platonaiplatonaiCommunityยท21 Agent Skills Included

Browser4

AI-driven browser automation, web scraping, and data extraction at scale

Automates real browsers through a CLI so AI agents can navigate pages, click, fill forms, take screenshots, and extract structured data. Eliminates manual scraping scripts, brittle selectors, and token-heavy LLM extraction with X-SQL queries and local ML clustering. Scales from single-page tasks to swarm crawling of hundreds of thousands of pages per day, with plugins for SEO audits, PDFs, and CAPTCHA handling.
npx skills add platonai/Browser4 --all -g -y
Available:

Gives the AI agent the system architecture, CLI-to-browser dispatch chain, known browser pitfalls, and build/test commands it needs to operate and extend this browser automation suite correctly.

All Skills in This Repository (21)

Pure Emerald Level Indicators
๐Ÿ“ฆ In Repo
platonaiplatonai

script-runner

Validate Python script execution pipelines for allowed tools, timeouts, and output limits.

Community
Basic
๐Ÿ“ฆ In Repo
platonaiplatonai

pdf

Extract text and structured data from PDF documents using pypdf and pdfplumber.

Community
Intermediate
๐Ÿ“ฆ In Repo
platonaiplatonai

form-filling

Automate web form input and submission with provided data.

Community
Intermediate
๐Ÿ“ฆ In Repo
platonaiplatonai

weather

Fetch real-time weather and 7-day forecasts for locations via Open-Meteo APIs.

Community
Intermediate
๐Ÿ“ฆ In Repo
platonaiplatonai

web-scraping

Extract titles, text, and structured fields from web pages using browser automation.

Community
Intermediate
๐Ÿ“ฆ In Repo
platonaiplatonai

data-validation

Validate data against predefined and custom rules.

Community
Advanced
๐Ÿ“ฆ In Repo
platonaiplatonai

mcp-builder

Develop MCP servers for LLM integration with Python and Node/TypeScript SDKs.

Community
Advanced
๐Ÿ“ฆ In Repo
platonaiplatonai

task-token-usage

Analyzes Claude Code session traces to report token usage per task.

Community
Intermediate
๐Ÿ“ฆ In Repo
platonaiplatonai

organize-task-files

Organizes Coworker task files across pipeline stages by scanning and parsing them automatically.

Community
Advanced
๐Ÿ“ฆ In Repo
platonaiplatonai

browser4-cli

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

Community
Advanced
๐Ÿ“ฆ In Repo
platonaiplatonai

coworker

Automates file-queue task pipelines using PowerShell workers and GitHub Copilot.

Community
Advanced
๐Ÿ“ฆ In Repo
platonaiplatonai

test-production

Acceptance-tests the published browser4-cli release by installing, exercising, and uninstalling it.

Community
Intermediate

Frequently Asked Questions

FAQPage Schema
How to install Browser4?โ–ผ

Run `npx skills add platonai/Browser4 --all -g -y` in your terminal to install all skills in this suite globally.

What can Browser4 automate in a browser?โ–ผ

It navigates pages, clicks and fills forms, takes screenshots, handles dialogs, and extracts structured data using CSS selectors or X-SQL queries. AI agents can also submit plain-English tasks and let the built-in agent plan and execute the browser steps autonomously.

Can Browser4 scrape data without using LLM tokens?โ–ผ

Yes. X-SQL queries and CSS selectors extract data deterministically, and the WebMiner tool clusters downloaded HTML pages into spreadsheets and reports entirely locally with zero LLM tokens.

Does Browser4 work with Claude Code and other AI agents?โ–ผ

Yes. It exposes browser control through MCP over HTTP and follows the standard SKILL.md format, so it works with Claude Code, Codex, OpenClaw, and similar agents.

Can Browser4 handle large-scale crawling?โ–ผ

Yes. Its swarm mode runs parallel browser contexts designed for 100k to 200k page visits per machine per day, with plugins for CAPTCHA solving, SEO audits, and media processing.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’