Skip to main content
affpapa.org
RU EN
skill CX Codex

harvard-art-museums-etl-analytics — Claude Code skill: ETL

This skill pulls Harvard Art Museums records through the API, stores structured data in SQL, and supports Streamlit dashboards for collection analysis.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add reason-machines/data-skills --skill harvard-art-museums-etl-analytics -a claude-code
Open on GitHub

What harvard-art-museums-etl-analytics does

The skill lays out a data flow from the Harvard Art Museums API through extraction, transformation, SQL storage, analysis, and visualization. It handles paged requests with rate limiting, separates object metadata from media and color records, and uses relational tables for storage. A set of 20+ SQL queries supports analysis, while Streamlit and Plotly present the results.

The project uses Python with requests, pandas, mysql-connector-python, Streamlit, Plotly, and python-dotenv. Configuration belongs in .env, including HARVARD_API_KEY plus MySQL or TiDB Cloud connection values: DB_HOST, DB_PORT, DB_USER, DB_PASSWORD, and DB_NAME. Data extraction cannot start without HARVARD_API_KEY.

What it helps with

  • pull Harvard Art Museums objects through the API
  • split raw records into metadata, media, and color data
  • store collection records in a relational MySQL schema
  • run predefined SQL analysis on museum objects
  • display query results in a Streamlit dashboard

Example prompts for the agent

  • Create a paginated ETL flow for Harvard Art Museums objects and load the results into MySQL.
  • Turn the collection response into metadata, media, and color tables, then add SQL analysis.
  • Build a Streamlit and Plotly view for the museum-object query results.

How to install harvard-art-museums-etl-analytics

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill harvard-art-museums-etl-analytics -a claude-code

2Manually: put the files in place

~/.claude/skills/harvard-art-museums-etl-analytics/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/harvard-art-museums-etl-analytics/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about harvard-art-museums-etl-analytics

How do I install harvard-art-museums-etl-analytics in Claude Code?

Run npx skills add reason-machines/data-skills --skill harvard-art-museums-etl-analytics -a claude-code, then check ~/.claude/skills/harvard-art-museums-etl-analytics/SKILL.md.

What does harvard-art-museums-etl-analytics do?

It guides an agent through collecting Harvard Art Museums API data, reshaping it for SQL storage, querying the collection, and presenting results with Streamlit and Plotly.

What configuration does the skill require?

Set HARVARD_API_KEY and the MySQL or TiDB Cloud values DB_HOST, DB_PORT, DB_USER, DB_PASSWORD, and DB_NAME in .env. The project also installs the Python dependencies from requirements.txt.

Similar skills

All skills for Data and databases →
indicator-setup marketcalls Creates a venv, installs the libraries OpenAlgo indicator scripts rely on, and prepares project folders plus a .env with your API key. CX Codex +1 551installs indicator-dashboard marketcalls Creates technical analysis dashboards with Plotly Dash or Streamlit. Generates live multi-timeframe charts and market scanners. CX Codex +1 570installs mysql sanjay3290 This skill runs SELECT queries against several MySQL databases and blocks every write. Handy when you want to inspect a schema or pull data without touching production. CX Codex +1 420installs etl-connector-strategy Samuel Berthe Walks a SaaS vendor through whether, where and how to appear as a source in customers' ETL/ELT pipelines, and what that costs to maintain. CX Codex +1 8,000installs business-analytics-reporter ailabs-393 Reads a CSV of sales and revenue, finds weak spots and suggests improvement strategies. Useful when you need a business performance report without manual math. CX Codex +1 2,200installs sql-pro https://github.com/Jeffallan Optimizes slow SQL queries, designs database schemas, and fixes performance bottlenecks. Built for EXPLAIN plan tuning and cross-dialect migrations. CX Codex +1 6,400installs

From the same set74

harvard-art-museum-data-pipeline Guides data pipeline setup for the Harvard Art Museums API. It normalizes artifact records into MySQL and renders a Streamlit dashboard. CX Codex +1 2,000installs harvard-artifacts-data-engineering-analytics Builds an ETL workflow for Harvard Art Museums records and a Streamlit analytics dashboard. It fits projects that combine the museum API, Python, and SQL. CX Codex +1 2,000installs harvard-artifacts-data-engineering-pipeline Pulls artifact records from the Harvard Art Museums API, loads them into SQL tables, and renders a Streamlit dashboard on top. CX Codex +1 2,000installs harvard-art-museum-etl-analytics Sets up an ETL workflow for the Harvard Art Museums API, organizes museum items into MySQL tables, and renders Streamlit visualizations. CX Codex +1 2,000installs harvard-artifacts-etl-analytics A skill that walks your agent through building an ETL pipeline and an analytics dashboard on Harvard Art Museums API data. Useful when you want a set route from API calls to Streamlit charts. CX Codex +1 2,000installs realtime-cinema-data-engineering-pipeline Instructions for assembling a streaming pipeline that routes simulated ticket transactions through message queues and warehouse layers. CX Codex +1 2,000installs harvard-art-museums-data-pipeline Builds a museum-artifact data flow from the Harvard API to SQL analysis and a Streamlit dashboard. Useful for collection data projects. CX Codex +1 2,000installs amee-joshi-data-engineering-portfolio A reference skill with Azure data engineering examples: Bronze–Silver–Gold layers, Delta Lake, dimensional models and pipeline designs. CX Codex +1 2,000installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor