Extract text and tables from PDFs using Python and CLI workflows.
npx skills add https://github.com/AizenvoltPrime/claude-compass --skill pdf-aizenvoltprime
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/AizenvoltPrime/claude-compass/tree/main/.claude/skills/document-skills/pdf Command: npx skills add https://github.com/AizenvoltPrime/claude-compass --skill pdf-aizenvoltprime
This Skill provides a comprehensive toolkit for working with PDFs: extracting text and tables, merging, creating new PDFs, and handling forms, with guidance on large-scale workflows.
Use the pdf skill to extract text from the first page of 'invoice.pdf'.
High-intent search queries and answers about installing and using this skill.
Text and table extraction from PDFs uses libraries like pdfplumber to parse content into structured formats. The skill handles both standard PDFs and scanned documents, returning extracted text, table data, and metadata that you can export to CSV, JSON, or other formats for further analysis.
Yes, you can automate form filling by mapping field names to values and writing them into fillable PDF fields using pypdf and related tools. The skill supports both fillable and non-fillable field detection, allowing you to populate forms at scale through JSON-based workflows.
PDF manipulation—merging multiple documents, splitting by page ranges, and rotating pages—is handled through pypdf and similar libraries. These operations let you compose new documents, reorganize content, and prepare PDFs for downstream processing without re-encoding.
Scanned PDFs require OCR processing via pdf2image and pytesseract to convert image content into readable text. The skill chains image extraction with optical character recognition, enabling you to recover text from documents that contain no embedded text layer.
Watermarking, annotation editing, and metadata retrieval are supported through libraries like reportlab and pypdf. You can stamp documents, embed structured data, and modify document properties to track versions or enforce document protection workflows.
The skill supports both Python-based workflows using pypdf, pdfplumber, and Pillow, and CLI interfaces for scripting environments. Choose Python for programmatic control and integration, or CLI commands for shell automation and batch processing pipelines.
AnishWerkstattExtract text and tables from PDFs using Python scripts.
weirdgmeDesign and implement scalable platform engineering patterns for internal developer platforms.
TencentExtract text and tables, fill forms, and merge PDFs using Python scripts.
vrcmsProcess, convert, and extract data from PDF, DOCX, and images via the Nutrient DWS API.
