analyze-data

Guide DuckDB SQL analysis of uploaded tabular datasets.

1|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/cyyeh/duckdb-data-agent --skill analyze-data-cyyeh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: analyze-data
Source: https://github.com/cyyeh/duckdb-data-agent/tree/main/skills/analyze-data
Command: npx skills add https://github.com/cyyeh/duckdb-data-agent --skill analyze-data-cyyeh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Helps users quickly analyze, profile, and summarize uploaded tabular datasets by guiding SQL-based exploration, detecting data quality issues, and recommending visualizations so non-expert users can get actionable insights without crafting complex queries from scratch.

Core Features & Use Cases

  • Guided data profiling: Lists tables, inspects schemas, reports row counts, samples rows, and computes null rates to surface data quality issues.
  • Flexible analysis patterns: Supports aggregation, trend analysis, comparisons, distributions, and Top-N ranking using DuckDB SQL constructs and window functions.
  • Visualization guidance: Recommends chart types and produces inline charts for categories, time series, distributions, and bivariate relationships.
  • Use case: Quickly profile a newly uploaded CSV or Parquet dataset, identify missing-value hotspots, compute key aggregates, and generate a monthly revenue trend chart.

Quick Start

Ask the agent to profile the dataset, show schema and sample rows for sales.csv, and produce a monthly revenue line chart.

Frequently Asked Questions about analyze-data

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

FAQPage Schema
How do I profile a CSV file to check data quality and find missing values?

Data profiling a CSV file inspects schemas, samples rows, and computes null rates to surface data quality issues. This Skill uses DuckDB to automatically guide SQL-based exploration on uploaded CSV files, reporting missing-value hotspots without requiring you to write complex queries.

Can I analyze Parquet and Excel files with DuckDB SQL?

Yes, you can analyze Parquet, Excel, JSON, and CSV tables with DuckDB SQL. The Skill loads these tabular datasets into isolated DuckDB sessions, allowing you to execute targeted SQL queries for aggregation, trend detection, and comparisons across all supported formats.

What is the best way to visualize time series data from a large dataset?

The best way to visualize time series data is by executing DuckDB SQL to aggregate the large dataset and rendering inline charts. This Skill samples large tables when needed and recommends appropriate chart types to produce visualizations like monthly revenue trends.

How do I generate aggregations and Top-N rankings from JSON data?

Generating aggregations and Top-N rankings from JSON data uses DuckDB SQL constructs and window functions. The Skill guides structured data analysis on uploaded JSON tables, executing targeted SQL queries to compute distributions, rankings, and key aggregates automatically.

Do I need to write SQL queries from scratch to get insights from tabular data?

No, you do not need to write SQL queries from scratch to get insights from tabular data. The Skill guides structured data analysis for non-expert users, automatically applying schema inspection, aggregation patterns, and visualization recommendations to deliver actionable insights.