exploratory-data-analysis (k-dense)
- Data
Profiles a dataset you already have — distributions, missingness, outliers, leakage, and transformation sensitivity — and scaffolds a rigorous EDA report, all computed locally and deterministically without touching the network. It INSPECTS data before you model it; it does not gather the data, draw the finished charts, or make causal or confirmatory claims.
A situation it fits
You inherited a messy spreadsheet of customer purchases and need a careful, offline pass to find gaps, weird numeric values, and any columns that might accidentally reveal the label before you train a model.
6 scenarios in the bank answer to exploratory-data-analysis (k-dense). The rest are in the game.
Skills it gets confused with
These share a family with exploratory-data-analysis (k-dense), which is another way of saying they are the ones you might reach for by mistake.
- chart-designer (claude-office)Turns a prepared dataset into the right visualization — choosing an appropriate chart type and emitting ready-to-render configs for libraries like ECharts and Chart.js, up to full dashboards. Its job is PRESENTING data visually; it does not scrape sources, clean the data, or compute the statistical findings you decide to show.
- deep-research (firecrawl)Investigates an open-ended question by gathering evidence across many websites and synthesizing a formal, cited report — executive summary, multi-angle findings, contrarian views, and open questions. It is for report-scale SYNTHESIS of a complex topic from the open web, not quick lookups, top-N product lists, or literature reviews over published papers.
- web-scraping (jamditis)Pulls data off web pages that don't hand it over cleanly — cascading through fallback fetch strategies and coping with 403s, CAPTCHAs, and rate limits, while validating every URL and treating whatever comes back as untrusted. It is a disciplined way to ACQUIRE raw data from the live web, not a tool for analyzing, charting, or synthesizing what you collect.
Knowing what exploratory-data-analysis (k-dense) does is the easy half. Telling it apart from the others under time pressure is the game.
Today's sessionexploratory-data-analysis (k-dense) is part of k-dense-ai/scientific-agent-skills. Licence: MIT. The description above was written for this game, not taken from the skill.