harvard-art-museums-data-pipeline — Claude Code skill: ETL
Builds a museum-artifact data flow from the Harvard API to SQL analysis and a Streamlit dashboard. Useful for collection data projects.
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a claude-codeWhat harvard-art-museums-data-pipeline does
This skill covers a data path from Harvard Art Museums API requests to an interactive view. It handles paged collection retrieval with rate limiting, reshapes nested JSON into relational tables, loads records into MySQL or TiDB Cloud, runs SQL analysis, and presents results with Streamlit and Plotly.
The setup uses the packages listed in requirements.txt: streamlit, pandas, requests, mysql-connector-python, plotly, and python-dotenv. Configure a .env file with HARVARD_API_KEY plus the database connection values. Without HARVARD_API_KEY, artifact collection cannot start.
What it helps with
- collect museum artifacts through the Harvard API
- normalize nested API records for SQL storage
- load collection data into MySQL or TiDB Cloud
- create a Streamlit view with Plotly charts
Example prompts for the agent
- Build an ETL flow for Harvard Art Museums artifacts with pagination and MySQL loading.
- Turn the API responses into metadata, media, and color tables, then add SQL analysis.
- Create a Streamlit dashboard for the artifact collection with Plotly visualizations.
How to install harvard-art-museums-data-pipeline
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a claude-code2Manually: put the files in place
~/.claude/skills/harvard-art-museums-data-pipeline/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/harvard-art-museums-data-pipeline/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a codex2Manually: put the files in place
.agents/skills/harvard-art-museums-data-pipeline/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a cursor2Manually: put the files in place
.cursor/skills/harvard-art-museums-data-pipeline/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/data-skills harvard-art-museums-data-pipeline2Manually: put the files in place
.github/skills/harvard-art-museums-data-pipeline/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/data-skills --path skills/harvard-art-museums-data-pipelineManually: put the files in place
.devin/skills/harvard-art-museums-data-pipeline/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-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-museums-data-pipeline
How do I install harvard-art-museums-data-pipeline in Claude Code?
Run npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a claude-code. The skill file is placed at ~/.claude/skills/harvard-art-museums-data-pipeline/SKILL.md.
What does harvard-art-museums-data-pipeline do?
It guides artifact collection from the Harvard Art Museums API, reshapes the records for SQL, loads them into a database, and supports a Streamlit visualization.
What must be configured before using it?
Set a Harvard Art Museums API key, create .env, and provide DB_HOST, DB_PORT, DB_USER, DB_PASSWORD, and DB_NAME for the database connection.
