jbvc/nutrient-document-processing
Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images.
76
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description excels at listing specific, concrete actions and covers a wide range of natural trigger terms across multiple document formats. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill over others. The broad scope across many file types also introduces some overlap risk with more specialized document skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to convert, OCR, redact, sign, or fill documents, or mentions the Nutrient DWS API.'
Consider clarifying the skill's niche relative to other document tools, e.g., 'Use this skill specifically for server-side document processing via the Nutrient DWS API rather than local file manipulation.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: process, convert, OCR, extract, redact, sign, and fill documents. Also names the specific API (Nutrient DWS API) and supported file formats. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions and file formats, but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this dimension at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'OCR', 'convert', 'extract', 'redact', 'sign', 'fill', 'PDFs', 'DOCX', 'XLSX', 'PPTX', 'HTML', 'images'. These cover a wide range of natural user requests related to document processing. | 3 / 3 |
Distinctiveness Conflict Risk | The mention of 'Nutrient DWS API' adds specificity, but the broad range of document types (PDFs, DOCX, XLSX, PPTX, HTML, images) and actions (convert, extract, process) could overlap with other document-handling or PDF-specific skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable API reference skill with excellent concrete examples for each operation. Its main weaknesses are the lack of error handling/validation guidance (especially for destructive operations like redaction) and some verbosity from repetitive curl boilerplate and sections that explain things Claude can infer. The structure is clear but could benefit from condensing repeated patterns.
Suggestions
Add error handling guidance: check HTTP status codes, handle rate limits, and verify output file integrity—especially for redaction and signing operations.
Reduce curl boilerplate repetition by defining a common pattern once (base URL, auth header) and showing only the varying parts (instructions JSON, file parameters) for each operation.
Remove the 'When to Use' section—Claude can infer appropriate use cases from the operations listed above it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete examples, but includes some unnecessary content like the 'When to Use' section (Claude can infer appropriate use cases) and the full list of supported input formats. The curl examples are repetitive in their boilerplate (Authorization header, URL) which could be condensed. | 2 / 3 |
Actionability | Every operation includes fully executable curl commands that are copy-paste ready with proper variable substitution. The instructions JSON format is shown concretely for each use case, and the MCP server config is a complete, usable JSON block. | 3 / 3 |
Workflow Clarity | Each operation is a single API call, so multi-step workflows aren't deeply needed. However, there's no mention of error handling, response status checking, or validation of outputs. For operations like redaction (destructive) and digital signing, there should be verification steps (e.g., checking the response code, validating the output). | 2 / 3 |
Progressive Disclosure | The skill has good section organization and links to external docs, but the content is somewhat monolithic—all operations are inline with full curl examples. The redaction presets list and supported formats could be referenced externally. The links section at the end provides good navigation to deeper resources. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents