# 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.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2000 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-art-museums-data-pipeline/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/harvard-art-museums-data-pipeline

## What it 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.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/data-skills harvard-art-museums-data-pipeline
```

2. **Manually: put the files in place**
- File: `.github/skills/harvard-art-museums-data-pipeline/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/data-skills --path skills/harvard-art-museums-data-pipeline
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill harvard-art-museums-data-pipeline -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-art-museums-data-pipeline/SKILL.md

## When to use it
- 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
- 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.

## Similar
- [data-pipeline](https://affpapa.org/en/nevibecode/skills/data-pipeline.md) — skill · 4900 installs
- [Data Cleaning Pipeline](https://affpapa.org/en/nevibecode/skills/data-cleaning-pipeline.md) — skill · 589 installs
- [ETL Pipeline](https://affpapa.org/en/nevibecode/skills/etl-pipeline.md) — skill · 4800 installs
- [geospatial-data-pipeline](https://affpapa.org/en/nevibecode/skills/geospatial-data-pipeline.md) — skill · 345 installs
- [ingesting-into-data-lake](https://affpapa.org/en/nevibecode/skills/ingesting-into-data-lake.md) — skill · 6600 installs
- [databricks-apps-python](https://affpapa.org/en/nevibecode/skills/databricks-apps-python.md) — skill · 305 installs

From the same set: [reason-machines/data-skills](https://affpapa.org/en/nevibecode/by/reason-machines/data-skills.md) — 74 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