Statistical Analysis
Data & Analyticsby anthropics
3/3 audits passApache-2.0
Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing.
Statistical Analysis gives the agent a working method for business statistics. For descriptive work it explains when to use mean, median or mode, insists on reporting mean and median together for business metrics, and covers standard deviation, IQR, coefficient of variation and a percentile ladder from p1 to p99. For trends it uses 7-day and 28-day moving averages, week-over-week to year-over-year comparisons, CAGR and log growth, seasonality checks, and simple forecasts (naive, seasonal naive, linear trend, moving average) that are always stated as a range.
Outliers are detected with z-scores, IQR or percentiles, and the skill asks you to report exactly what was excluded. Its hypothesis-testing table maps scenarios to t-tests, z-tests for proportions, paired t-tests, ANOVA, Mann-Whitney U and chi-squared, and it separates statistical from practical significance. It closes with cautions: correlation is not causation, multiple comparisons, Simpson's paradox, survivorship bias and the ecological fallacy. It is aimed at business analysts, and tells the agent to escalate to a data scientist for non-linear trends, multiple seasonalities or high-stakes forecasts.
In BusinessMCP the AI business analyst can apply these rules to your workspace's own analytics, conversion and Stripe revenue data, which keeps claims about growth or a test result properly hedged.
What you can do with it
- Summarise a skewed revenue metric with median, mean and percentiles
- Pick the right test to compare two conversion rates
- Flag outliers and report exactly what was excluded
- Give a forecast as a range with its assumptions stated
Run it on your business data
Imported into BusinessMCP, Statistical Analysis becomes a playbook your AI business analyst applies to your web analytics, funnels and connected databases.
Use Statistical Analysis in BusinessMCPInstall it in a coding agent
One command adds Statistical Analysis to your project.
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill statistical-analysisHow we vetted it
- Source
- anthropics/knowledge-work-plugins at da38ec1
- Licence
- Apache-2.0
- Security audits (skills.sh)
- Gen Agent Trust Hub: Pass · Socket: Pass · Snyk: Pass
- Bundled scripts
- None, instructions only
Checked 2026-09-25 against its skills.sh listing. How we vet skills
Related skills
All skillsExplore Data
Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or…
Data Visualization
Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles…
Data Storytelling
Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or building executive presentations.
Frequently asked questions
Which statistical tests does it cover?
Independent and paired t-tests, the z-test for proportions, ANOVA, the Mann-Whitney U test and the chi-squared test, each mapped to the scenario it fits.
Does it do advanced forecasting?
No. It sticks to naive, seasonal naive, linear trend and moving-average forecasts, and tells the agent to escalate to a data scientist for non-linear trends, multiple seasonalities or external drivers.
How do I install Statistical Analysis?
Run `npx skills add anthropics/knowledge-work-plugins --skill statistical-analysis`, or import it from the BusinessMCP dashboard to use it as a playbook in your workspace.
Keep exploring
Run Statistical Analysis against your whole business
Free plan, no credit card.
Use Statistical Analysis in BusinessMCP