What problem does it solve?
Manually collecting and tracking public data from job boards, e-commerce sites, news feeds, and other sources is time-consuming, difficult to schedule, and often requires paid hosting. This Skill eliminates that overhead by enabling you to build fully automated, AI-powered data collection agents that run for free on GitHub Actions.
Core Features & Use Cases
- Scheduled Scraping: Automatically collect data from any public website, API, or RSS feed on a custom schedule (hourly, daily, weekly etc.)
- AI Enrichment: Use free Gemini Flash to score, summarise, and classify collected items based on your custom priorities and context
- Flexible Storage: Push results directly to Notion, Google Sheets, or Supabase for easy review and analysis
- Feedback Learning: The agent improves over time by learning from your accept/reject decisions on collected items
- Common Use Cases: Monitor job listings for relevant roles, track product prices for drops, aggregate industry news, summarise new GitHub releases, and more
Quick Start
Use the data-scraper-agent skill to build an automated agent that monitors Hacker News for AI startup funding news and stores scored results in your Notion workspace.