How do I secure sensitive data with this skill?

You can use the built-in redaction actions to automatically hide sensitive info like SSNs, emails, and credit card numbers using presets or custom regex patterns.

Can I use this as an MCP server?

Yes, the skill provides a native MCP server integration using @nutrient-sdk/dws-mcp-server for streamlined tool use within Claude.

What file types can this skill process?

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

Is an API key required to use Nutrient Document Processing?

Yes, you must obtain a free API key from nutrient.io and set the NUTRIENT_API_KEY environment variable for the skill to function.

Does it support multilingual OCR?

Yes, it supports over 100 languages via ISO 639-2 codes, including English, German, French, Japanese, Korean, and Chinese.

Nutrient Document Processing

Name: Nutrient Document Processing
Author: saar120

bysaar120

0•

コンテンツ管理

Automates complex document workflows including format conversion, OCR, data extraction, and PII redaction across multiple file types.

Nutrient Document Processing is a comprehensive Claude Code skill that leverages the Nutrient DWS API to handle sophisticated document manipulation tasks directly within your AI-assisted workflow. It enables Claude to perform high-fidelity conversions between formats like PDF, DOCX, and HTML, execute OCR on scanned documents in over 100 languages, and extract structured data from tables. Furthermore, it provides critical security and administrative features such as automated PII redaction, digital signing, watermarking, and programmatic PDF form filling, making it an essential tool for developers building automated document pipelines or enterprise content management systems.

主な機能

010 GitHub stars

02Pattern-based and Regex-driven PII redaction for data privacy

03High-fidelity conversion between PDF, Office documents, HTML, and images

04Advanced OCR supporting 100+ languages including Japanese, Chinese, and Korean

05Digital signatures and automated PDF form filling capabilities

06Structured data extraction from tables and forms into Excel or Text formats

ユースケース

01Automating the migration of legacy DOCX and HTML archives into searchable PDF formats

02Extracting tabular data from scanned financial reports for automated analysis

03Sanitizing sensitive legal or medical documents by redacting PII before distribution

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add saar120/skillgate-registry nutrient-document-processing

For use in Claude.ai and ChatGPT

主な機能

010 GitHub stars

02Pattern-based and Regex-driven PII redaction for data privacy

03High-fidelity conversion between PDF, Office documents, HTML, and images

04Advanced OCR supporting 100+ languages including Japanese, Chinese, and Korean

05Digital signatures and automated PDF form filling capabilities

06Structured data extraction from tables and forms into Excel or Text formats

ユースケース

01Automating the migration of legacy DOCX and HTML archives into searchable PDF formats

02Extracting tabular data from scanned financial reports for automated analysis

03Sanitizing sensitive legal or medical documents by redacting PII before distribution