skill CX Codex

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

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

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

Q: What does the setup require?

Install the Python packages from `requirements.txt`, provide `HARVARD_API_KEY`, and set `DB_HOST`, `DB_USER`, `DB_PASSWORD`, and `DB_NAME`. The database target is MySQL or TiDB Cloud.

Builds an ETL workflow for Harvard Art Museums records and a Streamlit analytics dashboard. It fits projects that combine the museum API, Python, and SQL.

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

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

Open on GitHub

What harvard-artifacts-data-engineering-analytics does

This skill guides an end-to-end workflow for Harvard Art Museums data. It fetches paginated API results, reshapes nested records into separate metadata, media, and color datasets, then inserts them into MySQL or TiDB Cloud.

The analytics side uses SQL queries and a Streamlit interface with Plotly charts. The project expects Python packages from requirements.txt, the HARVARD_API_KEY variable, and database settings such as DB_HOST, DB_USER, DB_PASSWORD, and DB_NAME. Without the API key and database connection values, the pipeline cannot fetch and persist the collection data.

What it helps with

build an ETL workflow for museum records
turn nested API data into SQL tables
load metadata, media, and color records into MySQL
create a Streamlit view for collection analytics
run predefined SQL analysis on artifact data

Example prompts for the agent

Build a Python and SQL ETL workflow for Harvard Art Museums records.
Split the API response into metadata, media, and color tables, then load them into MySQL.
Create a Streamlit dashboard with Plotly charts for the museum collection.

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

1Skills CLI (Vercel)

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

2Manually: put the files in place

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

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

1Skills CLI (Vercel)

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

2Manually: put the files in place

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

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

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

2Manually: put the files in place

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

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

1GitHub CLI

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

2Manually: put the files in place

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

1Skills CLI (Vercel)

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

2Platform CLI

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

Manually: put the files in place

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

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill harvard-artifacts-data-engineering-analytics -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-analytics

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

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

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

It fetches Harvard Art Museums API records, converts them into related SQL tables, loads the data into a database, and supports a Streamlit dashboard with Plotly charts.

What does the setup require?

Install the Python packages from requirements.txt, provide HARVARD_API_KEY, and set DB_HOST, DB_USER, DB_PASSWORD, and DB_NAME. The database target is MySQL or TiDB Cloud.

Similar skills

All skills for Data and databases →

geo-data-engineering Muhammed Enes Duran Keeps an agent on track when spatial data has to be fetched, cleaned or pushed through a pipeline that has to run again next month. CX Codex +1 ★ 35repo stars using-dbt-for-analytics-engineering dbt-labs A skill that walks the agent through dbt work: building models, writing SQL with ref() and source(), adding tests, validating output with dbt show. CX Codex +1 1,200installs data-engineering Seth Hobson A plugin for Claude, Claude and Cursor that helps build ETL pipelines, design data warehouses and write batch processing jobs. CX Codex ★ 41,823repo stars aws-data-analytics Amazon Web Services An AWS plugin that gives Claude skills for data lakes, catalogs and ETL work on Amazon services. ★ 3,299repo stars google-analytics-data-api-basics official google This skill works with Google Analytics reporting data through Data API v1beta. Use it to enable the API, query metrics and dimensions, or check API access. CX Codex 7,364installs data-analytics official Data Analytics Maintainers Analyze product and business metrics, check data quality, and turn findings into reports, charts, or dashboards. Useful when a decision needs evidence from data. CX Codex GP ChatGPT ★ 7,604repo stars

From the same set74

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-app 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. CX Codex +1 2,000installs harvard-art-museum-data-pipeline Guides data pipeline setup for the Harvard Art Museums API. It normalizes artifact records into MySQL and renders a Streamlit dashboard. CX Codex +1 2,000installs 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-art-museum-etl-analytics Sets up an ETL workflow for the Harvard Art Museums API, organizes museum items into MySQL tables, and renders Streamlit visualizations. CX Codex +1 2,000installs harvard-art-museums-etl-analytics This skill pulls Harvard Art Museums records through the API, stores structured data in SQL, and supports Streamlit dashboards for collection analysis. 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