harvard-artifacts-etl-streamlit-analytics — Claude Code skill

What harvard-artifacts-etl-streamlit-analytics does

This skill covers the full loop for working with the Harvard Art Museums collection. The agent fetches objects from the API page by page, reshapes the response into three tables and loads them into a relational database. Metadata, media and colour data each get their own table, and the skill ships the CREATE TABLE statements so the schema does not have to be invented.

Python code inside handles the requests, turns the payload into pandas dataframes and connects to MySQL or TiDB Cloud through mysql-connector-python. A separate layer holds analytical SQL: culture, century, whether images exist, colour patterns. Streamlit renders the query output with Plotly charts.

You need a Harvard Art Museums API key and a reachable database before anything runs. Credentials come from environment variables: HARVARD_API_KEY, DB_HOST, DB_USER, DB_PASSWORD, DB_NAME. No key means the API calls fail; no connection means there is nowhere to load the tables. The fetch loop pauses between pages because the API caps how many requests you get per day.