tda-document-ingestion

Convert PDF, DOCX, and XLSX documents into Markdown for TDL workflows.

1|Updated Dec 13, 2025

Search Tags:#structured data #markdown #document conversion #OCR #TDL

Ready to run

npx skills add https://github.com/stephendor/TDL --skill tda-document-ingestion

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tda-document-ingestion
Source: https://github.com/stephendor/TDL/tree/main/.agents/skills/tda-document-ingestion
Command: npx skills add https://github.com/stephendor/TDL --skill tda-document-ingestion

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdfplumber, python-docx, openpyxl, pdf2image, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps convert a variety of document types into Markdown or structured artifacts suitable for Topology Development Language (TDL), streamlining document processing and ensuring data integrity.

Core Features & Use Cases

Document Conversion: Transform PDFs, DOCX, XLSX, and web captures into Markdown or structured artifacts.
Ingestion Control: Manages conversion with precision, flagging uncertain OCR regions and tables.
TDL Integration: Facilitates TDL workflow by providing pre-converted text for further verification.

Quick Start

Run the tda-document-ingestion skill with the file 'annual-report.pdf'.

Frequently Asked Questions about tda-document-ingestion

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert PDF and DOCX documents to structured markdown for TDL workflows?▼

This Skill converts PDF, DOCX, and XLSX files into structured markdown artifacts optimized for Topology Development Language workflows. It ensures precise formatting and OCR accuracy for downstream verification processes.

Does document conversion handle uncertain OCR regions and complex tables?▼

Yes, the document conversion process manages ingestion with precision by actively flagging uncertain OCR regions and complex tables. This ensures data integrity and facilitates subsequent verification processes within your TDL workflow.

What Python dependencies do I need to parse XLSX and PDF files into structured artifacts?▼

You need the pdfplumber, python-docx, openpyxl, and pdf2image Python dependencies to parse XLSX and PDF files. These libraries provide the required parsing and formatting tools to extract and convert content into structured markdown artifacts.

What is the best way to prepare unstructured PDF reports for Topology Development Language ingestion?▼

The best way to prepare unstructured PDF reports for TDL ingestion is to run an automated conversion that extracts text and tables while flagging uncertain OCR regions. This produces structured markdown artifacts ready for further verification.

Can I use this to convert web captures and XLSX files into markdown?▼

Yes, you can convert web captures and XLSX files into markdown. The Skill supports transforming a range of document types, including PDFs, DOCX, XLSX, and web captures, into structured artifacts suitable for Topology Development Language.