Table Extract
Extracts structured tabular data from PDF documents and images into clean JSON formats.
Table Extract provides automated table parsing capabilities for Claude Code, utilizing Camelot to detect and extract tabular structures from PDF files and images into standardized JSON. Built to function both as an internal utility for composite data-processing skills and as an on-demand tool when users request table extraction, it streamlines the conversion of unstructured document tables into machine-readable data arrays ready for analysis or downstream pipelines.
主要功能
01Extracts tabular structures from PDF files and document images
02Uses the Camelot library for reliable layout and boundary detection
030 GitHub stars
04Outputs parsed data in clean, predictable JSON formats
05Functions as a downstream dependency for complex data ingestion skills
06Responds to direct conversational table extraction requests
使用场景
01Extracting tabular metrics from technical documentation and research papers
02Converting financial and tabular reports from PDF documents into JSON
03Serving as a helper skill within automated document processing pipelines