data-analysis

Guide data analysis from CSV/JSON loading through cleaning, exploration, visualization, and export.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/SalesTeamToolbox/frood --skill data-analysis-salesteamtoolbox
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analysis
Source: https://github.com/SalesTeamToolbox/frood/tree/main/skills/builtins/data-analysis
Command: npx skills add https://github.com/SalesTeamToolbox/frood --skill data-analysis-salesteamtoolbox

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you reliably analyze data by guiding end-to-end workflows from loading and cleaning through pattern discovery and interpretation, so you can produce actionable insights instead of ad-hoc spreadsheets.

Core Features & Use Cases

  • Insight-focused analysis workflow: Turn a business question into a structured sequence of steps (inspect, clean, explore, analyze, visualize, interpret, recommend).
  • Data tool-driven operations: Load CSV/JSON, compute column-level statistics, filter with queries, generate charts, transform via group-by aggregations, and export results.
  • Practical visualization guidance: Choose appropriate chart types (bars, histograms, line tables, pie, scatter) and fall back to labeled markdown tables when needed.
  • Statistical and reporting best practices: Use mean vs. median correctly, interpret standard deviation and percentiles, consider sample size limitations, and avoid conflating correlation with causation.

Quick Start

Use the data tool to load your dataset and run a query that filters the rows you care about, then request stats and a chart for the most relevant columns.

Frequently Asked Questions about data-analysis

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

FAQPage Schema
How do I clean and analyze CSV data end to end?

To clean and analyze CSV data, load the dataset, compute column-level statistics, filter rows with queries, transform via group-by aggregations, generate charts, and export analytic outputs. This workflow guides you from raw inspection to actionable recommendations.

What is the best way to visualize statistics from a JSON dataset?

Visualizing statistics from a JSON dataset involves computing column-level mean, median, standard deviation, and percentiles, then choosing appropriate chart types like bars, histograms, line tables, pie, or scatter plots to interpret patterns clearly.

Can I use group-by transformations and filtering queries on messy datasets?

Yes, you can apply group-by transformations and filtering queries to messy datasets. The workflow guides loading, cleaning, and exploring data so you can aggregate rows and compute statistics reliably before visualization.

Does this data analysis workflow support exporting results to CSV?

Yes, the data analysis workflow supports exporting results to CSV. After inspecting, cleaning, transforming, and visualizing your dataset, you can export the final analytic outputs for downstream reporting and decision-making.

When should I use mean versus median for column statistics interpretation?

Use mean versus median for column statistics interpretation based on data distribution and sample size limitations. The workflow applies statistical best practices, avoiding conflating correlation with causation, to ensure accurate pattern discovery and recommendations.