Parse, convert, chunk, and structurally analyze PDFs, DOCX, PPTX, HTML, and images with IBM's open-source Docling toolkit.
Document Processing Skills
Create and edit documents, spreadsheets, and slides.
Skills in Document Processing
Skill: GLM-OCR Table Recognition
by Z.ai (Zhipu AI)
Extract complex tables, including merged cells and multi-row headers, from images and PDFs into clean Markdown.
Skill: PaddleOCR Document Parsing
by PaddlePaddle
Turn PDFs and scanned images into structured Markdown/JSON: cell-level tables, LaTeX formulas, correct multi-column order.
Skill: Spreadsheets (XLSX)
by Anthropic
Open, create, and edit spreadsheets — formulas, formatting, charts, data cleaning, and CSV/TSV conversion.
Skill: PowerPoint (PPTX)
by Anthropic
Build, read, and edit PowerPoint presentations — slides, layouts, templates, speaker notes, and comments.
Skill: Word Documents (DOCX)
by Anthropic
Create, read, and edit Microsoft Word documents — headings, tables of contents, page numbers, letterheads, tracked changes, comments, and images.
Skill: PDF
by Anthropic
Read, create, and manipulate PDF files — extract text and tables, merge, split, watermark, fill forms, encrypt, and OCR scanned pages.