tdg-personal/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.
75
75%
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 includes many natural trigger terms across multiple document formats. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude distinguish when to select this skill over other document-processing skills. The broad scope across many file types also introduces some conflict risk with more specialized 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.'
Clarify the skill's niche relative to other document tools by emphasizing what makes Nutrient DWS distinct (e.g., server-side API processing, batch operations, or specific capabilities not available in other document skills).
| 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 guidelines. | 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 skill with excellent concrete examples for every supported operation. Its main weaknesses are the lack of error handling/validation guidance (especially important for redaction and signing operations) and the length of inline content that could be better organized through progressive disclosure. The repetitive curl boilerplate across examples also inflates token usage.
Suggestions
Add error handling guidance: check HTTP status codes, handle common errors (401 auth, 413 file too large, 429 rate limit), and verify output file integrity—especially for destructive operations like redaction.
Extract the detailed per-operation curl examples into a separate OPERATIONS.md reference file, keeping SKILL.md as a concise overview with one representative example and links to the full catalog.
Reduce boilerplate repetition by defining the common curl pattern once (URL, auth header, multipart structure) and showing only the varying `instructions` JSON for each operation.
| 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 extensive list of supported input formats. The curl examples are repetitive in their boilerplate (Authorization header, URL) which could be condensed with a template pattern. | 2 / 3 |
Actionability | Every operation includes fully executable curl commands with realistic parameters that are copy-paste ready. The instructions JSON format is demonstrated concretely for each use case, and the MCP server config is a complete JSON block. No pseudocode or vague descriptions. | 3 / 3 |
Workflow Clarity | Each operation is presented as a standalone command rather than a multi-step workflow. There are no validation checkpoints—for example, no guidance on checking API response codes, handling errors, verifying output files, or dealing with rate limits. For operations like redaction (destructive) or digital signing, missing verification steps is a notable gap. | 2 / 3 |
Progressive Disclosure | The skill has good section organization with clear headers, and links to external docs at the bottom. However, the inline content is quite long (~150 lines of curl examples) and could benefit from splitting detailed operation examples into a separate reference file, keeping SKILL.md as a concise overview with one or two examples and pointers to the full catalog. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents