About this skill

Problem It Addresses

Many small data tasks get blocked by the environment: installing pandas, openpyxl, or Jupyter packages before running a basic CSV statistic, clean, or merge can add setup friction. This skill targets lighter workflows: accept a CSV file or inline text, then produce descriptive statistics, cleaned data, merged tables, and converted output using only Python standard-library modules such as csv and json.

Core Capabilities And Steps

Statistical analysis: parses CSV rows, distinguishes numeric and text columns, and reports counts, mean, median, standard deviation, minimum, maximum, and quantiles.
Data cleaning: supports dedup for exact duplicate rows, fill_na using mean, median, zero, drop, or empty string, and trim_space for leading/trailing whitespace, with a processing report.
Table merging: supports vertical row appending and horizontal key-based column joining.
Format conversion: converts between csv, tsv, json, and markdown, making results easier to feed into logs, APIs, or documentation.

Boundaries And Notes

It fits quick processing of straightforward CSV files, not complex database queries, multi-relational recursive cleaning, or large distributed workloads. Horizontal merging depends on a matching key; inconsistent field names will directly affect output. Automatic numeric/text detection can miss mixed-type columns. The JSON-style output is convenient for agents, but business interpretation still belongs to the caller.

Screenshots

Use Cases

Given raw user-behavior CSVs, produce column-level mean, median, and quantile summaries quickly.
When exported reports contain duplicate rows or padded spaces, dedupe rows, fill blanks, and get a cleanup report.
When two date-named order CSVs must be stacked into one table, merge them vertically and convert the output.
Before debugging a script, convert a CSV into JSON or Markdown so its structure is easy to inspect.

Best For

An analyst who owns monthly data rollups and needs quick CSV distribution stats plus field cleaning.
A backend engineer debugging scripts who needs CSV converted into JSON or TSV for service tests.
An operations lead comparing competitor exports and needs multiple CSVs joined horizontally by key.
A product engineer writing docs who needs table results rendered as Markdown for easy embedding.