Number crunch
Statistical analysis suite: descriptive statistics, correlation analysis, and outlier detection on a single dataset.
When to use this pack
An agent has a series of numbers (prices, scores, measurements) and needs the full statistical picture in one call: central tendency, spread, whether any values are anomalous, and the trend direction.
Tools in this pack
-
Stats summary
$0.001
POST /api/stats-summary
Compute the full descriptive-stats panel for an array of numbers in one call: count, sum, mean, median, mode, stddev (sample), variance, min, max, range, q1, q3, IQR. Beats calling 12 separate tools when you already have the array in front of you.
-
Correlation (Pearson)
$0.001
POST /api/correlation
Pearson correlation coefficient between two equal-length numeric series. Returns r (the correlation, -1 to 1), r² (variance explained), n (sample size). Use this to ask things like: is a stock's daily return correlated with a macro indicator? Are two FRED series moving together?
-
Outlier detection (IQR + z-score)
$0.001
POST /api/outliers
Flag outliers in a numeric series using either the IQR rule (Tukey fences at 1.5·IQR — robust, default) or z-score (|z| > threshold — assumes normality). Returns the outlier values + their indices + the thresholds used so you can decide whether to trust them.
Workflow
- Compute descriptive statistics with stats-summary — count, mean, median, stddev, quartiles, min, max.
- Run correlation of the values against their indices (position trend) — r near +1/-1 means a clear upward/downward trend over the series.
- Detect outliers — IQR fence + z-score methods flag anomalous values the agent should investigate or exclude.
Run it in Claude
claude mcp add agent402 -s user -- npx -y agent402-mcp@latest
Then paste this prompt into Claude:
Analyze the dataset [10,12,15,11,50,13,14] using Agent402: (1) stats-summary — descriptive stats. (2) correlation with x=values, y=indices — trend detection. (3) outliers — flag anomalies. Return {stats, trend, outliers}.← All skill packs