Agent skill · data analytics · aradotso
harvard-artifacts-collection-analytics
harvard-artifacts-collection-analytics — an agent skill for coding agents.
Why this skill is useful
Provides a detailed ETL pipeline and SQL schema specifically for the Harvard Art Museums API, which the AI wouldn't reliably generate on its own.
What it needs
Requires mysql-connector-python, pandas, plotly, python-dotenv, requests, streamlit installed locally. Requires harvard account access. About 5k tokens when loaded. Last updated 2026-08-05. 5 stars on the source repository.
What this skill does
bash Clone the repository git clone https://github.com/Manali0711/Harvard-Artifacts-Collection-Data-Engineering-Analytics-App.git cd Harvard-Artifacts-Collection-Data-Engineering-Analytics-App Install dependencies pip install -r requirements.txt txt streamlit pandas requests mysql-connector-python plotly python-dotenv env Harvard Art Museums API HARVARDAPIKEY=yourapikeyhere Database Configuration DBHOST=yourdatabasehost DBPORT=3306 DBUSER=yourdatabaseuser DBPASSWORD=yourdatabasepassword DBNAME=harvardartifacts sql -- Artifact Metadata CREATE TABLE artifactmetadata ( id INT PRIMARY KEY, title VARCHAR(500), culture VARCHAR(255), century VARCHAR(100), classification VARCHAR(255), department VARCHAR(255), division VARCHAR(255), dated VARCHAR(255), period VARCHAR(255), technique VARCHAR(500), medium VARCHAR(500), dimensions VARCHAR(500), people TEXT, url VARCHAR(500) ); -- Artifact Media CREATE TABLE artifactmedia ( mediaid INT AUTOINCREMENT PRIMARY KEY, artifactid INT, baseimageurl VARCHAR(500), format VARCHAR(50), height INT, width INT, FOREIGN KEY (artifactid) REFERENCES artifactmetadata(id) ); -- Artifact Colors CREATE TABLE artifactcolors ( colorid INT AUTOINCREMENT PRIMARY KEY, artifactid INT, color VARCHAR(50), percent FLOAT, FOREIGN KEY (artifactid) REFERENCES artifactmetadata(id) ); python import requests import os from dotenv import loaddotenv loaddotenv() def fetchartifacts(numpages=5): """Fetch artifacts from Harvard Art Museums API with pagination""" apikey = os.getenv('HARVARDAPIKEY') baseurl = 'https://api.harvardartmuseums.org/object' allartifacts = [] for page in range(1, numpages + 1): params = { 'apikey': apikey, 'size': 100, # Max results per page 'page': page, 'hasimage': 1 # Only artifacts with images } response = requests.get(baseurl, params=params) if response.statuscode == 200: data = response.json() allartifacts.extend(data.get('records', [])) else: print(f"Error fetching page {page}: {response.statuscode}") break return allartifacts python impo …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/harvard-artifacts-collection-analytics