nutrient-document-processing

使用 Nutrient DWS API 进行文档处理、转换、OCR、提取、脱敏、签名以及表单填充。支持 PDF、DOCX、XLSX、PPTX、HTML 和图像格式。

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./docs/ja-JP/skills/nutrient-document-processing/SKILL.md

Quality

Content

80%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is an executable, lean API reference with copy-paste curl examples for each operation, but it is a monolithic single file without progressive-disclosure references and lacks explicit validation/error-recovery checkpoints for its irreversible operations.

Suggestions

Add brief validation/error-recovery notes for destructive operations (e.g. how to confirm a redaction or signature applied, and how to retry on API errors).

Split the per-operation API reference into a separate REFERENCE.md and keep SKILL.md as a concise overview with one-level-deep links, to improve progressive disclosure.

Note key environment/error expectations (auth failures, rate limits) so Claude can recover from common failures.

Dimension	Reasoning	Score
Conciseness	The body is lean and reference-style: executable curl commands with brief inline comments and no padding explaining what PDFs or libraries are, so every token earns its place; it is not the level below because there is no unnecessary conceptual explanation.	3 / 3
Actionability	Each operation is given as a fully executable, copy-paste-ready curl command with a complete instructions JSON payload and the auth header, matching the anchor for executable code/commands with specific examples.	3 / 3
Workflow Clarity	Operations are clearly organized (setup, then per-operation sections), but it is a flat reference of independent single calls with no validation checkpoints or error-recovery guidance for irreversible operations like redaction/signing, which the rubric treats as a checkpoint gap rather than a fully sequenced workflow.	2 / 3
Progressive Disclosure	Content is well-sectioned by operation but entirely inline in a single ~160-line file with no bundle/reference files and no one-level-deep navigation; the per-operation API reference could be split into reference files, so it is structured but not progressively disclosed.	2 / 3
	Total	10 / 12 Passed

Description

60%Weight 40%Scale 1-3

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 is specific and action-oriented, naming a broad set of document operations and formats, but it omits any explicit 'Use when...' trigger guidance that would tell Claude when to invoke the skill.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user needs to convert, OCR, redact, sign, or fill PDF/Office documents via an API'.

Include natural user-facing phrasings alongside the API term (e.g. 'PDF conversion', 'scan to searchable text', 'redact sensitive info') to improve trigger-term coverage.

Clarify the when-to-use boundary to distinguish it from local-library document skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "转换、OCR、提取、脱敏、签名以及表单填充" (conversion, OCR, extraction, redaction, signing, form filling) — plus specific supported formats, matching the anchor for enumerating several specific actions.	3 / 3
Completeness	It clearly states what the skill does (the operations and formats), but provides no explicit "when to use it" / trigger guidance, so per the rubric a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant domain terms (OCR, PDF, 表单, 签名) and format names, but they lean toward API/domain jargon and lack common natural phrasings a user would say; no "Use when..." style trigger phrasing is present, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The named API (Nutrient DWS) and specific operation set give it a somewhat distinct niche, but without explicit trigger terms it could still overlap with other document-handling skills, so it sits at the 'somewhat specific' level rather than a clearly distinctive trigger set.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: xu-xiang/everything-claude-code-zh
Path: docs/ja-JP/skills/nutrient-document-processing/SKILL.md
Commit: dfbf946

Reviewed: 29 days ago

Table of Contents

Discovery Implementation Validation

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.