tech-data-scraper

Automate scheduled data collection from public sources with AI enrichment.

Updated Jan 28, 2026

Search Tags:#automation #ai #data #notion #gemini #scraper

Ready to run

npx skills add https://github.com/scanady/nexus-agents --skill tech-data-scraper

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tech-data-scraper
Source: https://github.com/scanady/nexus-agents/tree/main/skills/tech-data-scraper
Command: npx skills add https://github.com/scanady/nexus-agents --skill tech-data-scraper

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Gather, enrich, and store public data automatically, reducing manual research time by providing an end-to-end data-scraping workflow that runs on free infrastructure.

Core Features & Use Cases

Automated data collection from public sources (web, APIs, RSS) on a schedule
AI enrichment of collected items using Gemini (scores, summaries, notes)
Flexible storage targets (Notion, Google Sheets, Supabase) with deduplication and feedback learning
Fully free stack using GitHub Actions cron and Notion/Sheets/Supabase free tiers
Real-world use: monitor prices, track job boards, or gather news data for dashboards

Quick Start

Configure your storage and Gemini API key, then run the orchestrator to start the first automated scrape.

Frequently Asked Questions about tech-data-scraper

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

FAQPage Schema

How do I automate web data collection from public sources on a schedule?▼

Automated data collection from public sources runs on a free-stack architecture using GitHub Actions cron for scheduling, gathering web, API, or RSS data without manual research time.

Can I use Notion or Google Sheets to store scraped data automatically?▼

Scraped data can be stored automatically in Notion, Google Sheets, or Supabase. These flexible storage targets support deduplication and feedback learning to manage collected items.

How does AI enrichment work for scraped data items?▼

AI enrichment processes collected items using the Gemini API to generate scores, summaries, and notes, adding analytical value to the raw data gathered from public sources.

Do I need a Gemini API key to enrich collected data?▼

Yes, a Gemini API key is required for AI enrichment tasks. You also need storage credentials for Notion, Google Sheets, or Supabase to save and manage the scraped results.

What public data sources can I scrape for dashboards and monitoring?▼

You can scrape job boards, prices, news, GitHub repos, and sports data. Any public web data source, including APIs and RSS feeds, can be monitored for dashboards.

Is there a free way to run an automated data scraper continuously?▼

Yes, this data scraper runs on a fully free stack using GitHub Actions cron for scheduling and the free tiers of Notion, Google Sheets, or Supabase for storage.