skills.rest
starrank-soft
starrank-softOFFICIAL
Explore all skills by this author →
GitHub

data-scraper-agent

Build scheduled Python scrapers that enrich data with Gemini and store results.

Updated Jun 24, 2026
Search Tags:#automation#ai#gemini#scraping#github-actions#data-collection
One-click install
npx skills add https://github.com/starrank-soft/PixelArraySkill --skill data-scraper-agent-starrank-soft
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-scraper-agent
Source: https://github.com/starrank-soft/PixelArraySkill/tree/main/skills/data-scraper-agent
Command: npx skills add https://github.com/starrank-soft/PixelArraySkill --skill data-scraper-agent-starrank-soft

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, beautifulsoup4, lxml, python-dotenv, pyyaml, notion-client.

What problem does it solve?

This skill solves the challenge of manually monitoring and collecting data from public sources by providing a framework to build automated, AI-enriched scrapers that run for free on GitHub Actions.

Core Features & Use Cases

  • Automated Collection: Scrape websites, APIs, and RSS feeds on a set schedule.
  • AI Enrichment: Use Gemini Flash to score, summarize, and classify collected data automatically.
  • Seamless Storage: Sync results directly to Notion, Google Sheets, or Supabase.
  • Use Case: Automatically monitor job boards for specific roles, track product price drops, or summarize new GitHub repository releases without paying for hosting.

Quick Start

Set up a new data scraper agent by running the initialization script and configuring your target URL and storage provider in the config.yaml file.

Frequently Asked Questions about data-scraper-agent

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

FAQPage Schema
How do I build an automated data scraper that runs for free?▼

To build an automated data scraper for free, use this Skill to schedule Python web scraping scripts on GitHub Actions, eliminating the need for paid hosting infrastructure while collecting data from public sites.

Can I use AI to summarize and score data collected from web scraping?▼

Yes, you can use AI to summarize scraped data. This Skill integrates Gemini Flash API access to automatically score, classify, and enrich the raw data collected from websites and APIs after extraction.

Does this data collection agent support syncing scraped data to Notion?▼

Yes, this data collection agent supports syncing scraped data to Notion. It also integrates with Google Sheets and Supabase to seamlessly store and organize your AI-enriched results in real-time.

What's the best way to monitor job boards and price drops without a server?▼

The best way to monitor job boards or price drops without a server is configuring an automated scraper agent on GitHub Actions. This Skill schedules Python scripts to check public sources and syncs updates directly to Notion.

Do I need Python and Gemini API access to run automated web scrapers?▼

Yes, you need Python and Gemini API access to run these automated web scrapers. The framework relies on Python libraries like requests and beautifulsoup4 for extraction, and uses the Gemini API for AI data enrichment.

How does scheduling work for automated data collection on GitHub Actions?▼

Scheduling automated data collection on GitHub Actions works by configuring cron triggers in your repository. This Skill provides the framework to set these schedules in a config.yaml file, executing scrapers at defined intervals without external servers.

Related Skills

Explore More Data & Analytics Skills→
klu-devklu-dev
2

data-scraper-agent

Automate data collection from public websites and APIs with AI enrichment.

Community
Advanced
twwchtwwch
68

meeting-summary

Generate structured meeting summaries with sections for information, decisions, and action items.

Community
Intermediate
Penitence1992Penitence1992

cloud-storage-skill

Generate presigned URLs and upload or download files across S3 and OSS in Go backends.

Community
Intermediate
thangvawnthangvawn

data-scraper-agent

Automate data collection from public websites and APIs with scheduled Python scripts.

Community
Advanced