skills.rest
documenso
documensoOFFICIAL
Explore all skills by this author →
Website𝕏@documensoGitHub

agent-browser

Automate browser interactions for navigation, form filling, screenshots, and content extraction.

14.3k|3.0k|Updated Mar 12, 2023
Search Tags:#screenshots#session-management#e2e-testing#web-scraping#browser-automation#form-filling#proxy-support
One-click install
npx skills add https://github.com/documenso/documenso --skill agent-browser-documenso
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/documenso/documenso/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/documenso/documenso --skill agent-browser-documenso

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates repetitive and error-prone browser tasks so users can programmatically navigate sites, complete forms, perform authenticated workflows, capture screenshots or PDFs, and reliably extract page content without manual clicking or visual inspection.

Core Features & Use Cases

  • Interactive Element Snapshotting: Compact element refs (@e1, @e2) reduce context size and enable precise interactions.
  • Form Filling & Authentication: Discover login forms, perform credential entry, handle 2FA workflows, and save/load session state for reuse.
  • Data Extraction & Capture: Pull text, save full-page screenshots, export PDFs, and record video for debugging or CI artifacts.
  • Session & Proxy Management: Named isolated sessions, state persistence, parallel sessions, and proxy support for geo-testing or scraping.
  • Mobile & Visual Debugging: iOS simulator support, headed mode, element highlighting, and recording for documentation or troubleshooting.

Quick Start

Open the target URL, run an interactive snapshot to identify refs, fill the username and password fields with the discovered refs, click the submit button, wait for navigation to complete, and save the session state to a file.

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 interactions to fill forms and capture screenshots?▼

Automate browser interactions by using deterministic CLI commands to navigate pages, fill forms, click elements, and capture full-page screenshots. The tool snapshots interactive elements into compact refs like @e1, enabling precise targeting without manual inspection.

How does session management work for authenticated workflows and web scraping?▼

Session management for authenticated workflows works by saving and loading session state to maintain logins. You can run isolated named sessions in parallel, configure proxies for geo-testing or scraping, and reuse authenticated states across multiple browser automation tasks.

Can I run end-to-end web testing in headless mode and export PDFs?▼

You can run end-to-end web testing in both headed and headless execution modes. The automation tool extracts page text, exports PDFs, captures full-page screenshots, and records video for debugging or generating CI artifacts.

What is the best way to extract page content and handle 2FA login flows?▼

The best way to extract page content and handle 2FA login flows is through interactive element snapshotting. The tool discovers login forms, performs credential entry, manages 2FA workflows programmatically, and pulls text content reliably without manual clicking.

Does browser automation support mobile simulators and visual debugging?▼

Browser automation supports iOS simulators for mobile testing and provides visual debugging features. You can use headed mode with element highlighting to visually inspect interactions, record video for documentation, and troubleshoot automated web workflows.

Why use compact element refs for web scraping instead of standard selectors?▼

Compact element refs reduce context size and enable precise interactions during web scraping and form filling. Instead of relying on complex standard selectors, the tool generates deterministic refs like @e1 to reliably click elements and extract page content.

Related Skills

Explore More Software Engineering Skills→
polymerdaopolymerdao
1

polymer-pay-notte

Automate browser tasks and AI agent workflows via the Polymer Pay proxy.

Official
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
xxziikoxxziiko

playwright-e2e

Automate Playwright end-to-end test execution and debugging across projects.

Community
Intermediate
doanchienthangdevdoanchienthangdev
4

Testing with Playwright

Create end-to-end web application tests using Playwright.

Community
Advanced