BigHugger
sk Skill · affaan-m

data-scraper-agent

Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Runs on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.

installs 8w
1,792
30-day movement
starts with the next reading
Related entries
5
Connections
0
yamlpythonJavaScript

A skill that guides an AI coding agent through building a scheduled, AI-enriched data collection agent in Python for public sources like APIs, HTML pages, RSS feeds, and JS-rendered sites. It covers a ten-step workflow from source connectors through Gemini Flash enrichment, storage (Notion/Sheets/Supabase), feedback learning, and a GitHub Actions runner.

Reach for it when you need to scaffold a free, unattended pipeline that monitors or collects public data on a schedule.

Use it to

  • Build a scheduled scraper for a public API or website
  • Enrich collected records with Gemini Flash in batches
  • Store results in Notion, Sheets, or Supabase
  • Add a feedback loop that learns from user decisions
  • Set up a free GitHub Actions cron runner

For Developers building automated public-data collection bots

Host repository
affaan-m/ECC
Installs, lifetime
3,000
Installs, 8 weeks
1,792
Host stars
261k
Host language
JavaScript
topicsweb-scrapingagentsgeminigithub-actionspythonscheduling