nutrient-document-processing

Convert, OCR, redact, sign, and extract data from documents via the Nutrient DWS API.

Updated May 9, 2026
One-click install
npx skills add https://github.com/kk20300113-png/my-claude-skills --skill nutrient-document-processing-kk20300113-png
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nutrient-document-processing
Source: https://github.com/kk20300113-png/my-claude-skills/tree/main/nutrient-document-processing
Command: npx skills add https://github.com/kk20300113-png/my-claude-skills --skill nutrient-document-processing-kk20300113-png

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually converting documents between formats, extracting data from PDFs, running OCR on scanned files, redacting sensitive information, signing agreements, and filling forms is extremely time-consuming and prone to human error, especially when handling large volumes of mixed-format documents.

Core Features & Use Cases

  • Multi-format Document Conversion: Seamlessly convert between PDF, DOCX, XLSX, PPTX, HTML, and common image formats.
  • Advanced Document Operations: Extract text and tables, run OCR on scanned documents, redact PII using presets or custom regex, add watermarks, digitally sign PDFs, and fill form fields programmatically.
  • Use Case: A legal operations team can use this skill to batch-redact sensitive client data from 100+ case PDFs, convert them to editable DOCX files, and add confidentiality watermarks in a single workflow.

Quick Start

Use the nutrient-document-processing skill to extract all text from the attached scanned PDF file 'client-contract.pdf' and save it as a searchable, editable text document.

Frequently Asked Questions about nutrient-document-processing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I batch redact PII from multiple PDF files and convert them to DOCX?

To redact PII and convert PDFs to DOCX, use the nutrient-document-processing skill to send multipart POST requests to the Nutrient build endpoint. It applies custom regex or preset redactions and performs multi-format conversion in a single workflow.

Can I run OCR on scanned PDFs and extract structured data like tables?

Yes, you can run OCR on scanned PDFs and extract structured data. The skill sends custom instructions to the Nutrient DWS API to recognize text in scanned images and extract unstructured data like text and tables from your files.

Do I need a Nutrient API key to perform digital signing and form filling?

Yes, a valid Nutrient API key is required to perform digital signing and form filling. The skill relies on this key to authenticate multipart POST requests sent to the Nutrient build endpoint for these document operations.

What is the best way to programmatically add watermarks to legal PDF documents?

The best way to programmatically add watermarks to legal PDFs is using the Nutrient API via this skill. It applies custom instructions to the document build endpoint, adding confidentiality watermarks alongside other operations like redaction.

Does this tool support converting HTML and XLSX files into PDF format?

Yes, the tool supports converting HTML and XLSX files into PDF format. It handles multi-format document conversion across PDF, DOCX, XLSX, PPTX, HTML, and common image formats using the Nutrient DWS API.

Why does my document processing workflow fail when handling multiple mixed formats?

Document processing fails if you lack a valid Nutrient API key or send incorrect multipart POST requests. The skill requires proper API authentication and custom instructions for the Nutrient build endpoint to process mixed-format files.