Do I need an API key to use Nutrient Document Processing?

Yes, you must obtain a free API key from nutrient.io and export it as NUTRIENT_API_KEY in your environment.

Does the OCR support languages other than English?

Absolutely. It supports over 100 languages, including Japanese, Chinese, German, French, and Spanish using standard ISO codes.

How do I integrate this as a native tool in Claude?

You can use the provided MCP server configuration to integrate Nutrient DWS as a native tool using the @nutrient-sdk/dws-mcp-server package.

What file formats are supported by this skill?

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

Can I redact sensitive information like SSNs automatically?

Yes, the skill includes built-in presets for redacting SSNs, email addresses, credit card numbers, and other PII, as well as custom regex support.

Nutrient Document Processing

Name: Nutrient Document Processing
Author: affaan-m

byaffaan-m

•

112,919

•

内容管理

Automates document conversion, OCR, data extraction, and PII redaction using the Nutrient DWS API.

Nutrient Document Processing is a comprehensive Claude Code skill designed to handle complex document lifecycles directly within your development workflow. By leveraging the Nutrient DWS (Document Web Service) API, it enables Claude to perform high-fidelity conversions between PDF, Microsoft Office, HTML, and image formats. Beyond simple conversion, the skill provides advanced capabilities like OCR for over 100 languages, intelligent PII redaction, digital signing, and structured data extraction. It is ideal for developers building automated document pipelines, sanitizing sensitive data, or extracting information from scanned assets without leaving the terminal.

主要功能

01112,919 GitHub stars

02Advanced OCR for scanned documents supporting 100+ languages

03Automated PII redaction using preset patterns or custom regex

04Programmatic PDF form filling and digital CMS signing

05High-fidelity conversion between PDF, DOCX, XLSX, PPTX, and HTML

06Structured data extraction for tables and plain text

使用场景

01Redacting sensitive information from legal documents before analysis

02Extracting tabular data from scanned invoices into Excel format

03Converting batch Office documents to PDF for web distribution

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add affaan-m/everything-claude-code nutrient-document-processing

For use in Claude.ai and ChatGPT

主要功能

01112,919 GitHub stars

02Advanced OCR for scanned documents supporting 100+ languages

03Automated PII redaction using preset patterns or custom regex

04Programmatic PDF form filling and digital CMS signing

05High-fidelity conversion between PDF, DOCX, XLSX, PPTX, and HTML

06Structured data extraction for tables and plain text

使用场景

01Redacting sensitive information from legal documents before analysis

02Extracting tabular data from scanned invoices into Excel format

03Converting batch Office documents to PDF for web distribution

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add affaan-m/everything-claude-code nutrient-document-processing

For use in Claude.ai and ChatGPT