skill CX Codex

harvard-artifacts-data-engineering-app — Claude Code skill

Q: How do I install harvard-artifacts-data-engineering-app in Claude Code?

Run `npx skills add reason-machines/data-skills --skill harvard-artifacts-data-engineering-app -a claude-code`. The skill file lands at `~/.claude/skills/harvard-artifacts-data-engineering-app/SKILL.md`.

Q: What do I need before running it?

A `HARVARD_API_KEY` and a MySQL or TiDB database, because the app reads `DB_HOST`, `DB_USER`, `DB_PASSWORD` and `DB_NAME` from environment variables.

A skill that walks an agent through an ETL pipeline on Harvard Art Museums API data, SQL storage and a Streamlit dashboard with Plotly charts.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add reason-machines/data-skills --skill harvard-artifacts-data-engineering-app -a claude-code

Open on GitHub

What harvard-artifacts-data-engineering-app does

The skill covers the whole chain. It pulls museum objects from the Harvard Art Museums API page by page, unpacks the nested JSON, and spreads it across three tables: artifactmetadata, artifactmedia and artifactcolors. From there the rows go into MySQL or TiDB, and a Streamlit dashboard with Plotly charts sits on top.

You get working pieces to start from: a pymysql connection helper, table definitions with foreign keys, extract and transform functions, and inserts that refresh existing rows with ON DUPLICATE KEY UPDATE. For analysis there are more than 20 ready SQL queries over the collection.

Nothing runs without HARVARD_API_KEY and a reachable database, since the app reads DB_HOST, DB_USER, DB_PASSWORD and DB_NAME from the environment. The schema targets MySQL or TiDB — the upsert statements will not work on SQLite. Dependencies come from requirements.txt: streamlit, pandas, requests, pymysql, plotly and python-dotenv.

What it helps with

build an ETL pipeline from the Harvard Art Museums API into a relational database
flatten nested object JSON into normalized tables
stand up a dashboard with charts for a museum collection
run analytical SQL over artifact metadata and colors
load rows into MySQL or TiDB while updating existing records

Example prompts for the agent

Build the pipeline: fetch objects from the Harvard Art Museums API and load them into artifactmetadata, artifactmedia and artifactcolors.
Create a Streamlit dashboard with Plotly charts for artifact colors and techniques.
Write SQL queries to analyze the collection by culture and period.

How to install harvard-artifacts-data-engineering-app

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill harvard-artifacts-data-engineering-app -a claude-code

2Manually: put the files in place

~/.claude/skills/harvard-artifacts-data-engineering-app/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/harvard-artifacts-data-engineering-app/

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill harvard-artifacts-data-engineering-app -a codex

2Manually: put the files in place

.agents/skills/harvard-artifacts-data-engineering-app/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill harvard-artifacts-data-engineering-app -a cursor

2Manually: put the files in place

.cursor/skills/harvard-artifacts-data-engineering-app/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install reason-machines/data-skills harvard-artifacts-data-engineering-app

2Manually: put the files in place

.github/skills/harvard-artifacts-data-engineering-app/SKILL.md

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill harvard-artifacts-data-engineering-app -a gemini-cli

2Platform CLI

gemini skills install https://github.com/reason-machines/data-skills --path skills/harvard-artifacts-data-engineering-app

Manually: put the files in place

.devin/skills/harvard-artifacts-data-engineering-app/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill harvard-artifacts-data-engineering-app -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about harvard-artifacts-data-engineering-app

How do I install harvard-artifacts-data-engineering-app in Claude Code?

Run npx skills add reason-machines/data-skills --skill harvard-artifacts-data-engineering-app -a claude-code. The skill file lands at ~/.claude/skills/harvard-artifacts-data-engineering-app/SKILL.md.

What does harvard-artifacts-data-engineering-app do?

It guides an agent through fetching data from the Harvard Art Museums API, turning nested JSON into relational tables, loading MySQL or TiDB, and building a Streamlit dashboard with Plotly charts.

What do I need before running it?

A HARVARD_API_KEY and a MySQL or TiDB database, because the app reads DB_HOST, DB_USER, DB_PASSWORD and DB_NAME from environment variables.

Similar skills

All skills for Data and databases →

xlsx official anthropics Creates, reads, edits, and converts spreadsheet files. Use it when the requested deliverable is an Excel workbook or another tabular file. 187,223installs google-agents-cli-observability official Google This skill guides you through tracing and monitoring AI agents, including ADK agents. Use it when you need to inspect agent execution or monitor a deployed agent. CX Codex +1 511,300installs caveman-evidence-review JuliusBrussee A read-only skill reviews Caveman Cloud evidence on LLM spend, traces, and routing. Use it to see where a project’s model budget goes. CX Codex +1 104,500installs migration JuliusBrussee Enforces reversible, compatibility-safe transitions for schema, data, and API updates. Useful whenever data loss or rollout downtime is unacceptable. CX Codex +1 103,900installs performance-optimization addyosmani An agent skill that measures before it changes code: Core Web Vitals budgets, N+1 queries, missing indexes and slow endpoints. CX Codex +1 65,200installs supabase official supabase Guides the agent through database configuration and strict RLS policies in Supabase. CX Codex GP ChatGPT 8installs

From the same set31

mm2-analytics-roblox-toolkit A skill that lets your coding agent run the MM2 Analytics dashboard: track knife skins and gamepasses, review match stats, export reports. CX Codex +1 2,300installs mm2-analytics-dashboard-roblox A Murder Mystery 2 toolkit for Roblox: catalogues your inventory, tracks knife skins and gamepasses, and turns match stats into strategy advice. CX Codex +1 2,300installs employee-performance-analytics-hr This skill turns an employee CSV into department KPIs, per-person efficiency scores and charts. Useful when you need to read a workforce export without building pivot tables by hand. CX Codex +1 2,100installs llm-intelligent-public-opinion-analytics This skill sets up an LLM-powered opinion analytics assistant: it crawls hot lists, scores sentiment, clusters topics and sends alerts. CX Codex +1 2,100installs harvard-artifacts-data-engineering-pipeline Pulls artifact records from the Harvard Art Museums API, loads them into SQL tables, and renders a Streamlit dashboard on top. CX Codex +1 2,000installs harvard-artifacts-etl-analytics A skill that walks your agent through building an ETL pipeline and an analytics dashboard on Harvard Art Museums API data. Useful when you want a set route from API calls to Streamlit charts. CX Codex +1 2,000installs amee-joshi-data-engineering-portfolio A reference skill with Azure data engineering examples: Bronze–Silver–Gold layers, Delta Lake, dimensional models and pipeline designs. CX Codex +1 2,000installs data-engineering-study-material A study guide skill for data engineering: explains concepts, shows pipeline examples, and helps with interview prep. CX Codex +1 2,000installs