skills / data

statistical-analysis

what it does

Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.

Verified Before and after: 2 models 1 try per case View source Download .zip

Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the skill and once without. Read both and judge for yourself.

“What's our typical order value this week? I need one number for the weekly report.”

Source material given with the request

Order values this week (USD), 20 orders: 18, 22, 25, 27, 29, 31, 33, 34, 36, 38, 40, 42, 45, 48, 52, 55, 61, 70, 640, 1250
with the skill
**Typical order value this week: $39 (median)** Use the median rather than the mean here. The mean is $129.80, but that is pulled up by two very large orders ($640 and $1,250). Those two orders make up about 73% of the week's $2,596 in revenue, yet 18 of the 20 orders are $70 or less. Only 2 of 20 orders (10%) are above the mean, so it doesn't describe a typical order. | Measure | Value | |---|---| | Median | $39 | | Mean | $129.80 | | Middle 50% of orders | about $30 to $54 | | Mean excluding the two large orders | $39.20 | **Suggested line for the report:** "Typical order value was $39 (median). Average order value was $130, inflated by two large orders ($640 and $1,250) that accounted for roughly 73% of revenue." - **The two large orders:** I kept them in the median, since they are real orders, not errors. Check whether they are bulk or enterprise purchases. If so, it's reasonable to report them separately. - **Sample size:** 20 orders is small, so the median could shift noticeably from week to week. Compare it with prior weeks before reading much into a change.
without
**Typical order value: $39** (median) The median is the better choice here because two large orders ($640 and $1,250) pull the mean up to about $129.80. That is more than triple what 18 of the 20 orders look like. The median is $39, the average of the 10th and 11th values (38 and 40). If you have room for a short note in the report, you could add: "Two orders over $600 lifted the average to $130; excluding them, the average is about $39." The mean of the other 18 orders is $1,306 ÷ 18 ≈ $38.97, which confirms that $39 is representative.

Answers are shown exactly as the model wrote them, from the first try, and nothing is picked by hand.

The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 3 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 3 Nov 2026

The tasks

written by Carte Blanche
landing-page-simpson

“Which landing page converts better? Looks like B is the clear winner to me.”

segment-pvalue-multiple-tests

“Marketing wants to put next quarter's budget into Ohio because the analysis found a significant lift there (p = 0.02). Is that sound?”

signup-anomalies-before-removal

“Here are daily signups for the last four weeks. Flag anything anomalous. I'm planning to drop outliers before I compute the monthly average.”

store-layout-paired-test

“I tested whether our new store layout increased sales. I ran a two-sample t-test and got p = 0.63, so I'm going to report that the layout did nothing. Is my conclusion right?”

typical-order-value-skewed

“What's our typical order value this week? I need one number for the weekly report.”

Install

Download the .zip and unzip it. Put its files, in a folder named statistical-analysis, here:

Claude Code~/.claude/skills/Every project. For one project only, use .claude/skills/ inside it.
Codex~/.agents/skills/Every project. For one repository only, use .agents/skills/ inside it.
Cursor~/.cursor/skills/Cursor also reads the Claude Code and Codex folders above.

Then start a new session and ask for what the skill does. Other agents that read SKILL.md have their own skills folder; check their docs.

Coming after launch: get skills from inside your agent, no download needed.