skills.rest
helloluis
helloluisCOMMUNITY
Explore all skills by this author →
Website𝕏@helloluisGitHub

kamai

Automate web browsing tasks with Puppeteer or Playwright for navigation and content extraction.

Updated Mar 25, 2026
Search Tags:#automation#data extraction#javascript#form filling#web-browsing#clicking
One-click install
npx skills add https://github.com/helloluis/kamai --skill kamai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kamai
Source: https://github.com/helloluis/kamai/tree/main
Command: npx skills add https://github.com/helloluis/kamai --skill kamai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables automated headless browsing of websites, allowing extraction of clean text, links, and form fields, thereby simplifying data retrieval from complex or JavaScript-heavy pages.

Core Features & Use Cases

  • Website Navigation & Data Extraction: Programmatically browse websites, perform interactions like filling forms, clicking buttons, and navigating multi-page flows.
  • Use Case: For a researcher needing to scrape data from dynamic portals or legacy ASPX sites, this Skill allows scripting complex workflows with minimal manual effort.
  • Flexibility for Automation: Performs actions like scrolling, waiting, evaluating JavaScript, and bounding text extraction, suitable for automating digital workflows.

Quick Start

Provide a URL and instructions to the AI to visit the page, perform actions such as clicking a button to reveal data, and then extract the main text content.

Frequently Asked Questions about kamai

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

FAQPage Schema
How do I extract data from JavaScript-heavy websites?▼

You can extract data from JavaScript-heavy websites by automating headless browsing to navigate dynamic portals, wait for rendered content, and pull clean text, links, and form fields. It scripts user interactions like clicking and scrolling to retrieve data reliably.

Can I automate form filling on legacy ASPX sites?▼

Yes, you can automate form filling on legacy ASPX sites by scripting user actions programmatically. The Skill handles navigating multi-page flows, inputting data, and clicking buttons to fulfill complex automation workflows on legacy portals.

Do I need Playwright to scrape dynamic web pages?▼

Yes, you need Playwright or Puppeteer libraries installed to scrape dynamic web pages using this Skill. These dependencies provide the headless browser environment required to evaluate JavaScript and interact with complex page elements.

What is the best way to automate clicking buttons to reveal hidden web content?▼

The best way to automate clicking buttons to reveal hidden web content is by providing a URL and scripting instructions to the AI. The Skill programmatically performs actions like waiting and bounding text extraction to capture data only visible after interaction.

Why does web browsing automation fail on JavaScript-dependent sites?▼

Web browsing automation often fails on JavaScript-dependent sites when tools do not wait for dynamic content to render. This Skill overcomes this by evaluating JavaScript directly and ensuring reliable data collection from complex pages across various scenarios.

Related Skills

Explore More Content & Communication Skills→
nirholasnirholas
443

algorithm-cultivation

Train an X/Twitter algorithmic feed using Puppeteer and LLMs.

Community
Advanced
alibabaalibaba
10.5k

pdf-extractor

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

Official
Intermediate
ironkid90ironkid90

firecrawl-build-interact

Integrate browser interactions like clicks and form submissions into Firecrawl.

Community
Intermediate
otrebuotrebu
4

web-to-markdown

Batch-convert JavaScript-rendered web pages to a timestamped Markdown file.

Community
Advanced