Agent skill · writing content · claude-office-skills
doc-parser
>
Why this skill is useful
Adds executable scripts for advanced document parsing and extraction that leverage IBM's docling library, which the AI wouldn't generate on its own.
What it needs
Requires docling installed locally. About 6k tokens when loaded. Last updated 2026-01-31. 363 stars on the source repository.
What this skill does
Document Parser Skill Overview This skill enables advanced document parsing using docling - IBM's state-of-the-art document understanding library. Parse complex PDFs, Word documents, and images while preserving structure, extracting tables, figures, and handling multi-column layouts. How to Use 1. Provide the document to parse 2. Specify what you want to extract (text, tables, figures, etc.) 3. I'll parse it and return structured data Example prompts: "Parse this PDF and extract all tables" "Convert this academic paper to structured markdown" "Extract figures and captions from this document" "Parse this report preserving the document structure" Domain Knowledge docling Fundamentals Supported Formats Format Extension Notes -------- ----------- ------- PDF .pdf Native and scanned Word .docx Full structure preserved PowerPoint .pptx Slides as sections Images .png, .jpg OCR + layout analysis HTML .html Structure preserved Basic Usage Advanced Configuration Document Structure Extracting Tables Extracting Figures Handling Multi-column Layouts Export Formats Batch Processing Best Practices 1. Use Appropriate Pipeline: Configure for your document type 2. Handle Large Documents: Process in chunks if needed 3. Verify Table Extraction: Complex tables may need review 4. Check OCR Quality: Enable OCR for scanned documents 5. Cache Results: Store parsed documents for reuse Common Patterns Academic Paper Parser Report to Structured Data Examples Example 1: Parse Financial Report Example 2: Technical Documentation Parser Example 3: Contract Analysis Limitations Very large documents may require chunking Handwritten content needs OCR preprocessing Complex nested tables may need manual review Some PDF types (encrypted) not supported GPU recommended for best performance Installation Resources docling GitHub Documentation IBM Research Blog
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills claude-office-skills/doc-parser