# harvard-artifacts-collection-data-engineering

This skill pulls Harvard Art Museums data into MySQL and renders it in Streamlit. Useful when you want a working ETL example from API to dashboard.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1900 installs · ★ 5
- Author: reason-machines
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/data-skills/tree/HEAD/skills/harvard-artifacts-collection-data-engineering/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/harvard-artifacts-collection-data-engineering

## What it does

The skill covers a full application: a client for the Harvard Art Museums API with pagination, an ETL pipeline, a relational schema and interactive dashboards. The flow is API → ETL → SQL → analytics → visualization.

Three tables hold the data — `artifactmetadata`, `artifactmedia` and `artifactcolors`. Media and colors come out of nested JSON as separate rows and link back to the artifact by foreign key. Analytics is a set of ready-made SQL queries, and charts run on Plotly inside Streamlit.

You need a `HARVARD_API_KEY` and a reachable MySQL instance: host, port, user, password and database name all come from environment variables. Dependencies install from `requirements.txt` — `streamlit`, `pandas`, `requests`, `mysql-connector-python` and `plotly`. There are no migrations, so create the tables yourself before the first pipeline run; otherwise the load step has nowhere to write.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-artifacts-collection-data-engineering -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/harvard-artifacts-collection-data-engineering/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/harvard-artifacts-collection-data-engineering/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-artifacts-collection-data-engineering -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/harvard-artifacts-collection-data-engineering/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-artifacts-collection-data-engineering -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/harvard-artifacts-collection-data-engineering/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/data-skills harvard-artifacts-collection-data-engineering
```

2. **Manually: put the files in place**
- File: `.github/skills/harvard-artifacts-collection-data-engineering/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-artifacts-collection-data-engineering -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/data-skills --path skills/harvard-artifacts-collection-data-engineering
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/harvard-artifacts-collection-data-engineering/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-artifacts-collection-data-engineering -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/data-skills/tree/HEAD/skills/harvard-artifacts-collection-data-engineering/SKILL.md

## When to use it
- pull a museum collection from the API page by page
- flatten nested JSON into relational tables
- link artifacts to their images and colors
- run analytical queries over collection metadata
- build an interactive Streamlit dashboard

## Example prompts
- build an ETL pipeline for Harvard Art Museums artifact data
- set up batch loading from the Harvard API into MySQL
- create a Streamlit dashboard over the artifactmetadata table

## Similar
- [data-engineering](https://affpapa.org/en/nevibecode/plugins/data-engineering.md) — plugin · ★ 41729
- [context-engineering-collection](https://affpapa.org/en/nevibecode/skills/context-engineering-collection.md) — skill · 4200 installs
- [sql-pro](https://affpapa.org/en/nevibecode/skills/httpsgithubcomjeffallan-sql-pro.md) — skill · 6400 installs
- [database-optimizer](https://affpapa.org/en/nevibecode/skills/httpsgithubcomjeffallan-database-optimizer.md) — skill · 6000 installs
- [mysql-patterns](https://affpapa.org/en/nevibecode/skills/mysql-patterns.md) — skill · 4700 installs
- [sql-queries](https://affpapa.org/en/nevibecode/skills/phuryn-sql-queries.md) — skill · 2800 installs

From the same set: [reason-machines/data-skills](https://affpapa.org/en/nevibecode/by/reason-machines/data-skills.md) — 31 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md