harvard-art-museum-data-pipeline — Claude Code skill
Guides data pipeline setup for the Harvard Art Museums API. It normalizes artifact records into MySQL and renders a Streamlit dashboard.
npx skills add reason-machines/data-skills --skill harvard-art-museum-data-pipeline -a claude-codeWhat harvard-art-museum-data-pipeline does
This skill guides the creation of an ingestion pipeline for artifact catalogs. Python scripts fetch museum records in batches while respecting request limits. Incoming nested payloads get parsed into three structured tables: artifactmetadata, artifactmedia, and artifactcolors.
Data lands in MySQL or a managed TiDB Cloud instance using bulk inserts. The setup includes over 20 prewritten analytical queries and a Streamlit interface powered by Plotly charts. You get a fully functional data workflow template.
The pipeline immediately fails without a Harvard API token and an active database target. You will need Python 3.8+, packages like pandas and mysql-connector-python, plus credentials saved in environment variables.
What it helps with
- ingest artifact records from the Harvard Art Museums API with pagination
- structure relational database tables for museum metadata, media, and colors
- load normalized dataframes into MySQL or TiDB Cloud
- build an interactive analytics interface using Streamlit and Plotly
Example prompts for the agent
- Set up a Python ETL script to extract object records from the Harvard Art Museums API
- Design the SQL schema for artifactmetadata and artifactmedia tables in MySQL
- Create a Streamlit and Plotly dashboard to explore museum artifact colors
How to install harvard-art-museum-data-pipeline
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museum-data-pipeline -a claude-code2Manually: put the files in place
~/.claude/skills/harvard-art-museum-data-pipeline/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/harvard-art-museum-data-pipeline/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museum-data-pipeline -a codex2Manually: put the files in place
.agents/skills/harvard-art-museum-data-pipeline/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museum-data-pipeline -a cursor2Manually: put the files in place
.cursor/skills/harvard-art-museum-data-pipeline/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/data-skills harvard-art-museum-data-pipeline2Manually: put the files in place
.github/skills/harvard-art-museum-data-pipeline/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museum-data-pipeline -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/data-skills --path skills/harvard-art-museum-data-pipelineManually: put the files in place
.devin/skills/harvard-art-museum-data-pipeline/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museum-data-pipeline -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about harvard-art-museum-data-pipeline
How do I install harvard-art-museum-data-pipeline in Claude Code?
Run npx skills add reason-machines/data-skills --skill harvard-art-museum-data-pipeline -a claude-code in your terminal.
What does harvard-art-museum-data-pipeline do?
It instructs the agent on assembling an ETL pipeline: pulling museum API data, structuring it into relational tables, and rendering dashboard charts.
What credentials are required to run this pipeline?
You need a Harvard Art Museums API key alongside connection details for MySQL or TiDB Cloud. These pass via HARVARD_API_KEY, DB_HOST, DB_USER, and DB_PASSWORD variables.
