data-insights

Guide exploratory data analysis to derive actionable insights from datasets.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/pe-menezes/pmflow --skill data-insights-pe-menezes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-insights
Source: https://github.com/pe-menezes/pmflow/tree/main/skills/data-insights
Command: npx skills add https://github.com/pe-menezes/pmflow --skill data-insights-pe-menezes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps Product Managers transform raw data into clear, actionable insights, enabling data-driven decision-making and hypothesis validation.

Core Features & Use Cases

  • Data Question Formulation: Guides users to define specific, answerable questions from vague curiosities.
  • Data Loading & Cleaning: Supports various data sources (CSV, direct paste, database connections) and includes data quality checks.
  • Analysis & Interpretation: Performs exploratory data analysis, identifies trends, segments users, and flags common interpretation pitfalls like correlation vs. causation.
  • Use Case: A PM notices a drop in user retention and uses this skill to investigate, identify the drop-off point in the user funnel, and understand the contributing factors, leading to targeted product improvements.

Quick Start

Use the data-insights skill to analyze the attached CSV file and identify the key drivers of user churn.

Frequently Asked Questions about data-insights

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

FAQPage Schema
How do I investigate a drop in user retention using exploratory data analysis?

To investigate user retention drops, you formulate specific data questions, load and clean your dataset, perform segmented analysis to locate funnel drop-off points, and interpret trends to identify contributing factors for product improvements.

What is the best way to formulate answerable data questions from vague product management curiosities?

Formulating answerable data questions refines vague curiosities into specific, testable hypotheses, ensuring your exploratory data analysis focuses on deriving actionable product insights rather than executing aimless queries.

Can I load and clean data from a CSV file for metric investigation?

Yes, you can load and clean data from CSV files, direct paste, or database connections. The process includes data quality checks to prepare datasets for accurate metric investigation and segmented analysis.

Does this approach to data analysis flag correlation versus causation pitfalls during interpretation?

Yes, this data analysis approach explicitly flags common interpretation pitfalls like correlation versus causation, ensuring you accurately interpret exploratory results and derive genuinely actionable product insights.

How do I identify key drivers of user churn from a dataset?

Identifying key drivers of user churn requires loading your dataset, performing segmented analysis across user cohorts, interpreting trends, and validating hypotheses to pinpoint the specific behavioral or product factors causing retention loss.