Skip to main content
affpapa.org
RU EN
skill CX Codex

harvard-artifacts-etl-pipeline — Claude Code skill: ETL and dashboards

A skill that walks your coding agent through an ETL pipeline from the Harvard Art Museums API to Streamlit charts.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add reason-machines/data-skills --skill harvard-artifacts-etl-pipeline -a claude-code
Open on GitHub

What harvard-artifacts-etl-pipeline does

The skill covers the whole path: paged requests to the Harvard Art Museums API, flattening nested JSON into tables, loading into MySQL or TiDB Cloud, analytical SQL, and Plotly charts in Streamlit. Your agent gets working code templates for each stage.

Inside are Python examples. fetch_artifacts pulls pages of 100 records and stops once the pages run out; extract_metadata, extract_media and extract_colors split the API response into three tables. The schema ships too: artifactmetadata, artifactmedia and artifactcolors, joined by artifact_id.

You need a HARVARD_API_KEY and a database — host, port, user and password go into .env. Without the API key every request fails, so check that first. Dependencies come from requirements.txt: streamlit, pandas, requests, mysql-connector-python, plotly, python-dotenv.

What it helps with

  • pull museum objects from the Harvard Art Museums API page by page
  • turn nested museum JSON into relational tables
  • load artifact metadata and colors into MySQL or TiDB Cloud
  • write SQL queries over the collection and its media
  • build an interactive Streamlit dashboard with Plotly charts

Example prompts for the agent

  • Help me write an ETL pipeline that fetches objects from the Harvard Art Museums API and splits them into tables
  • Write SQL queries against the artifactmetadata table and chart the results with Plotly in Streamlit
  • Set up paged fetching from the Harvard API and load the data into TiDB Cloud

How to install harvard-artifacts-etl-pipeline

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill harvard-artifacts-etl-pipeline -a claude-code

2Manually: put the files in place

~/.claude/skills/harvard-artifacts-etl-pipeline/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/harvard-artifacts-etl-pipeline/

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

Questions about harvard-artifacts-etl-pipeline

How do I install harvard-artifacts-etl-pipeline in Claude?

Run npx skills add reason-machines/data-skills --skill harvard-artifacts-etl-pipeline -a claude-code. The skill lands in ~/.claude/skills/harvard-artifacts-etl-pipeline/SKILL.md.

What does harvard-artifacts-etl-pipeline do?

It helps your agent build ETL pipelines and analytics dashboards on Harvard Art Museums API data: fetching, reshaping JSON into SQL tables, querying, and visualizing in Streamlit.

What do I need before running the pipeline?

A HARVARD_API_KEY and access to a MySQL or TiDB Cloud database. The API key and database credentials live in a .env file.

Similar skills

All skills for Data and databases →
ETL Pipeline Claude Office Skills A skill for designing and automating ETL pipelines: pull from databases and APIs, transform, load into warehouses. Useful when you need a recurring data flow. CX Codex +1 4,800installs etl-connector-strategy Samuel Berthe Walks a SaaS vendor through whether, where and how to appear as a source in customers' ETL/ELT pipelines, and what that costs to maintain. CX Codex +1 8,000installs pyspark-etl-best-practices-cursorrules-prompt-file PatrickJS A Cursor rule that sets PySpark code style: F.col(), explicit joins, select over withColumn, and Iceberg-aware ETL structure. ★ 41,011repo stars data-pipeline claude-office-skills A skill for building ETL pipelines: extract from APIs and databases, transform, then load into warehouses and sheets. Useful when data from several sources has to land in one place on a schedule. CX Codex +1 4,900installs checking-freshness astronomer The skill checks when a table was last updated and tells you whether the data is safe to use. CX Codex +1 1,000installs streamlit-to-marimo marimo-team Turns a Streamlit app into a marimo notebook: maps the widgets, state and caching, writes a new file and checks it. CX Codex +1 2,300installs

From the same set22

harvard-artifacts-collection-analytics-pipeline A skill that walks your agent through a full Harvard Art Museums API pipeline: ETL, SQL storage and a Streamlit dashboard. CX Codex +1 1,900installs iac-terraform-data-engineering A skill for Claude and other AI agents that helps describe AWS data infrastructure in Terraform: S3 buckets, EC2 instances, IAM roles. CX Codex +1 1,800installs iac-data-engineering-terraform A skill with ready Terraform patterns for data engineering: S3 buckets, EC2 instances and IAM roles. Useful when you need to stand up pipeline infrastructure declaratively. CX Codex +1 1,800installs terraform-data-engineering-infrastructure A skill with Terraform patterns for data engineering: S3 data lake buckets, EC2 processing nodes, IAM roles. Useful when AWS infrastructure has to be described in code, not clicked together. CX Codex +1 1,800installs data-analytics-skills-claude A collection of analytics skills for checking data, investigating metrics, and shaping dashboard specs. Use it when an analysis needs a clear workflow and shareable results. CX Codex +1 1,300installs harvard-art-museum-data-engineering A skill that builds an ETL pipeline for the Harvard Art Museums API: pull artifacts, shape them into tables, load into SQL, and chart them in Streamlit. CX Codex +1 1,300installs harvard-art-museums-data-engineering A skill for building ETL pipelines on Harvard Art Museums API data: normalise into MySQL, run SQL analytics, ship a Streamlit dashboard. CX Codex +1 843installs bigquery-agent-analytics-sdk A skill for analyzing AI agent telemetry in BigQuery: trace reconstruction, LLM-as-Judge evaluation, and drift detection. CX Codex +1 768installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor