CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is nutrient-document-processing in affaan-m/ECC

SKILL.md
Quality
Evals
Security

Quality

Content

90%Weight 40%Scale 1-5

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

A lean, highly actionable skill that teaches the Nutrient DWS API entirely through complete, executable curl examples with useful inline reference data (presets, language codes, supported formats) and well-placed links for deeper detail. The only weaknesses are the absence of any error-handling or output-verification guidance and a single-file layout that front-loads operations rather than the use cases.

DimensionReasoningScore

Conciseness

The body is almost entirely executable curl commands with no concept explanations, and exhaustive detail (OCR language table, full API docs) is delegated to external links. Every section adds information Claude would not already know.

5 / 5

Actionability

Every operation is a complete, copy-paste-ready curl command with auth header, instructions JSON, and output file, covering the common cases for conversion, extraction, OCR, redaction (preset and regex), watermarking, signing, and form filling.

5 / 5

Workflow Clarity

Setup (export API key) followed by a single unambiguous command per operation is a clear sequence with no destructive or batch steps, since all outputs go to new files. It falls short of 5 only because there is no error-handling or output-verification guidance for API calls that can fail.

4 / 5

Progressive Disclosure

Section-per-operation organization is clear and depth is properly delegated to well-signaled external links (OCR language table, full API docs, npm MCP page). At ~160 lines with all operations inlined in one file and 'When to Use' placed last rather than as an up-front overview, it shows minor organization gaps rather than the fully split structure of the top anchor.

4 / 5

Total

18

/

20

Passed

Description

66%Weight 40%Scale 1-5

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 tool-anchored, listing seven concrete document operations across a broad format range with good natural trigger terms like OCR, redact, and fill. Its main flaw is the complete absence of any 'Use when...' trigger guidance, which caps completeness, alongside verb-only action phrasing and missing common synonyms like Word, Excel, PowerPoint, and forms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when converting documents between formats, OCRing scans, redacting PII, signing contracts, or filling PDF forms.'

Give the action verbs objects and cover the remaining operations: 'extract text and tables', 'add watermarks', 'merge documents'.

Include natural synonyms users say — Word, Excel, PowerPoint, forms, .pdf — alongside the current format list to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

'Process, convert, OCR, extract, redact, sign, and fill documents' lists seven concrete action verbs plus the tool and formats, but the verbs lack objects ('extract' never says text or tables) and watermark/merge coverage from the body is missing, fitting 'several specific actions; minor gaps' better than the comprehensive top anchor.

4 / 5

Completeness

The 'what' is clear (seven named actions via the Nutrient DWS API across six format families), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; it is not 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Strong natural terms ('OCR', 'redact', 'convert', 'sign', 'fill', 'PDFs', 'DOCX', 'XLSX', 'PPTX', 'HTML', 'images') with file extensions covered. Not 5 because common synonyms users would actually say ('Word', 'Excel', 'PowerPoint', 'forms', 'watermark') are absent.

4 / 5

Distinctiveness Conflict Risk

'using the Nutrient DWS API' establishes a clear niche, but 'Works with PDFs, DOCX, XLSX, PPTX, HTML, and images' creates minor overlap risk with dedicated per-format document skills, matching 'mostly distinct; minor overlap risk' rather than the minimal-conflict top anchor.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

valeriibeck-star/claude-skills

Path

skills/nutrient-document-processing/SKILL.md

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.