← Back to Skills Marketplace
jdrhyne

Nutrient Document Processing (Universal Agent Skill)

by Jonathan Rhyne · GitHub ↗ · v1.1.2 · MIT-0
cross-platform ✓ Security Clean
615
Downloads
0
Stars
2
Active Installs
5
Versions
Install in OpenClaw
/install nutrient-document-processing-universal
Description
Universal (non-OpenClaw) Nutrient DWS document-processing skill for Agent Skills-compatible products. Best for Claude Code, Codex CLI, Gemini CLI, Cursor, Wi...
Usage Guidance
This skill appears to do what it says (document processing via Nutrient) and requires the Nutrient API keys and either curl or npx. Before installing: (1) review the @nutrient-sdk/dws-mcp-server package source on npm/GitHub if you plan to use MCP mode (npx will download and run it), (2) avoid pasting API keys into shared/persistent config files unless you trust the environment — prefer scoped/limited keys or temporary credentials, (3) set SANDBOX_PATH to a restricted directory to limit filesystem exposure, and (4) if you only need direct calls, prefer curl mode to avoid executing remote npm code. If you need higher assurance, ask the publisher for a signed release or include a local vetted binary instead of npx.
Capability Analysis
Type: OpenClaw Skill Name: nutrient-document-processing-universal Version: 1.1.2 The skill is a legitimate integration for the Nutrient (formerly PSPDFKit) Document Processing API. It provides instructions for document conversion, OCR, and redaction using either a standard MCP server (@nutrient-sdk/dws-mcp-server) or direct curl commands to api.nutrient.io. The documentation is transparent about data being sent to the external API and follows standard security practices for agent skills.
Capability Assessment
Purpose & Capability
Name, description, and operations (convert, OCR, redact, extract, sign, etc.) align with the declared requirements: it needs API keys for Nutrient and either curl or npx for direct API or MCP server mode. Requesting an npm package for an MCP server and showing curl examples is coherent with a document-processing integration.
Instruction Scope
SKILL.md stays on-topic (shows curl API calls and MCP server setup). Two practical caveats: (1) the MCP config example embeds NUTRIENT_DWS_API_KEY in a JSON config, which would persist the key in a config file if users paste it there, contradicting the doc's claim that keys aren't stored beyond the session; (2) MCP server uses a SANDBOX_PATH and may read/write files in that directory (expected for processing, but worth noting).
Install Mechanism
Install uses npx to fetch/run @nutrient-sdk/dws-mcp-server from npm at runtime. This is an expected mechanism for an optional MCP server, but npx downloads and executes code from the public npm registry each time — moderate operational risk if you haven't reviewed the package source or don't trust the publisher.
Credentials
Requires two env vars (NUTRIENT_API_KEY for direct API calls and NUTRIENT_DWS_API_KEY for MCP server). Both are plausible for supporting both modes. The SKILL.md's guidance to put keys into persistent MCP config or environment files can cause long-lived storage of secrets — consider using short-lived or scoped keys and avoid pasting secrets into shared config files.
Persistence & Privilege
always:false and standard autonomous invocation behavior are appropriate. The skill does not request system-wide privileges. The only notable persistence vector is the user-populated MCP config (which is outside the skill itself) and the fact that npx will fetch and run code from npm.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install nutrient-document-processing-universal
  3. After installation, invoke the skill by name or use /nutrient-document-processing-universal
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.2
Clarify full DWS capability coverage in listing summary (convert PDF/Office/images, OCR, extraction, PII redaction, watermark, signing, merge/split/reorder, form fill, usage checks).
v1.1.1
Fix scanner metadata mismatch: add top-level homepage/repository and explicit openclaw requires env/bins/install metadata; keep safety boundaries
v1.1.0
Fix suspicious flag: declare required env vars (NUTRIENT_API_KEY, NUTRIENT_DWS_API_KEY), add Safety Boundaries section documenting data handling
v1.0.1
SEO/positioning refresh: explicit non-OpenClaw targeting + MCP/API keyword coverage for document workflows.
v1.0.0
Initial ClawHub release for non-OpenClaw environments (MCP/API mode).
Metadata
Slug nutrient-document-processing-universal
Version 1.1.2
License MIT-0
All-time Installs 3
Active Installs 2
Total Versions 5
Frequently Asked Questions

What is Nutrient Document Processing (Universal Agent Skill)?

Universal (non-OpenClaw) Nutrient DWS document-processing skill for Agent Skills-compatible products. Best for Claude Code, Codex CLI, Gemini CLI, Cursor, Wi... It is an AI Agent Skill for Claude Code / OpenClaw, with 615 downloads so far.

How do I install Nutrient Document Processing (Universal Agent Skill)?

Run "/install nutrient-document-processing-universal" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Nutrient Document Processing (Universal Agent Skill) free?

Yes, Nutrient Document Processing (Universal Agent Skill) is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Nutrient Document Processing (Universal Agent Skill) support?

Nutrient Document Processing (Universal Agent Skill) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Nutrient Document Processing (Universal Agent Skill)?

It is built and maintained by Jonathan Rhyne (@jdrhyne); the current version is v1.1.2.

💬 Comments