メニュー
Export datasets to multiple output formats in one invocation — CSV, JSON, Parquet, and Excel. Supports per-format configuration, batch export of multiple DataFrames, and ZIP packaging.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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 | multi-format-exporter |
| description | Export datasets to multiple output formats in one invocation — CSV, JSON, Parquet, and Excel. Supports per-format configuration, batch export of multiple DataFrames, and ZIP packaging. |
| version | 0.5.0 |
A versatile data export tool that writes datasets to multiple file formats simultaneously. In a single invocation, can output the same data as CSV, JSON (records or nested), Parquet (columnar), and Excel (.xlsx with optional formatting). Supports batch mode for exporting multiple datasets at once, and can package all outputs into a ZIP archive.
--input / -i: Path(s) to input data file(s) (required)--output-dir / -o: Output directory (required)--formats / -f: Comma-separated output formats: csv,json,parquet,excel (default: csv)--base-name: Base filename for outputs (default: derived from input)--csv-delimiter: Delimiter for CSV output (default: ,)--csv-encoding: Encoding for CSV output (default: utf-8)--json-orient: JSON orientation: records, columns, split (default: records)--json-indent: JSON indentation (default: 2)--parquet-compression: Compression for Parquet: snappy, gzip, zstd (default: snappy)--zip: Package all outputs into a ZIP file--float-format: Format for float columns in CSV (e.g., %.2f)data.csv, data.json, data.parquet, data.xlsx)export_manifest.json: List of exported files with sizes and checksumsexport_bundle.zip containing all outputspython3 ./skills/multi_format_exporter/export.py -i <file> -o <output_dir> -f csv,jsonpandas, pyarrow, openpyxl