メニュー
Evaluate data quality from observed structure and summary evidence.
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
Compare scientific variables with units, ranges, and quality caveats.
Inspect dataset structure before analysis or visualization.
Choose visual checks that match the inspected data.
Route dataset questions to structure, analysis, or visualization experts.
Choose a plot that confirms numeric conversion integrity.
Classify scientific dtype conversions by loss and safety risk.
| name | reason_about_quality |
| title | Reason About Quality |
| description | Evaluate data quality from observed structure and summary evidence. |
Use this skill to turn raw inspection results into quality findings. Check for missing values, impossible ranges, inconsistent units, duplicate identifiers, low sample counts, suspicious constants, and metadata gaps.
Keep quality judgments evidence-based. If the data is insufficient for a firm claim, report the uncertainty and the additional check needed.
