菜单
Aggregate data by multiple dimensions (time, product, region, channel) with configurable metrics, pivot tables, and generate KPI summary reports with top products, trends, and cross-dimensional breakdowns.
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 | data-aggregation-and-reporting |
| description | Aggregate data by multiple dimensions (time, product, region, channel) with configurable metrics, pivot tables, and generate KPI summary reports with top products, trends, and cross-dimensional breakdowns. |
| version | 1.0.0 |
Performs group-by aggregations across multiple dimensions and generates comprehensive KPI summary reports. Supports flat aggregation, pivot table generation, rolling window aggregation, and pre-built sales reporting templates (daily/weekly/monthly trends, top products, regional/channel breakdowns, category analysis).
Merges functionality from: data_aggregator, summary_report_generator.
--input / -i: Path to input data (CSV or Parquet) (required)--group-by / -g: Grouping columns (comma-separated)--metrics: Metric specs like revenue:sum,quantity:mean,order_id:count--mode: flat, pivot, rolling, or report (default: flat)--pivot-columns: Column for pivot columns--pivot-values: Value column for pivot--window: Window size for rolling mode--catalog / -c: Product catalog JSON (for category info in report mode)--top-n: Number of top items in report (default: 10)--time-granularity: daily, weekly, monthly (default: all)--output / -o: Output directory--sort-by: Sort by column (descending)summary_report.json: KPI summary with all sectionsagg_daily.csv, agg_weekly.csv, agg_monthly.csv: Time aggregationsagg_by_product.csv: Per-product summaryagg_by_region.csv: Regional breakdownagg_by_channel.csv: Channel performanceagg_region_category.csv: Region × Category pivotpython3 ./skills/data_aggregation_and_reporting/aggregate.py -i <file> -o <output_dir>pandas, numpy