data-scraper-agent - Automate public data collection and enrichment
Builds scheduled agents that collect public data, enrich it with Gemini, store results, and use feedback to improve over time.
Tags
Updated: 2026-10-19Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Collect public data
- Scrape HTML sources
- Read RSS feeds
- Call public APIs
- Enrich data with Gemini
- Batch AI analysis
- Store results
- Schedule GitHub Actions runs
- Learn from user feedback
Inputs
- Public source URL, API, or RSS feed
- Target data fields
- Storage destination
- AI enrichment preferences
- Run frequency
- User context and criteria
Outputs
- Scraper project files
- Collected data records
- AI-enriched records
- Stored database entries
- Scheduled workflow
- Feedback history file
Requirements
- Python environment
- Gemini API access
- GitHub Actions-enabled repository
- Storage service access when used