skills.rest
Wike-CHI
Wike-CHICOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser interactions and extract structured page content via CLI.

2|Updated Mar 31, 2026
Search Tags:#automation#browser#headless#screenshot#web-scraping#form-filling
One-click install
npx skills add https://github.com/Wike-CHI/acquisition-agent --skill agent-browser-wike-chi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Wike-CHI/acquisition-agent/tree/main/skills/agent-browser
Command: npx skills add https://github.com/Wike-CHI/acquisition-agent --skill agent-browser-wike-chi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Agent Browser removes the manual, fragile steps of navigating web UIs, locating elements, and extracting structured information by providing a fast CLI-driven headless browser interface that agents can control programmatically for scraping, form filling, UI testing, and demo capture.

Core Features & Use Cases

  • Ref-based Interactions: Snapshot returns stable element refs (e.g., @e1) so agents can click, fill, and query elements deterministically.
  • Comprehensive Controls: Navigate, back/forward, reload, session isolation, viewport/device emulation, and geolocation for realistic testing.
  • Data Extraction & Output: Interactive snapshots, get text/html/value/attr, JSON output mode for machine-readable scraping and structured extraction.
  • Media & Debugging: Screenshots, full-page capture, PDF export, video recording, console/log access, trace recording, and network routing for testing and demo creation.
  • Advanced Workflows: Uploads, downloads, cookie/storage management, request mocking, and semantic find commands enable end-to-end automation and resilient scraping.
  • Use Case: Automatically log into an application with saved state, navigate to a report page, snapshot interactive elements, extract structured rows into JSON, and capture a PDF report.

Quick Start

Open https://example.com, take an interactive snapshot, fill the email and password refs, click the login ref, and return the resulting page text.

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 extract structured data from modern web pages?▼

Automate web scraping by using a headless browser to navigate pages, take interactive snapshots, and extract structured content like text, HTML, attributes, or JSON from web elements.

How does headless browser automation handle dynamic form filling and UI testing?▼

Headless browser automation handles form filling and UI testing by using stable element refs from snapshots to deterministically click, fill inputs, and query elements across isolated sessions.

Can I capture screenshots and PDF exports during automated web interactions?▼

Yes, automated web interactions support capturing screenshots, full-page captures, PDF exports, and video recording to document testing workflows and generate visual demo content.

What's the best way to manage session state and cookies for automated web scraping workflows?▼

Manage scraping workflows by utilizing session isolation, cookie and storage management, and saved login states to navigate authenticated areas and extract data across multiple independent sessions.

Does headless web scraping support network request routing and request mocking?▼

Yes, headless web scraping supports network request routing, request mocking, and console access to intercept network traffic and test application behavior under controlled conditions.

Do I need a specific CLI binary to run automated browser interactions?▼

Yes, automated browser interactions require a dedicated CLI binary for primary execution, with an optional Node fallback available for environments where the binary is not installed.

Related Skills

Explore More Software Engineering Skills→
kbtimekbtime

Agent Browser

Automate web interactions and extract structured data via the agent-browser CLI.

Community
Intermediate
Blake-JohnBlake-John

pymupdf

Convert PDF documents into Markdown, JSON, and text for LLM workflows.

Community
Intermediate
Magnatrix-LabMagnatrix-Lab
1

competitive-ads-extractor

Extract competitor ad insights via web scraping and structured data processing.

Community
Advanced
FReptar0FReptar0

browser-use

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

Community
Advanced