Skill

document-processor-api

Executes document processing tasks including convert, merge, split, OCR, extract text/tables/key-value pairs, watermark, redact, sign, optimize, protect, reorder via nutrient-dws Python client and uv run scripts. Builds custom multi-step pipelines.

Python

automation

cli-tools

npx claudepluginhub pspdfkit-labs/nutrient-skills --plugin nutrient-dws

Tool Access

This skill uses the workspace's default tool permissions.

Preview

All paths below are relative to this skill's directory (the directory containing `scripts/`, `assets/`, and `references/`).

Supporting Assets

SKILL.md

Similar Skills

nutrient-document-processing

154

Process documents with Nutrient API: convert formats (PDF, DOCX, XLSX, images), OCR scans (100+ languages), extract text/tables, redact PII, sign, fill forms.

awesome-claude-notes

nutrient-document-processing

179.0k

Convert formats, OCR scans, extract text/tables, redact PII, sign, and fill forms using Nutrient DWS API. Handles PDF, DOCX, XLSX, PPTX, HTML, images.

ecc

nutrient-document-processing

Processes documents via Nutrient DWS API: convert formats (PDF/DOCX/XLSX/PPTX/HTML/images), OCR, extract text/tables, redact PII, sign, fill forms.

everything-claude-code

Stats

Parent Repo Stars7

Parent Repo Forks0

Last CommitMar 30, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Nutrient Document Processor API

Quick Start

All paths below are relative to this skill's directory (the directory containing scripts/, assets/, and references/).

Export the API key before running scripts:
- export NUTRIENT_DWS_API_KEY="nutr_sk_..."
Run task scripts with uv run from the plugin root. The nutrient-dws package is fetched automatically on first use.

Task Scripts

Use one script per operation.

Convert formats: scripts/convert.py
Merge files: scripts/merge.py
Split by ranges: scripts/split.py
OCR documents: scripts/ocr.py
Extract text: scripts/extract-text.py
Extract tables: scripts/extract-table.py
Extract key-value pairs: scripts/extract-key-value-pairs.py
Add text watermark: scripts/watermark-text.py
AI redaction: scripts/redact-ai.py
Rotate pages: scripts/rotate.py
Sign PDF: scripts/sign.py
Optimize PDF: scripts/optimize.py
Password protect PDF: scripts/password-protect.py
Add blank pages: scripts/add-pages.py
Delete pages: scripts/delete-pages.py
Duplicate/reorder pages: scripts/duplicate-pages.py

Check exact arguments with uv run <script> --help.

Custom Pipelines

When the user asks for a workflow not covered by the scripts above, create a new script rather than forcing ad hoc one-off commands.

Start from assets/templates/custom-workflow-template.py.
Save the new script in scripts/ with a task-specific name (for example scripts/redact-and-watermark.py).
Keep API usage on nutrient-dws.
Prefer direct methods (client.convert, client.merge, etc.) for single-step tasks.
Use client.workflow() and BuildActions for multi-step tasks.
Keep every custom script CLI-driven (--input, --out, explicit options), deterministic, and runnable end-to-end.
Run the script with sample input to verify behavior before finalizing.

Implementation Rules

Fail fast when required arguments are missing.
Require local input for operations that do not support URL input (sign).
Write outputs to explicit paths and print created files.
Do not log secrets.
If the package import fails, install latest with uv add nutrient-dws.

References

Script matrix and method mapping: references/script-catalog.md
Custom pipeline patterns: references/custom-pipeline-guidelines.md