data-analysis

Analyze datasets to extract insights and produce structured reports.

Updated Dec 20, 2023
One-click install
npx skills add https://github.com/Thiago-Cruz-eng/Hibrygame --skill data-analysis-thiago-cruz-eng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analysis
Source: https://github.com/Thiago-Cruz-eng/Hibrygame/tree/main/.claude/skills/data-analysis
Command: npx skills add https://github.com/Thiago-Cruz-eng/Hibrygame --skill data-analysis-thiago-cruz-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you turn messy or unfamiliar datasets into trustworthy insights without manually juggling calculations and charts.

Core Features & Use Cases

  • Data exploration & profiling: Quickly inspect schema, missing values, distributions, and summary statistics.
  • Cleaning & validation-ready preparation: Handle missing data, duplicates, type conversions, and outlier filtering on a copy of the data.
  • Statistical analysis & reporting: Compute descriptive stats, grouped aggregates, correlations, pivots, and trend metrics, then structure results into a readable report.
  • Visualization for decision-making: Generate histograms, boxplots, heatmaps, and time-series summaries to reveal patterns.

Quick Start

Use the data-analysis skill to analyze the file you provide, produce a structured findings report, and include a visualization plan based on the dataset’s columns and date fields.

Frequently Asked Questions about data-analysis

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

FAQPage Schema
How do I analyze a CSV file to find patterns and generate a report?

To analyze a CSV file for patterns, you load the dataset, clean missing values and duplicates, compute statistical aggregates, generate visualizations like histograms, and structure the findings into a readable report.

What is the best way to clean and prepare raw datasets for statistical analysis?

The best way to clean raw datasets for statistical analysis is to create a copy, handle missing values, remove duplicates, perform type conversions, and filter outliers while preserving the original data.

Can I use pandas data frames and SQL query results for data exploration and visualization?

Yes, you can use pandas data frames and SQL query results for data exploration and visualization. The workflow supports computing descriptive stats, generating heatmaps, and identifying trends across these formats.

Does data analysis work with JSON datasets to compute descriptive statistics and grouped aggregates?

Data analysis works with JSON datasets to compute descriptive statistics, grouped aggregates, correlations, and pivots. It inspects schema and distributions before producing a structured findings report.

What visualizations can I generate from time-series datasets to reveal patterns for decision-making?

From time-series datasets, you can generate visualizations like time-series summaries, histograms, boxplots, and heatmaps to reveal underlying patterns and support data-driven decision-making.

How does this approach handle sensitive personal data during the data profiling and reporting pipeline?

The data profiling pipeline handles sensitive personal data by validating results and avoiding exposure of sensitive information, ensuring that the generated reports and visualizations remain secure.