skills.rest
miptah21
miptah21COMMUNITY
Explore all skills by this author →
GitHub

analyzing-data

Discover warehouse tables, execute SQL, and return Polars or Pandas dataframes.

2|Updated Apr 8, 2026
Search Tags:#caching#metrics#business intelligence#polars#data discovery#warehouse#sql analysis
One-click install
npx skills add https://github.com/miptah21/skills --skill analyzing-data-miptah21
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: analyzing-data
Source: https://github.com/miptah21/skills/tree/main/.agents/skills/analyzing-data
Command: npx skills add https://github.com/miptah21/skills --skill analyzing-data-miptah21

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires click, jupyter-client, ipykernel, pyyaml, python-dotenv, cryptography, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill helps you answer business questions by automatically querying your data warehouse instead of manually hunting for the right tables and writing one-off SQL.

Core Features & Use Cases

  • Pattern lookup for common question types: Reuses a cached query strategy to speed up repeat analyses (e.g., “how many customers…”, “top N…”, “find customers…”).
  • Concept-to-table discovery: Maps business concepts to specific warehouse tables using a persistent cache to reduce repeated discovery work.
  • Warehouse execution with guarded workflow: Runs discovery, executes SQL via a persistent Python kernel, caches learnings before presenting results, and returns results as Polars or Pandas dataframes.

Use case: A product manager asks “Who uses Feature X?” and the skill identifies the relevant tables (via cached concept mappings or SQL discovery), executes the correct query, and returns the matching users/customers plus supporting metrics.

Quick Start

Ask your agent to run the skill and execute a warehouse query for your question, for example: “Query the warehouse to show the number of active customers in the last 30 days and summarize the trend week-by-week.”

Frequently Asked Questions about analyzing-data

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I answer business questions by querying warehouse data without writing SQL manually?▼

To answer business questions from warehouse data, you can use an automated analytics skill to discover relevant tables, execute SQL queries, and return results as Polars or Pandas dataframes. It maps business concepts to tables and caches query patterns to speed up repeat analysis.

Can I return warehouse query results as Polars dataframes instead of Pandas?▼

Yes, warehouse query results can be returned as Polars dataframes. The skill executes SQL via a persistent Python kernel and supports returning dataframe objects in both Polars and Pandas formats for your business intelligence analysis.

What's the best way to find which warehouse tables contain specific business metrics?▼

The best way to find relevant warehouse tables is through concept-to-table discovery. This maps business concepts to specific tables using a persistent cache, reducing repeated discovery work when running metrics reporting or SQL analysis.

Does this approach cache table schemas and query patterns for repeated SQL analysis?▼

Yes, it caches table schemas and query patterns. It uses a persistent cache to store concept mappings and query strategies, satisfying persistent caching requirements to speed up repeat analyses like trend reporting and customer lookups.

How do I report week-by-week metrics trends from my data warehouse?▼

To report metrics trends, ask your agent to execute a warehouse query for your specific question. The skill discovers relevant tables, runs the SQL analysis via a persistent kernel, and returns the trend data as a dataframe for reporting.

Do I need a Python kernel to run SQL analysis on my warehouse data?▼

Yes, you need a Python kernel to execute SQL analysis. The skill uses a start/exec kernel workflow to run discovery, execute queries on your warehouse data, cache learnings, and return the results as dataframes.

Related Skills

Explore More Data & Analytics Skills→
marcosgomeseburymarcosgomesebury

mysql_connect

Validate MySQL database connectivity using environment-provided credentials.

Community
Intermediate
astronomerastronomer
419

analyzing-data

Query data warehouses with SQL and return Polars/Pandas dataframes.

Official
Advanced
minyeamerminyeamer
3

analyzing-data

Execute SQL queries against a data warehouse using a persistent Jupyter kernel.

Community
Intermediate
JingyiWngJingyiWng

databricks-metric-views

Define, create, and query governed business metric views in Unity Catalog.

Community
Intermediate