data-scraper-agent

Automate public data collection and AI enrichment with Python and Gemini Flash.

1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/Michae2xl/claude-skills-michael --skill data-scraper-agent-michae2xl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-scraper-agent
Source: https://github.com/Michae2xl/claude-skills-michael/tree/main/skills/data-scraper-agent
Command: npx skills add https://github.com/Michae2xl/claude-skills-michael --skill data-scraper-agent-michae2xl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, BeautifulSoup, playwright, notion-client, gspread, supabase, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the collection of data from public sources, such as job boards, prices, news, GitHub, and sports, and enriches it with AI to provide valuable insights.

Core Features & Use Cases

  • Automated Data Collection: Monitor and collect data from any public source on a schedule.
  • AI Enrichment: Use a free LLM to score, summarize, classify, and match data items.
  • Storage Options: Store results in Notion, Sheets, or Supabase.
  • Use Case: For example, you can build an agent to track the latest job listings matching your resume criteria or monitor price changes of products you're interested in.

Quick Start

Use the data-scraper-agent skill to create a scraper for job listings from 'https://www.example.com/jobs'.

Frequently Asked Questions about data-scraper-agent

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

FAQPage Schema
How do I automate data scraping from public sources on a schedule?

Automating data scraping involves using Python scripts with requests and BeautifulSoup to extract public data on a schedule. This skill handles scheduling, collection, and AI enrichment to provide insights from sources like job boards or prices.

Can I use AI to enrich and summarize scraped web data?

Yes, you can use AI to enrich scraped web data by processing it with Gemini Flash. This free LLM scores, summarizes, classifies, and matches data items automatically, transforming raw public data into valuable insights.

Does this data scraping approach support exporting results to Notion and Google Sheets?

Yes, this data scraping approach supports exporting results to Notion and Google Sheets. It provides storage options for collected and enriched data by integrating directly with Notion, Sheets, and Supabase.

What Python libraries are required for automated web data collection?

Automated web data collection requires Python along with the requests, BeautifulSoup, and playwright libraries. These dependencies handle HTTP requests, HTML parsing, and browser automation for scraping public sources.

What is the best way to track price changes and job listings from public websites?

The best way to track price changes and job listings is building an automated scraper using Python and a free LLM. This approach collects data from public sources, enriches it with AI, and stores results in your preferred database.

Do I need to pay for an LLM to classify and match scraped data items?

No, you do not need to pay for an LLM to classify and match scraped data items. This skill uses Gemini Flash, a free LLM, to handle AI enrichment tasks like scoring, summarizing, classifying, and matching data.