Smart Eda · k4thir bundle Adaptive exploratory data analysis. Use whenever a tabular dataset (CSV, Excel/xlsx, Parquet, TSV, JSON-lines, or an in-memory DataFrame) needs to be understood — including any request like "analyze this data", "explore this dataset", "what's in this file", "summarize this CSV", "EDA on this", "profile this data", "look at the distributions", "check for outliers", "what are the patterns here", or simply when a data file is uploaded with no explicit task. Also triggers for data-quality audits, missing-value investigations, correlation analysis, time-series profiling, and pre-modeling data understanding. Prefer this skill over ad-hoc analysis whenever the user's data hasn't been examined yet, even if they just say "take a look" or "what do you think". The skill profiles the data first, then chooses techniques based on what it actually finds — column types, scale, time structure, target presence — instead of running a fixed playbook.
