skills.rest
multiplex-ai
multiplex-aiOFFICIAL
Explore all skills by this author →
Website𝕏@Muggle_AIGitHub

data-scraper-agent

Scrape, enrich, and store public data on a schedule.

2|Updated Mar 20, 2026
Search Tags:#automation#workflow#ai#data#notion#scraping
One-click install
npx skills add https://github.com/multiplex-ai/muggle-ai-teams --skill data-scraper-agent-multiplex-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-scraper-agent
Source: https://github.com/multiplex-ai/muggle-ai-teams/tree/main/skills/data-scraper-agent
Command: npx skills add https://github.com/multiplex-ai/muggle-ai-teams --skill data-scraper-agent-multiplex-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manual data collection from public sources is time-consuming, error-prone, and expensive when scaling; this skill automates end-to-end data gathering, enrichment, and storage, enabling you to monitor multiple sources with a low-friction setup.

Core Features & Use Cases

  • Automates three-layer data pipelines: Collect → Enrich → Store, running on a schedule without hosting costs.
  • Free enrichment via Gemini Flash and open-source tooling; stores results to Notion, Google Sheets, or Supabase; learns from user feedback to improve over time.
  • Use cases include tracking job boards, price changes, news, GitHub repos, sports scores, and public listings; producible workflows that can be extended to any public data source.

Quick Start

Configure GEMINI_API_KEY and storage credentials, then run the agent to start scheduled data collection across public sources.

Frequently Asked Questions about data-scraper-agent

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

FAQPage Schema
How do I automate web scraping and store the results in Notion on a schedule?▼

You can automate web scraping to Notion by running a three-layer pipeline that collects, enriches, and stores public data on a schedule. It uses Python scrapers and GitHub Actions for continuous monitoring without hosting costs.

What is the best way to scrape job boards and track price changes automatically?▼

Scraping job boards and tracking prices is done via an automated data collection pipeline. It targets public data streams, enriches them with Gemini Flash, and stores results in Notion, Sheets, or Supabase.

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

Yes, you need a Gemini API key to enrich scraped data. The pipeline uses Gemini Flash for free data enrichment and implements a model fallback chain to ensure processing continuity.

Can I use GitHub Actions to host a Python scraper for continuous monitoring?▼

Yes, you can use GitHub Actions to host a Python scraper for continuous monitoring. The pipeline runs scheduled data collection across public sources without incurring hosting costs.

How does the scraping pipeline handle duplicate data entries?▼

The scraping pipeline handles duplicate data entries through built-in deduplication. This ensures continuous monitoring of public sources like job boards and news streams does not store redundant records.

Does this data scraping approach work with Supabase and Google Sheets?▼

Yes, this data scraping approach works with Supabase and Google Sheets. The pipeline stores enriched results directly into Notion, Google Sheets, or Supabase based on configured credentials.

Related Skills

Explore More Data & Analytics Skills→
scanadyscanady

tech-data-scraper

Automate scheduled data collection from public sources with AI enrichment.

Community
Intermediate
AppleLampsAppleLamps
1

rate-limit-setup

Implement a database-backed rate-limiting system for API requests.

Community
Advanced
vinitgirdharvinitgirdhar

data-scraper-agent

Collect public data, enrich with Gemini Flash, and store in databases.

Community
Advanced
woxiangyangzhimaowoxiangyangzhimao
3

data-scraper-agent

Automates scheduled scraping of public sources with AI enrichment into databases like Notion.

Community
Advanced