engineering-data-scraper - Automated AI-Powered Data Collection Agent
Builds automated data collection agents that scrape web sources, enrich data with Gemini Flash, store results, and run on GitHub Actions.
Tags
Updated: 2026-09-24Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Scrape public web sources
- Enrich data with Gemini Flash
- Store results in database
- Learn from user feedback
- Deduplicate items by URL
Inputs
- Target data source URL
- Gemini API key
- Notion API token
- Configuration file
Outputs
- Notion database pages
- Feedback JSON file
- Environment template file
Requirements
- Python runtime environment
- Gemini Flash API access
- GitHub Actions environment
- Notion API access