Table Extractor
Extracts structured tabular data from PDFs and images into clean, standardized JSON format.
Table Extractor enables Claude Code to parse and reconstruct rows, columns, and cell structures from documents, PDFs, and images into structured JSON. Leveraging pdfplumber as a primary extraction engine alongside coordinate-based text clustering for borderless tables, this skill provides reliable tabular parsing both as an on-demand utility for user requests and as a downstream dependency for other document processing pipelines.
主な機能
01Handles both simple and complex document table layouts
02Outputs structured JSON containing standardized row and cell arrays
03Estimates borderless table columns using x-coordinate text clustering
040 GitHub stars
05Extracts tabular data from PDF documents using pdfplumber
06Functions as a reusable sub-skill for automated document pipelines
ユースケース
01Converting financial statements or report tables in PDF format into machine-readable JSON
02Serving as a helper skill for larger document ingestion and processing workflows
03Extracting data from scanned forms and borderless document tables without manual data entry