Nutrient Document Processing is a comprehensive Claude Code skill that enables automated document manipulation and data extraction through the Nutrient DWS API. It allows developers to seamlessly convert between formats like PDF, DOCX, and HTML, perform high-accuracy OCR in over 100 languages, redact sensitive PII, and digitally sign documents directly within their development workflow. Whether you need to automate PDF form filling, apply watermarks to sensitive drafts, or extract structured data from complex tables into Excel, this skill provides a robust, enterprise-grade toolkit for sophisticated document management tasks.
主要功能
01Automated PII redaction using presets or regex
02Digital signatures and PDF form filling
03OCR for scanned documents in 100+ languages
04214,597 GitHub stars
05Multi-format conversion (PDF, Office, HTML, Images)
06Structured data extraction from tables and text
使用场景
01Extracting tabular data from PDF invoices into Excel spreadsheets
02Automating legal document redaction and signing workflows
03Converting batch legacy documents into searchable, machine-readable PDFs