nutrient-document-processing

Convert, extract, OCR, redact, watermark, sign, and fill PDF forms via the Nutrient DWS Processor API.

1|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/khetansarvesh/ai_skills_repo --skill nutrient-document-processing-khetansarvesh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nutrient-document-processing
Source: https://github.com/khetansarvesh/ai_skills_repo/tree/main/skills/nutrient-document-processing
Command: npx skills add https://github.com/khetansarvesh/ai_skills_repo --skill nutrient-document-processing-khetansarvesh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the manual burden of converting, OCR-ing, extracting, and sanitizing documents so teams can safely reuse document content without reformatting or retyping.

Core Features & Use Cases

  • Multi-format conversion: Transform PDFs, DOCX, XLSX, PPTX, HTML, and common image formats into target output formats for downstream workflows.
  • Text and table extraction: Extract plain text and convert tables into structured outputs such as XLSX for analysis or ingestion.
  • OCR for scanned documents: Turn scanned PDFs/images into searchable PDFs using selectable OCR languages (100+).
  • PII redaction: Apply preset or regex-based redaction strategies to mask sensitive information before sharing or storing.
  • Watermarking and digital signing: Add confidentiality watermarks and apply CMS digital signatures to records.
  • PDF form filling: Populate PDF form fields from provided values to automate document completion.

Quick Start

Request nutrient-document-processing to convert your document to the desired output, extract text or tables, run OCR if it is scanned, and redact specified PII before returning the final file.

Frequently Asked Questions about nutrient-document-processing

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

FAQPage Schema
How do I extract text and tables from a scanned PDF using OCR?

To extract text and tables from a scanned PDF, apply OCR to create a searchable document, then extract plain text and convert tables into structured XLSX outputs for analysis or downstream ingestion.

Can I redact PII from Office files and HTML before sharing?

Yes, you can redact PII from Office files and HTML by applying preset or regex-based redaction strategies to mask sensitive information before sharing or storing the transformed documents.

What is the best way to automate PDF form filling and digital signing?

Automating PDF form filling and digital signing involves populating form fields from provided values and applying CMS digital signatures to finalize records for compliance and document automation.

Does this document conversion approach support adding watermarks to images?

Yes, this document conversion approach supports adding confidentiality watermarks to common image formats and other files, ensuring safe reuse of document content without reformatting or retyping.

When do I need to use regex-based redaction for document sanitization?

You need to use regex-based redaction for document sanitization when specific patterns of sensitive information must be masked, allowing precise compliance sanitization before downstream workflows.

How do I convert DOCX and PPTX files into target output formats for data capture?

To convert DOCX and PPTX files for data capture, transform these formats into target output formats using multipart POST requests with an instructions JSON payload supporting file parts and actions.