data-analysis · akillness — Claude Code skill: dataset analysis and reports

What data-analysis does

The skill sets an order for working with a dataset. The agent frames the question and the metric, profiles the data for nulls, duplicates and impossible values, and only then computes. Four patterns are covered: explaining a change, comparing segments, funnel and retention work, and telemetry review. Each comes with its own checklist.

Findings come back in three layers: what the data shows, what it likely means, and what could weaken the conclusion. That keeps observation apart from guesswork. Tool access is limited to Read, Grep, Glob and Bash — reading files, searching and running commands, with no code edits.

This is not the skill for anomaly hunting across a codebase or for building a dashboard; the same collection has separate skills for those. When data quality is poor, the agent says what can be trusted instead of forcing conclusions out of a messy extract.