nutrient-document-processing

Convert, OCR, redact, sign, and fill documents using the Nutrient DWS API.

2|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/adamreger/ecc-antigravity --skill nutrient-document-processing-adamreger
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nutrient-document-processing
Source: https://github.com/adamreger/ecc-antigravity/tree/main/skills/nutrient-document-processing
Command: npx skills add https://github.com/adamreger/ecc-antigravity --skill nutrient-document-processing-adamreger

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Working with documents across formats requires juggling many tools: converting DOCX to PDF, extracting text from scanned files, redacting PII before sharing, and filling PDF forms manually. This Skill consolidates all of these operations into a single API-driven workflow. ## Core Features & Use Cases - Format Conversion: Convert between PDF, DOCX, XLSX, PPTX, HTML, and image formats via the Nutrient DWS Processor API. - OCR and Extraction: Extract text and tables from documents, and OCR scanned files in 100+ languages to produce searchable PDFs. - Redaction, Signing, and Forms: Redact PII using presets or regex, add watermarks, apply digital signatures, and fill PDF form fields programmatically. - Use Case: Before sharing a contract PDF externally, redact all social security numbers and email addresses, add a CONFIDENTIAL watermark, and apply a digital signature in one workflow. ## Quick Start Set the NUTRIENT_API_KEY environment variable and ask the agent to convert a DOCX file to PDF or redact sensitive data from a 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 convert DOCX to PDF with an API?▼

Send a multipart POST request to https://api.nutrient.io/build with the DOCX file and an instructions JSON specifying the file part. The Nutrient DWS API returns the converted PDF, and the same pattern works for PDF to DOCX or HTML to PDF.

How to redact PII from PDF documents automatically?▼

Use the redaction action with preset strategies like social-security-number, email-address, or credit-card-number, or supply a custom regex pattern. The API applies permanent redactions and returns the sanitized PDF.

Does the Nutrient DWS API support OCR for scanned documents?▼

Yes, the OCR action converts scanned PDFs into searchable documents and supports over 100 languages via ISO 639-2 codes such as eng, deu, jpn, and chi_sim. Full language names like english also work.

What file formats does Nutrient document processing support?▼

Supported inputs include PDF, DOCX, XLSX, PPTX, DOC, XLS, PPT, ODT, RTF, HTML, and images such as JPG, PNG, TIFF, HEIC, GIF, WebP, and SVG. Outputs include PDF, DOCX, XLSX, and plain text.

Can I fill PDF forms programmatically with this API?▼

Yes, the fillForm action accepts a formFields object mapping field names to values and returns the completed PDF. You supply the form file and a JSON object of field values in the instructions payload.

Is there an MCP server alternative to curl for Nutrient DWS?▼

Yes, the @nutrient-sdk/dws-mcp-server npm package provides native tool integration via MCP. Configure it with your NUTRIENT_DWS_API_KEY and a sandbox working directory path.