Convert PDFs, DOCX, and images to text, markdown, or searchable PDFs.
npx skills add https://github.com/spoonbobo/trinity --skill doc-convert
Please help me install this Agent Skill. Skill: doc-convert Source: https://github.com/spoonbobo/trinity/tree/main/app/skills/doc-convert Command: npx skills add https://github.com/spoonbobo/trinity --skill doc-convert
This Skill automates the conversion and text extraction from various document formats, including PDFs, DOCX, and images, streamlining document processing workflows.
Use the doc-convert skill to extract text from the file named 'report.pdf'.
High-intent search queries and answers about installing and using this skill.
To extract text from a scanned PDF using OCR, this Skill utilizes tesseract to recognize characters in document images and pdftotext to process digital PDFs. It converts inaccessible document images into searchable plain text or markdown formats.
Yes, you can convert a DOCX file to markdown automatically by utilizing the pandoc engine integrated within this Skill. It directly transforms Microsoft Word documents into structured markdown text for easier downstream processing.
Yes, this tool supports converting standard PDFs and image files into searchable PDFs by applying optical character recognition. It utilizes tesseract alongside Python libraries to embed extracted text layers over original document images.
The best way to extract text from multiple PDF invoices into a structured file is using this Skill's batch processing capability. It automates text extraction from various formats and outputs structured data ready for analysis.
No, you do not need to manually install pandoc and tesseract separately to convert document formats. The Skill abstracts these dependencies internally, allowing you to directly perform text extraction and document conversion without manual environment setup.
A limitation of using pdftotext for text extraction is that it cannot process scanned image-based documents, requiring tesseract OCR instead. This Skill automatically handles such constraints by routing image-dependent PDFs to the appropriate OCR engine.
pinakdhabuConvert PDFs, DOCX files, images, and scanned documents to text.
jleechanorgExtract text, Markdown, tables, and images from PDFs and scans.
mofa-orgExtract text and tables from PDFs and export to Excel, CSV, or Markdown.
kngender5Extract text, tables, and equations from PDFs and scanned documents using OCR.
