptable browser automation layer that reduces manual effort, preserves session state, and makes interactions deterministic and auditable.

Core Features & Use Cases

  • Interactive compact snapshots that produce stable refs (e.g., @e1) for reliable element targeting and low-context AI prompts.
  • Comprehensive CLI commands for navigation, snapshotting, interaction (click/fill/select), waiting strategies, screenshots, PDF output, visual diffing, video recording, and profiler traces.
  • Session and state management with save/load, parallel named sessions, CDP connectivity, proxy support, and mobile/iOS simulator workflows for authentication automation, scraping, visual regression, and E2E testing.
  • Ready-to-use templates and detailed references for commands, snapshot lifecycles, authentication patterns, profiling, proxy configuration, and recording workflows.

Quick Start

Open the target site, take an interactive snapshot to discover refs, fill the required fields using those refs, submit the form, and save the authenticated session state if needed.

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 with persistent login sessions?▼

Automate web scraping and form filling by using CLI commands to navigate sites, take interactive snapshots, fill fields via stable refs, and save authenticated session state for reuse across parallel named sessions.

Can I run headless browser automation and capture screenshots or video recordings?▼

Yes, headless browser automation supports capturing screenshots, generating PDF output, recording video, and collecting profiler traces to audit DOM inspection and visual diff workflows.

Does browser automation work with mobile simulators and proxy configuration?▼

Browser automation supports mobile and iOS simulator workflows alongside proxy configuration and CDP connectivity, enabling authentication automation and E2E testing across simulated desktop and mobile environments.

What is the best way to target DOM elements reliably for automated end-to-end testing?▼

The best way to target DOM elements is by taking interactive compact snapshots that produce stable refs like @e1, ensuring reliable element targeting for clicks, form fills, and low-context AI prompts.

How do I perform visual regression testing and compare UI differences automatically?▼

Perform visual regression testing by capturing screenshots during browser interactions and applying visual diffing commands to detect and compare UI differences automatically across desktop and mobile simulators.

Why does my browser automation script fail to maintain state across multiple runs?▼

Browser automation scripts fail to maintain state when session persistence is not configured; use the save and load state management commands to preserve login flows and authenticated profiles across multiple runs.

Related Skills

Explore More Software Engineering Skills→
npc-livenpc-live
168

agent-browser

Automate browser interactions via Chrome/CDP using the agent-browser CLI.

Official
Intermediate
CygnusfearCygnusfear
5

chrome-devtools

Control Chrome DevTools Protocol to automate browser interactions and capture console, network, and screenshots.

Community
Advanced
stephendorstephendor
1

executing-plans-extras

Verify CLI command execution against output, state changes, and exit codes.

Community
Intermediate
wormholecowboywormholecowboy
1

agent-browser

Automate browser tasks via CLI with headless Chromium.

Community
Intermediate