harvard-artifacts-collection-analytics

Extract, transform, and analyze Harvard Art Museums API data with Python and SQL.

5|1|Updated May 16, 2026
One-click install
npx skills add https://github.com/Aradotso/data-skills --skill harvard-artifacts-collection-analytics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: harvard-artifacts-collection-analytics
Source: https://github.com/Aradotso/data-skills/tree/main/skills/harvard-artifacts-collection-analytics
Command: npx skills add https://github.com/Aradotso/data-skills --skill harvard-artifacts-collection-analytics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires streamlit, pandas, requests, mysql-connector-python, plotly, python-dotenv, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the process of working with the Harvard Art Museums API, enabling efficient data extraction, transformation, and analysis of art artifacts.

Core Features & Use Cases

  • ETL Pipeline: Extracts and transforms data from the API into a normalized relational database structure.
  • Data Analysis: Executes predefined SQL queries for insights on artifacts, cultures, centuries, and media.
  • Visualization: Generates interactive dashboards to visualize data using Plotly charts.
  • Use Case: Use this Skill to quickly analyze the Harvard Art Museums' artifact collection, understand the cultural distribution of artifacts, and visualize their color usage patterns.

Quick Start

Execute the following command to run the Streamlit app and access the analytics dashboard: streamlit run app.py

Frequently Asked Questions about harvard-artifacts-collection-analytics

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

FAQPage Schema
How do I extract and analyze data from the Harvard Art Museums API?

To extract and analyze Harvard Art Museums API data, this Skill runs an automated ETL pipeline that pulls artifacts into a normalized relational database, then uses predefined SQL queries and Streamlit dashboards for interactive visualization.

What do I need to set up before visualizing Harvard Art Museums artifacts?

Before visualizing artifacts, you need a Harvard Art Museums API key, an active database connection, and a Python environment installed with streamlit, pandas, requests, mysql-connector-python, plotly, and python-dotenv.

Can I use Streamlit and Plotly to visualize cultural distribution of art collections?

Yes, you can use Streamlit and Plotly to visualize art collections. This Skill generates interactive dashboards that display insights on artifact cultures, centuries, and color usage patterns directly from the extracted data.

How does the ETL pipeline transform API data into a relational database structure?

The ETL pipeline transforms API data by extracting raw artifact records from the Harvard Art Museums API and loading them into a normalized relational database structure using Python and SQL for downstream analysis.

What are the limitations of using Streamlit for artifact data analysis?

A limitation of this Streamlit analysis approach is that it depends on predefined SQL queries for insights on artifacts, cultures, centuries, and media, meaning custom ad-hoc querying requires manual SQL modifications within the scripts.