メニュー
Validate tabular data against JSON schemas and configurable business rules — column presence, type checks, nullable/unique constraints, range rules, referential integrity against lookup tables, and temporal consistency.
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。
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.
SOC 職業分類に基づく
| name | data-validation |
| description | Validate tabular data against JSON schemas and configurable business rules — column presence, type checks, nullable/unique constraints, range rules, referential integrity against lookup tables, and temporal consistency. |
| version | 1.0.0 |
Validates dataset records against both structural schema definitions and domain-specific business rules. Checks column presence, data types, nullable/unique constraints, regex patterns (schema layer), plus numeric range checks, cross-column constraints, referential integrity against external catalog/lookup tables, and date range validation (business rule layer). Records failing validation are flagged, rejected, or separated.
Merges functionality from: schema_validator, business_rule_checker.
[min, max] or > 0end_date >= start_date)product_id in product catalog)--input / -i: Path to dataset (CSV or Parquet) (required)--schema / -s: Path to JSON schema file--rules / -r: Path to business rules config (JSON or YAML)--lookup-dir: Directory containing lookup tables for referential checks--output / -o: Output directory--reject-action: flag, reject, or separate (default: flag)--strict: Fail on extra columns beyond schema--max-errors: Stop after N errors (default: unlimited)valid_records.csv: Records passing all checksrejected_records.json: Failed records with violation details and reasonsvalidation_report.json: Overall pass/fail, per-column results, per-rule countsrule_summary.json: Per-rule pass/fail percentagespython3 ./skills/data_validation/validate.py -i <file> -s <schema> -r <rules> -o <output_dir>pandas, numpy, jsonschema