harvard-art-museums-data-engineering-analytics: Claude Code skill
Builds an ETL pipeline for the Harvard Art Museums collection and sets up interactive analytics. Uses Python, SQL databases, and Streamlit.
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-engineering-analytics -a claude-codeWhat harvard-art-museums-data-engineering-analytics does
This skill guides the assistant through extracting artifact records from the museum REST API. The workflow handles page iteration and respects rate limits during network calls. Incoming nested JSON payloads get separated into relational tables covering object details and media items using pandas.
Data gets cleaned by trimming text and dropping broken entries before insertion into MySQL or TiDB Cloud. On top of the database, it provides twenty analytical SQL queries paired with interactive Plotly visual charts inside a Streamlit web app.
Execution requires a registered HARVARD_API_KEY alongside database connection credentials. Without these environment variables, ingestion scripts cannot reach endpoints or store records.
What it helps with
- fetch museum artifacts with pagination from the Harvard API
- normalize nested JSON into tables for media and metadata
- ingest validated records into MySQL or TiDB Cloud schemas
- display collection insights using Plotly charts in Streamlit
Example prompts for the agent
- Build an ETL pipeline to pull artifact records from Harvard Art Museums into MySQL
- Parse nested image fields from museum JSON into pandas DataFrames
- Set up a Streamlit dashboard with Plotly charts for museum collection metrics
How to install harvard-art-museums-data-engineering-analytics
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-engineering-analytics -a claude-code2Manually: put the files in place
~/.claude/skills/harvard-art-museums-data-engineering-analytics/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/harvard-art-museums-data-engineering-analytics/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-engineering-analytics -a codex2Manually: put the files in place
.agents/skills/harvard-art-museums-data-engineering-analytics/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-engineering-analytics -a cursor2Manually: put the files in place
.cursor/skills/harvard-art-museums-data-engineering-analytics/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/data-skills harvard-art-museums-data-engineering-analytics2Manually: put the files in place
.github/skills/harvard-art-museums-data-engineering-analytics/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-engineering-analytics -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/data-skills --path skills/harvard-art-museums-data-engineering-analyticsManually: put the files in place
.devin/skills/harvard-art-museums-data-engineering-analytics/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-engineering-analytics -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-engineering-analytics
How to install harvard-art-museums-data-engineering-analytics in Claude Code?
Run npx skills add reason-machines/data-skills --skill harvard-art-museums-data-engineering-analytics -a claude-code.
What does this skill do?
It provides workflow patterns to extract museum data via REST API, transform nested records with pandas, load them into SQL, and present results in Streamlit.
What credentials and libraries are required?
You need a valid HARVARD_API_KEY, a reachable MySQL or TiDB instance, and Python packages including pandas, requests, streamlit, plotly, and mysql-connector-python.
