nutrient-openclaw

Document processing for OpenClaw — convert, extract, OCR, redact, sign, and watermark PDFs and Office documents using the Nutrient DWS API. Use when asked to convert documents (DOCX/XLSX/PPTX to PDF, PDF to images or Office formats), extract text or tables from PDFs, apply OCR to scanned documents, redact sensitive information or PII, add watermarks, or digitally sign documents. Triggers on "convert to PDF", "extract text", "OCR this", "redact PII", "watermark", "sign document", or any document processing request.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

76%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 concise, well-organized plugin README that gets installation right and assumes Claude's intelligence throughout. The main gaps are operational: destructive tools (redact, sign) lack validation steps, and there is no per-tool parameter detail or reference file for the less obvious invocations.

Suggestions

Add a validation checkpoint for destructive operations: after nutrient_redact or nutrient_ai_redact, instruct Claude to verify the redacted output (e.g., re-extract text to confirm no PII remains) before returning it to the user.

Add brief parameter guidance or a short reference for the non-obvious tools — e.g., how watermark text/position is specified, what redaction patterns are supported, and what fields nutrient_sign needs.

Show a short example multi-step flow for common compound requests (e.g., OCR a scanned PDF, then extract tables, then convert to XLSX) so sequencing is explicit rather than implied by the tool table.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a one-line summary, a copy-paste install command, a compact tool table, five brief example prompts, and links. No section explains concepts Claude already knows, and every token earns its place, matching the top anchor.	5 / 5
Actionability	The install command and config YAML are fully executable, and the tool table plus example prompts tell Claude which tool to pick, but no guidance shows how to supply per-tool parameters (e.g., watermark text, signature fields, redaction patterns), leaving minor gaps that keep it below fully-executable coverage of common cases.	4 / 5
Workflow Clarity	The content is organized per-tool rather than as sequenced workflows, and the destructive operations (nutrient_redact, nutrient_ai_redact, nutrient_sign) ship with no verification step — e.g., confirming the redacted output before returning it. Per the rubric's guideline, missing validation for destructive/batch operations caps this dimension at 3 even though tool selection itself is unambiguous.	3 / 5
Progressive Disclosure	Sections are clear and well-labeled (Installation, Available Tools, Example Prompts, Links) with no nested-reference antipattern, but the ~55-line body inlines a 10-row tool table with terse one-line descriptions and offers no one-level-deep reference for per-tool options — a minor organization gap versus the ideal split.	4 / 5
	Total	16 / 20 Passed

Description

96%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.

A strong description: concrete capability enumeration, explicit use-when guidance with natural trigger phrases, and a clearly branded niche. The only weakness is mild conflict risk from generic triggers like "extract text" and the broad "any document processing request" clause.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete actions ("convert, extract, OCR, redact, sign, and watermark") with explicit format mappings ("DOCX/XLSX/PPTX to PDF, PDF to images or Office formats"), matching the comprehensive-coverage anchor. It exceeds the several-actions-with-minor-gaps (4) anchor and contains no vague filler that would pull it lower.	5 / 5
Completeness	Both questions are explicitly answered: the opening sentence and enumerated parentheticals state what the skill does, and "Use when asked to convert documents… extract text or tables… apply OCR… redact… add watermarks, or digitally sign documents" provides explicit trigger guidance with concrete phrases. This matches the top anchor exactly; a 4 would require the 'when' clause to be less explicit, which it is not.	5 / 5
Trigger Term Quality	Natural trigger phrases users would actually say ("convert to PDF", "extract text", "OCR this", "redact PII", "watermark", "sign document") are explicitly listed alongside file extensions (DOCX/XLSX/PPTX), matching the comprehensive-coverage-with-synonyms-and-extensions anchor.	5 / 5
Distinctiveness Conflict Risk	The Nutrient DWS API and the PDFs-and-Office-documents framing give it a mostly distinct niche, but "extract text" and the catch-all "any document processing request" could overlap with a general PDF-processing skill, keeping it below the minimal-conflict (5) anchor while clearly above the broad-overlap (3) anchor.	4 / 5
	Total	19 / 20 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: bap-jorkim/agent-skills-fork-feb-25
Path: skills/nutrient-openclaw/SKILL.md
Commit: f4ed46f

Reviewed: 4 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.