Name: doc-help
Rating: 85.8 (1 reviews)
Author: netwrix

doc-help

Interactive writing assistant for Netwrix documentation. Use when a writer wants hands-on, conversational help: brainstorming structure, drafting a section, editing existing content, incorporating external documents (e.g., .docx files) into existing markdown files, or understanding a style or Vale rule. For fully autonomous tasks (write this entire doc, fix all Vale errors end-to-end), use the tech-writer agent instead.

1.18x

Quality

—

Does it follow best practices?

Impact

69%

1.18x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

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

A well-structured, actionable interactive workflow with strong sequencing and an explicit Vale/Dale validation loop. Its main weaknesses are mild verbosity (some framing and a trigger section that duplicates the description) and a monolithic single-file layout that underuses progressive disclosure.

Suggestions

Trim the Trigger Conditions section or replace it with a one-line pointer to the description, since it largely restates the 'Use when' clause already in the frontmatter.

Cut soft persona prose such as 'Act as a patient, knowledgeable writing partner' in favor of the concrete behavioral rules that already follow it.

Consider moving the per-stage detail (e.g., the Drafting and Editing step-by-step guidance) into a reference file linked from a concise SKILL.md overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows, but the ~206-line body carries soft framing ('patient, knowledgeable writing partner') and a Trigger Conditions section that largely restates the description's 'Use when' clause; mostly efficient but could be tightened.	2 / 3
Actionability	Provides concrete executable commands ('vale <file>', '/dale <file>'), exact intake questions, and concrete before/after and structure-proposal examples, giving specific actionable guidance rather than abstract direction.	3 / 3
Workflow Clarity	Stages 1–4 are clearly sequenced with numbered steps and an explicit validation loop ('Fix all reported errors. Re-run until zero errors remain') plus a final-review checklist, matching the anchor for clear sequence with validation checkpoints.	3 / 3
Progressive Disclosure	Headers and stages are well organized, but the bulk of operational detail lives inline in one ~206-line file with only a single one-level pointer to docs/CLAUDE.md; content that could be split into reference files is kept inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, third-person description that names concrete capabilities, gives explicit 'Use when' triggers with natural keywords, and draws a clear boundary against the autonomous tech-writer agent. It satisfies all four dimensions at the top of the scale.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('brainstorming structure, drafting a section, editing existing content, incorporating external documents (e.g., .docx files) into existing markdown files, or understanding a style or Vale rule'), matching the anchor for multiple specific concrete actions; uses third-person voice so no specificity penalty applies.	3 / 3
Completeness	Explicitly answers both what ('Interactive writing assistant for Netwrix documentation' plus action list) and when via an explicit 'Use when a writer wants...' clause with concrete triggers.	3 / 3
Trigger Term Quality	Covers natural writer phrasing a user would actually say — 'drafting a section', 'editing existing content', '.docx files', 'style or Vale rule' — giving good coverage of common variations rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Carves out a clear interactive/conversational niche and explicitly diverts autonomous work to 'the tech-writer agent instead', making it unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: netwrix/docs
Commit: c229736

Reviewed: 2 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.