菜单
Compute statistical summaries (mean, median, p95, p99, min, max) for numeric columns in a CSV file and output a JSON report.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Validate tabular data against configurable business rules — range checks, cross-column constraints, referential integrity against lookup tables, and temporal consistency.
Load and parse CSV files into structured data frames with configurable encoding, delimiter, and date parsing options.
Export pandas DataFrames or processed datasets to well-formatted CSV files with configurable encoding, delimiter, quoting, and column ordering.
Aggregate tabular data by one or more dimensions with configurable metrics — sum, mean, count, min, max, median. Supports multi-level grouping and pivot table generation.
Comprehensive data cleaning toolkit — handles missing values, duplicate removal, type coercion, whitespace trimming, and outlier detection in a single pass over the dataset.
Identify and remove duplicate records from tabular datasets using exact-match, fuzzy-match, or composite-key-based deduplication strategies.
| name | csv-stats-reporter |
| description | Compute statistical summaries (mean, median, p95, p99, min, max) for numeric columns in a CSV file and output a JSON report. |
| version | 1.0.0 |
Reads a CSV file and computes descriptive statistics for all numeric columns. Produces a JSON report containing per-column metrics that is useful for monitoring, anomaly detection, and dashboarding.
| Parameter | Flag | Required | Description |
|---|---|---|---|
| input | -i | Yes | Path to the input CSV file |
| output | -o | Yes | Path to the output JSON report |
| columns | --columns | No | Comma-separated list of columns to analyse (default: all) |
| group-by | --group-by | No | Column name to group statistics by |
For each numeric column the following metrics are computed:
count — number of non-null valuesmean — arithmetic meanmedian — 50th percentilestd — standard deviationmin / max — extremesp95 — 95th percentilep99 — 99th percentileA JSON file structured as:
{
"source": "<input_file>",
"total_rows": 1234,
"columns_analysed": ["response_time_ms", "status_code"],
"stats": {
"response_time_ms": {
"count": 1200,
"mean": 245.3,
"median": 180.0,
"std": 312.7,
"min": 12,
"max": 4500,
"p95": 890.0,
"p99": 2100.0
}
}
}
When --group-by is used, stats becomes a nested dict keyed by group value.
python3 ./skills/csv-stats-reporter/stats_reporter.py -i <input.csv> -o <report.json> \
[--columns col1,col2] [--group-by col_name]