home / skills / openclaw / skills / nutrient-document-processing

nutrient-document-processing skill

/skills/jdrhyne/nutrient-document-processing

This skill processes documents in OpenClaw by converting formats, OCR, redacting PII, watermarking, and signing through the Nutrient API.

npx playbooks add skill openclaw/skills --skill nutrient-document-processing

Review the files below or copy the command above to add this skill to your agents.

Files (2)

SKILL.md

2.3 KB

---
name: nutrient-openclaw
description: Document processing for OpenClaw — convert, extract, OCR, redact, sign, and watermark PDFs and Office documents using the Nutrient DWS API. Use when asked to convert documents (DOCX/XLSX/PPTX to PDF, PDF to images or Office formats), extract text or tables from PDFs, apply OCR to scanned documents, redact sensitive information or PII, add watermarks, or digitally sign documents. Triggers on "convert to PDF", "extract text", "OCR this", "redact PII", "watermark", "sign document", or any document processing request.
---

# Nutrient Document Processing

Process documents directly in OpenClaw conversations — convert formats, extract text, apply OCR, redact PII, add signatures, and watermark files through natural language.

## Installation

```bash
openclaw plugins install @nutrient-sdk/nutrient-openclaw
```

Configure your API key:

```yaml
plugins:
  entries:
    nutrient-openclaw:
      config:
        apiKey: "your-api-key-here"
```

Get an API key at [nutrient.io/api](https://www.nutrient.io/api/)

## Available Tools

| Tool | Description |
|------|-------------|
| `nutrient_convert_to_pdf` | Convert DOCX, XLSX, PPTX, HTML, or images to PDF |
| `nutrient_convert_to_image` | Render PDF pages as PNG, JPEG, or WebP |
| `nutrient_convert_to_office` | Convert PDF to DOCX, XLSX, or PPTX |
| `nutrient_extract_text` | Extract text, tables, or key-value pairs |
| `nutrient_ocr` | Apply OCR to scanned PDFs or images |
| `nutrient_watermark` | Add text or image watermarks |
| `nutrient_redact` | Redact via patterns (SSN, email, phone) |
| `nutrient_ai_redact` | AI-powered PII detection and redaction |
| `nutrient_sign` | Digitally sign PDF documents |
| `nutrient_check_credits` | Check API credit balance and usage |

## Example Prompts

**Convert:** "Convert this Word doc to PDF"

**Extract:** "Extract all text from this scanned receipt" / "Pull tables from this PDF"

**Redact:** "Redact all PII from this document" / "Remove email addresses and phone numbers"

**Watermark:** "Add a CONFIDENTIAL watermark to this PDF"

**Sign:** "Sign this contract as Jonathan Rhyne"

## Links

- [npm package](https://www.npmjs.com/package/@nutrient-sdk/nutrient-openclaw)
- [GitHub](https://github.com/PSPDFKit-labs/nutrient-openclaw)
- [Nutrient API](https://www.nutrient.io/)

Overview

This skill processes documents inside OpenClaw conversations using the Nutrient DWS API. It converts between Office and PDF formats, extracts text and tables, runs OCR on scans, redacts PII, applies watermarks, and digitally signs files. Use natural-language commands like “convert to PDF,” “extract text,” or “redact PII” to trigger the appropriate action.

How this skill works

The skill sends files to the Nutrient API and invokes specific endpoints for conversion, extraction, OCR, redaction, watermarking, and signing. Results return as downloadable files, extracted text/table data, or redaction reports. You can check API credit usage and adjust jobs (page ranges, output formats, watermark appearance, or redaction patterns) via the request parameters.

When to use it

Convert DOCX/XLSX/PPTX/HTML/images to PDF or render PDF pages as images
Extract searchable text, tables, or key-value pairs from PDFs or Office files
Perform OCR on scanned PDFs and images to make them searchable
Redact sensitive information or automatically detect PII with AI-powered redaction
Add text or image watermarks to PDFs for branding or confidentiality
Digitally sign contracts or official PDFs and verify signature status

Best practices

Specify exact pages or page ranges when converting or extracting to reduce processing time and credits
Provide sample output preferences (format, image resolution, OCR language) in the prompt
Use AI-powered redaction for broad PII detection and pattern-based redaction for known fields like SSNs or emails
Test watermarks and signatures on a sample document before batch processing
Monitor credit usage with the check-credits tool and break large jobs into smaller batches if needed

Example use cases

Convert a 20-page PPTX to a print-ready PDF with slide notes and hidden slides removed
Extract tables from an invoice PDF into CSV or Excel for accounting ingestion
OCR a scanned receipt folder and return searchable PDFs plus a consolidated text transcript
Redact all emails, phone numbers, and SSNs from an employee onboarding packet before sharing externally
Apply a diagonal CONFIDENTIAL watermark and digitally sign an NDA for secure distribution

FAQ

Can the skill handle password-protected PDFs?

Yes — include the PDF password in your request; otherwise the service cannot open encrypted files.

How accurate is the OCR and AI redaction?

OCR accuracy depends on scan quality and language; AI redaction catches common PII but verify critical redactions manually before release.

What output formats are supported for conversions?

You can convert to PDF, PNG/JPEG/WebP images, and Office formats DOCX/XLSX/PPTX depending on the tool used.