Data Change Analysis

Explain why a metric moved by decomposing it across segments, separating mix from rate, and stating what the data cannot explain. Use when someone asks why a number went up or down.

5 stars 1 forksOther

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add eshmith7/claude-skills-library --skill data-change-analysis
Manual install
git clone --depth 1 https://github.com/eshmith7/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/data-skills/data-change-analysis ~/.claude/skills/data-change-analysis

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Why Did This Change

This is the most common request an analyst receives and the one most often answered with a guess. The guess sounds reasonable, gets repeated upward, and becomes the accepted reason. This skill answers it with decomposition, and is explicit about the difference between what moved and what caused it.

## When to use this

Trigger on: why did X drop, what is driving this change, why are sales down, explain this movement, "the number looks off this month", root cause of a metric change.

## Before you start

Required: the metric with its dimensions, covering both periods being compared.

Ask, briefly:
1. Which two periods are being compared, and whether the comparison should be against the prior period, the same period last year, or a target
2. Which dimensions are available: region, channel, product, segment, salesperson, store, campaign
3. Whether anything changed operationally in the window, such as a price change, a campaign, a tracking change or a definition change. Ask this early. It frequently is the answer, and it saves an hour of decomposition.

## Step zero, and do not skip it

**Is this even a real change?**

Most metric movements are normal variation, and explaining noise is the most common waste of analyst time. Before decomposing anything:

- Look at the metric's history if it is available. How much does it move month to month in a normal period?
Read the full skill on GitHub

Details

Skill name
data-change-analysis
Path
data-skills/data-change-analysis/SKILL.md
Repo updated
9 September 2026

FAQ

What does the Data Change Analysis skill do?

Explain why a metric moved by decomposing it across segments, separating mix from rate, and stating what the data cannot explain. Use when someone asks why a number went up or down.

How do I install the Data Change Analysis skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add eshmith7/claude-skills-library --skill data-change-analysis. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Data Change Analysis popular?

It lives in eshmith7/claude-skills-library, which has 5 GitHub stars and 1 forks.

Related skills

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.