analyze

Analyze data questions with SQL or natural-language prompts and present validated results.

704|58|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/openyak/desktop --skill analyze-openyak
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: analyze
Source: https://github.com/openyak/desktop/tree/main/backend/app/data/plugins/data/skills/analyze
Command: npx skills add https://github.com/openyak/desktop --skill analyze-openyak

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyze data questions by providing direct answers and insights from datasets.

Core Features & Use Cases

  • Quick lookups for single metrics
  • Multi-dimensional analyses (trend, comparison, segmentation)
  • Formal reporting with methodology and caveats

Quick Start

Ask a data question in natural language to receive a concise analysis and answer.

Frequently Asked Questions about analyze

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

FAQPage Schema
How do I get answers to data questions from my warehouse using natural language?

To answer data questions using natural language, submit prompts directly to your connected data sources. The system translates queries to validate results and presents concise outputs with caveats for quick lookups or trend investigations.

Can I run time-series and segment comparisons without writing SQL?

Yes, you can perform time-series analysis and segment comparisons without manual SQL by submitting natural-language prompts. The system processes multi-dimensional analyses across connected data sources and returns validated insights directly.

What is the best way to generate formal reporting with methodology from datasets?

The best way to generate formal reporting from datasets is to request multi-dimensional analyses directly. The system produces formal reports that include methodology and caveats alongside the direct answers to ensure data validation.

Do I need a data warehouse to analyze metrics and trends?

Yes, you need access to a data warehouse or sample data inputs to analyze metrics and trends. The system requires connected data sources to validate results and provide direct answers for your data exploration.

Does this approach work for quick single metric lookups as well as deep exploration?

Yes, this approach works for both quick single metric lookups and deep data exploration. It applies natural-language or SQL prompts to validate results across connected sources and presents outputs with appropriate caveats.