skills.rest
LuizEduPP
LuizEduPPCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser navigation, form filling, and page interaction via CLI.

Updated Apr 10, 2026
Search Tags:#cli#cdp#session-management#web-testing#browser-automation#agent-browser
One-click install
npx skills add https://github.com/LuizEduPP/skills --skill agent-browser-luizedupp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/LuizEduPP/skills/tree/main/agent-browser
Command: npx skills add https://github.com/LuizEduPP/skills --skill agent-browser-luizedupp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

agent-browser removes tedious manual browsing steps so agents can click buttons, fill forms, and gather data without repeated human guidance, especially on authenticated or dynamic single-page apps.

Core Features & Use Cases

  • CLI-first control: Use the agent-browser commands to open URLs, snapshot the accessibility tree, interact with @refs, manage tabs, and chain commands via Bash to keep the browser daemon alive.
  • Authentication & persistence: Import auth states, reuse Chrome profiles, and save session files or use the auth vault to keep logins valid across runs.
  • Observability & exports: Capture screenshots, PDFs, or videos, diff snapshots, stream sessions, and consult the reference guides for commands, profiling, and proxy strategies.
  • Use case: Automate regression testing or customer journey checks by scripting navigation through multiple pages, filling forms, waiting for selectors, and validating snapshots.

Quick Start

Tell agent-browser to open https://example.com, snapshot the page to gather refs, interact with the desired elements, and capture a screenshot to confirm completion.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser navigation and form filling for repetitive web tasks?▼

You automate browser navigation by using CLI commands to open URLs, snapshot the accessibility tree, interact with @refs, and chain commands via Bash to keep the browser daemon alive for form filling and data gathering.

What is the best way to maintain authenticated sessions for automated web testing?▼

Maintaining authenticated sessions involves importing auth states, reusing Chrome profiles, and saving session files or using the auth vault to keep logins valid across automated browser runs.

Do I need a specific browser environment to run CLI browser automation?▼

Running CLI browser automation requires a Chromium environment accessible via CDP and the agent-browser CLI toolchain to execute commands and manage session/auth vault features.

How do I capture screenshots and PDFs during automated web page interaction?▼

Capturing screenshots and PDFs during web interaction is done using the observability and exports features of the agent-browser CLI, which also records videos, diffs snapshots, and streams sessions.

Can I automate regression testing for dynamic single-page apps using CLI commands?▼

Automating regression testing for dynamic single-page apps is possible by scripting navigation, filling forms, waiting for selectors, and validating snapshots to verify customer journeys.

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
tilework-techtilework-tech
149

webapp-testing

Automate web application end-to-end testing with Python Playwright.

Official
Advanced
penghang1223penghang1223
1

browser-use

Automate browser interactions for web testing, form filling, and data extraction.

Community
Intermediate
mikkelkrogsholmmikkelkrogsholm
5

playwright-cli

Automate browser interactions for web testing, form filling, screenshots, and data extraction.

Community
Intermediate