nutrient-document-processing
使用Nutrient DWS API处理、转换、OCR识别、提取、编辑、签名和填写文档。支持PDF、DOCX、XLSX、PPTX、HTML和图像格式。
86
66%
Does it follow best practices?
Impact
100%
1.49xAverage score across 6 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/zh-CN/skills/nutrient-document-processing/SKILL.mdQuality
Discovery
60%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 capabilities and supported formats, providing a comprehensive view of what the skill does. However, it lacks an explicit 'Use when...' clause, which is critical for Claude to know when to select this skill over others. The trigger terms are adequate but lean toward technical language rather than natural user phrasing.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to convert, edit, sign, or extract content from documents, or when OCR is needed for scanned documents or images.'
Include more natural user-facing trigger terms and variations, such as 'scan documents', 'convert Word to PDF', 'fill out forms', 'e-sign', 'extract text from images', to improve matching with how users naturally phrase requests.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 处理 (process), 转换 (convert), OCR识别 (OCR recognition), 提取 (extract), 编辑 (edit), 签名 (sign), and 填写 (fill) documents. Also specifies supported formats (PDF, DOCX, XLSX, PPTX, HTML, images). | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions and supported formats, but lacks an explicit 'Use when...' clause or equivalent trigger guidance explaining when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like PDF, DOCX, XLSX, PPTX, HTML, OCR, and document-related action terms. However, it misses common user-facing variations and natural language triggers (e.g., 'scan documents', 'convert to PDF', 'fill forms', '.pdf files'). The terms are somewhat technical (e.g., 'Nutrient DWS API') rather than user-natural. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Nutrient DWS API' and the broad range of document formats (PDF, DOCX, XLSX, PPTX, HTML, images) makes it somewhat distinctive, but the wide scope of supported formats and actions could overlap with other document-processing skills. It covers so many formats that it could conflict with format-specific skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
72%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 API reference skill with excellent actionability—every operation has executable curl examples. The main weaknesses are the lack of error handling/validation guidance (important for destructive operations like redaction) and some verbosity in the use cases section and repeated curl boilerplate. The progressive disclosure and organization are strong.
Suggestions
Add a brief error handling section showing how to check HTTP response codes and handle common failures (e.g., invalid API key, unsupported format).
Remove or significantly condense the '使用场景' section since the operations themselves already make the use cases self-evident.
Add a validation note for destructive operations like redaction (e.g., 'verify redacted output before deleting originals').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete curl examples, but includes some unnecessary content like the '使用场景' (use cases) section which restates what's already obvious from the operations, and the supported formats list could be more compact. The repetitive curl boilerplate across examples adds bulk. | 2 / 3 |
Actionability | Every operation includes fully executable curl commands that are copy-paste ready with proper authentication headers, file parameters, and JSON instructions. The examples cover all major use cases with concrete, working commands. | 3 / 3 |
Workflow Clarity | Each operation is presented as a single API call which is clear, but there's no guidance on error handling, validation of responses (checking HTTP status codes), or what to do when operations fail. For operations like redaction (destructive) and digital signing, missing verification steps is a gap. | 2 / 3 |
Progressive Disclosure | The skill is well-structured with clear sections, provides a concise overview of each operation inline, and appropriately links out to full API documentation, the OCR language table, the API playground, and the MCP server npm package for deeper exploration. | 3 / 3 |
Total | 10 / 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 | |
- Repository
- affaan-m/everything-claude-code
- Commit
5df943e
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.