Outlier Detection

Identifies outliers in a dataset using IQR and z-score methods, interprets what each outlier represents, and produces a recommended action (remove, investigate, cap, or flag) for each outlier with rationale. Use when the user has data with suspected extreme values and needs a systematic approach to identify and handle them. Do NOT use for data cleaning beyond outlier handling (use data-cleaning-protocol), distribution analysis (use eda-framework), or hypothesis testing (use hypothesis-testing).

FerroxLabs Updated 618 repo stars
Murage. You have the vision. Put an AI workforce behind it. Dark-mode team conversation, Chief of Staff and Team map.

File contents

ferroxlabs/murage commit 32aebab2dd

Frequently asked questions

npx get-skill add ferroxlabs/outlier-detection