skills.rest
minyeamer
minyeamerCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

analyzing-data

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

3|Updated Jul 22, 2025
Search Tags:#data analysis#concept mapping#business metrics#sql queries#warehouse discovery#pattern caching#polars pandas
One-click install
npx skills add https://github.com/minyeamer/linkmerce --skill analyzing-data-minyeamer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: analyzing-data
Source: https://github.com/minyeamer/linkmerce/tree/main/.agents/skills/analyzing-data
Command: npx skills add https://github.com/minyeamer/linkmerce --skill analyzing-data-minyeamer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires click, jupyter-client, ipykernel, pyyaml, python-dotenv, cryptography, snowflake-connector-python[pandas], psycopg[binary,pool], google-cloud-bigquery[pandas,pyarrow], db-dtypes, sqlalchemy, duckdb, duckdb-engine, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you answer business questions by querying your data warehouse instead of manually guessing tables, writing ad-hoc SQL, or repeatedly re-discovering schemas.

Core Features & Use Cases

  • Pattern lookup + learning: Reuses cached query strategies for common question types (e.g., counts, trends, top-N) and learns new strategies when caches miss.
  • Concept-to-table discovery: Maps business concepts (like “customers”) to concrete warehouse tables, with caching to reduce future discovery time.
  • Warehouse exploration and SQL execution: Discovers relevant tables (including via INFORMATION_SCHEMA) and executes queries in a persistent kernel using run_sql / run_sql_pandas.
  • Schema caching: Stores table schemas to speed up repeated query authoring and validation.

Quick Start

Ask the skill to execute a direct SQL analysis question by running: uv run scripts/cli.py exec "df = run_sql('SELECT ...')"

Frequently Asked Questions about analyzing-data

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

FAQPage Schema
How do I query my data warehouse to answer a business question without manually finding tables?▼

You can query a data warehouse by asking a natural business question; the tool maps concepts to tables, executes SQL via a persistent Jupyter kernel, and returns results. It caches table schemas and query strategies to speed up future discovery and execution.

Can I use Polars or Pandas to process warehouse query results directly?▼

Yes, the tool provides dedicated result helpers for both Polars and Pandas. You can execute SQL using the `run_sql` or `run_sql_pandas` functions to load warehouse data directly into dataframes for immediate processing and analysis.

Does this support querying Snowflake, BigQuery, and Postgres warehouses?▼

Yes, it supports querying Snowflake, BigQuery, and Postgres data warehouses. Dependencies include snowflake-connector-python, google-cloud-bigquery, and psycopg, allowing you to connect and execute SQL across these platforms.

What's the best way to discover relevant tables before writing complex SQL?▼

The best way is using safety-oriented discovery steps via INFORMATION_SCHEMA or SQL file search. The tool automatically discovers relevant tables and caches concept-to-table mappings, reducing manual schema exploration before heavy aggregation.

How does the tool handle repeated queries for common metrics like trends or top-N counts?▼

It uses pattern matching to reuse cached query strategies for common metrics like trends and counts. When a cache miss occurs, the tool learns and records new query strategies for future use, optimizing repeated warehouse data analysis.

Related Skills

Explore More Data & Analytics Skills→
0xHoneyJar0xHoneyJar
1

loa-credentials

Manage API credentials across environment variables, encrypted stores, and dotenv files.

Official
Intermediate
silvainfmsilvainfm
2

duckdb

Run SQL analytics directly on CSV, Parquet, and JSON files and Pandas or Polars DataFrames.

Community
Advanced
clawdataclawdata
24

duckdb

Query local DuckDB warehouses with SQL and ingest CSV, Parquet, and JSON files.

Official
Intermediate
trmaphitrmaphi

datafusion-cli

Query Parquet, Arrow, IPC, and AVRO files with SQL via DataFusion CLI.

Community
Intermediate