agentsclimarketplace

Csv summarizer

Skill suifeng156/skillport/examples/csv-summarizer

Cross-platform compatibility tester for Agent Skills — run one SKILL.md on Claude Code, Codex, and Gemini CLI; see where they diverge.

Install
npx -y skills add suifeng156/skillport --skill csv-summarizer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Read a CSV file and produce a concise summary including row count, column names, inferred types per column, and any obvious data-quality issues. Activates when the user asks to summarize, profile, or describe a CSV file or any tabular dataset in the working directory.

SKILL.md

1.5 KB, as published. Nobody here has run it

CSV Summarizer

When the user asks you to summarize or profile a CSV file, follow this protocol.

1. Identify the file

If the user names a specific file, use that. Otherwise list .csv files in the working directory and use the most recently modified one. Report the filename you chose.

2. Read and analyze

Read the file (or its first 1000 rows if very large). Compute:

  • Row count — total rows excluding the header.
  • Column count — from the header row.
  • Per-column:
    • Inferred type: integer, decimal, date, boolean, string, or mixed.
    • Distinct value count for low-cardinality columns (< 20 distinct).
    • A representative sample value.
  • Data quality flags — missing values, type inconsistencies inside a column, suspicious outliers, malformed dates, duplicated rows.

3. Report format

Produce a single response with:

  1. A one-line header: csv-summarizer: <filename> (N rows × M columns).
  2. A markdown table of columns: | name | inferred type | sample | notes |.
  3. A short paragraph titled "Data quality" describing any flags found, or "No issues detected" if none.

Do not modify the file. Read-only.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.