data-normalizer

What problem does it solve?

Archaeological research often involves manually extracting data from numerous documents (PDF, HWP, DOCX, TXT), a process that is both time-consuming and prone to errors. This Skill automates the collection and standardization of this critical information.

Core Features & Use Cases

• Automated Data Extraction: Scans diverse document types (PDF, HWP, DOCX, TXT) to extract raw text and key metadata.
• Metadata Normalization: Standardizes extracted information such as title, author, publication year, location, coordinates, historical period, and artifact/feature types.
• Use Case: Process hundreds of archaeological reports and academic papers from your local folders, automatically creating a unified, structured dataset (JSONL, CSV) ready for in-depth analysis, saving days of manual data entry.

Quick Start

Use the data-normalizer skill to collect and normalize all documents in the '논문/', '발굴조사보고서/', and '주변유적/' folders.