skills.rest
Davie521
Davie521COMMUNITY
Explore all skills by this author →
GitHub

data-scraper-agent

Schedule scrapes from public sources and store enriched data in Notion, Sheets, or Supabase.

7|Updated Mar 4, 2026
Search Tags:#automation#supabase#notion#sheets#data-scraping#public-data#ai-enrichment
One-click install
npx skills add https://github.com/Davie521/claude-skills --skill data-scraper-agent-davie521
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-scraper-agent
Source: https://github.com/Davie521/claude-skills/tree/main/plugins/data/skills/data-scraper-agent
Command: npx skills add https://github.com/Davie521/claude-skills --skill data-scraper-agent-davie521

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Public data sources are scattered and manually collecting data is slow and error-prone. This Skill provides an automated AI-powered agent that schedules scrapes, enriches results with a free LLM, and stores outputs in Notion, Sheets, or Supabase, enabling continuous monitoring and data quality improvement.

Core Features & Use Cases

  • Schedule-driven scraping from diverse public sources (jobs, prices, news, GitHub repos, sports, events)
  • AI enrichment with Gemini Flash and scoring/classification
  • Flexible storage with Notion, Sheets, or Supabase; supports feedback loop and learning
  • Free hosting on GitHub Actions

Quick Start

Configure a Notion/Supabase/Sheets storage and GEMINI_API_KEY in your GitHub Secrets, then trigger the workflow to start data collection.

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 data scraping from public sources on a schedule?▼

Automated data scraping from public sources runs on a schedule using GitHub Actions, which triggers the Python agent to collect, enrich, and store data continuously. You configure the workflow, and it monitors sources without manual intervention.

Can I use AI enrichment to classify scraped job board or news data?▼

AI enrichment classifies scraped job board, news, or sports data using Gemini Flash. The free tier LLM processes collected public data, applying scoring and classification to improve data quality before storing results in your configured database.

Does this data scraping agent support storing results in Notion, Sheets, or Supabase?▼

The data scraping agent supports storing results in Notion, Sheets, and Supabase. You must configure your chosen storage backend and the GEMINI_API_KEY in your GitHub Secrets before triggering the workflow to start data collection.

What do I need to set up to run a Python scraper on GitHub Actions?▼

To run a Python scraper on GitHub Actions, you need Python, a configured storage backend like Supabase or Notion, and a GEMINI_API_KEY stored in GitHub Secrets. Free hosting on GitHub Actions runs the scheduled scraping workflow.

Is there a free way to monitor prices and GitHub repos automatically?▼

Monitoring prices and GitHub repos automatically is free using GitHub Actions for hosting and Gemini Flash for AI enrichment. The scheduler triggers the Python agent to collect public data and store it in Notion or Sheets without server costs.

Related Skills

Explore More Data & Analytics Skills→
aayushsoamaayushsoam
1

data-scraper-agent

Automate scheduled collection and enrichment of public data sources.

Community
Advanced
Ryko1141Ryko1141

kpi-dashboards

Generate real-time KPI dashboards from Supabase, Creem.io, Google Sheets, and Vercel Analytics.

Community
Advanced
woxiangyangzhimaowoxiangyangzhimao
3

data-scraper-agent

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

Community
Advanced
GrassHopper42GrassHopper42

skillify

Scrape web pages and codify data into browser skills.

Community
Intermediate