Agent skill · data analytics · claude-office-skills
data-extractor
>
Why this skill is useful
Provides specific commands and patterns for extracting structured data from various document formats that the AI wouldn't reliably generate on its own.
What it needs
Requires unstructured installed locally. About 5k tokens when loaded. Last updated 2026-01-31. 363 stars on the source repository.
What this skill does
Data Extractor Skill Overview This skill enables extraction of structured data from any document format using unstructured - a unified library for processing PDFs, Word docs, emails, HTML, and more. Get consistent, structured output regardless of input format. How to Use 1. Provide the document to process 2. Optionally specify extraction options 3. I'll extract structured elements with metadata Example prompts: "Extract all text and tables from this PDF" "Parse this email and get the body, attachments, and metadata" "Convert this HTML page to structured elements" "Extract data from these mixed-format documents" Domain Knowledge unstructured Fundamentals Supported Formats Format Function Notes -------- ---------- ------- PDF partitionpdf Native + scanned Word partitiondocx Full structure PowerPoint partitionpptx Slides & notes Excel partitionxlsx Sheets & tables Email partitionemail Body & attachments HTML partitionhtml Tags preserved Markdown partitionmd Structure preserved Plain Text partitiontext Basic parsing Images partitionimage OCR extraction Element Types Auto Partition Format-Specific Partitioning Working with Tables Metadata Access Chunking for AI/RAG Batch Processing Export Formats Best Practices 1. Choose Strategy Wisely: "fast" for speed, "hires" for accuracy 2. Enable Table Detection: For documents with tables 3. Specify Language: For better OCR on non-English docs 4. Chunk for RAG: Use semantic chunking for AI applications 5. Handle Errors: Some formats may fail gracefully Common Patterns Document to JSON Email Parser Examples Example 1: Research Paper Extraction Example 2: Invoice Data Extraction Example 3: Document Corpus Builder Limitations Complex layouts may need manual review OCR quality depends on image quality Large files may need chunking Some proprietary formats not supported API rate limits for cloud processing Installation Resources unstructured GitHub Documentation Unstructured API
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills claude-office-skills/data-extractor