Skip to content
Agentmart
Submit a tool

data-analysis

Analyze user behavior patterns through quantitative data to validate hypotheses and discover product growth drivers.

Skill by zpower426

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/zpower426-data-analysis

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Analyze user behavior patterns through quantitative data to validate hypotheses and discover product growth drivers.

Use cases: data, marketing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/data-analysis

What's inside

Skill name
data-analysis
Description
Analyze user behavior patterns through quantitative data to validate hypotheses and discover product growth drivers.
License
MIT
Instructions
22 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Data Analysis: Quantitative Analysis and Experimental Evidence

Data doesn't lie, but it can mislead.

## Checklist

1. **Define Funnels** — What is the user conversion path? Where is the most severe churn?
2. **Execute Retention Cohort Analysis** — How does retention performance differ across various user cohorts over time?
3. **Perform Correlation Search** — Which core behavior is highly correlated with long-term user retention (The Magic Number)?
4. **Verify Experimental Conclusions (Post-Experiment Audit)** — Did the experimental results achieve statistical significance?

## Core Mandates

- **Reject Vanity Metrics**: Focus on "DAU/Day-1 Retention" rather than "Total Registered Users."
- **Segment and Sub-segment**: Global data often hides the truth. Perform segment analysis by channel, device, and region.
- **Correlation is Not Causation**: Seeing two metrics rise simultaneously does not mean A caused B.

## Expert Principles

Before looking at data, write down your **expected conclusion**. If the data does not match the expectation, that is where the real learning opportunity begins.

From zpower426/pmpowers, MIT.

More from zpower426/pmpowers

Signals

Stars
0
Forks
1
Open issues
0
Last commit (this folder)
Mar 31, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/zpower426/pmpowers
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from zpower426

Cite this page

data-analysis skill. Agent Mart. https://agentmart.dev/skills/zpower426-data-analysis (last updated 2026-10-24)