Does the OCR feature support languages other than English?

Yes, the OCR engine supports over 100 languages, including Chinese (Simplified and Traditional), Japanese, Korean, Arabic, and most European languages.

Is an API key required to use this document processing skill?

Yes, you need a free or paid API key from nutrient.io (formerly PSPDFKit) to authenticate requests.

Can I use this as an MCP server instead of raw curl commands?

Yes, the skill includes configuration for the Nutrient DWS MCP server, allowing for native tool integration within Claude Code.

Can this skill help with data privacy and compliance?

Yes, it features built-in redaction tools that can automatically identify and mask sensitive information like SSNs, emails, and credit card numbers.

What file formats does this Nutrient skill support?

It supports a wide range of formats including PDF, DOCX, XLSX, PPTX, HTML, and various image formats like JPG, PNG, and TIFF.

Nutrient Document Processing

Name: Nutrient Document Processing
Author: xu-xiang

byxu-xiang

•

323

•

内容管理

Automates advanced document manipulation, conversion, and data extraction using the Nutrient DWS API.

This skill integrates the Nutrient (formerly PSPDFKit) Document Workflows (DWS) API into Claude Code, enabling developers to perform complex document operations directly from their development environment. It provides a comprehensive suite of tools for converting between formats like PDF, Office documents, and HTML, alongside sophisticated capabilities such as OCR for scanned files, PII redaction for security compliance, digital signatures, and automated form filling. It is particularly useful for building automated document pipelines, ensuring professional-grade document handling within an AI-assisted workflow.

主要功能

01323 GitHub stars

02High-accuracy OCR for scanned documents in over 100 languages

03Automated PII redaction and sensitive data masking using regex or presets

04Digital signing and programmatic PDF form filling

05Multi-format conversion between PDF, DOCX, XLSX, HTML, and images

06Data extraction from documents into structured text or Excel formats

使用场景

01Implementing secure workflows that automatically redact sensitive identifiers before document sharing

02Automating the conversion of internal HTML reports into professional, watermarked PDF documents

03Extracting tabular data from scanned invoices and receipts into structured Excel files

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add xu-xiang/everything-claude-code-zh nutrient-document-processing

For use in Claude.ai and ChatGPT

主要功能

01323 GitHub stars

02High-accuracy OCR for scanned documents in over 100 languages

03Automated PII redaction and sensitive data masking using regex or presets

04Digital signing and programmatic PDF form filling

05Multi-format conversion between PDF, DOCX, XLSX, HTML, and images

06Data extraction from documents into structured text or Excel formats

使用场景

01Implementing secure workflows that automatically redact sensitive identifiers before document sharing

02Automating the conversion of internal HTML reports into professional, watermarked PDF documents

03Extracting tabular data from scanned invoices and receipts into structured Excel files

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add xu-xiang/everything-claude-code-zh nutrient-document-processing

For use in Claude.ai and ChatGPT