CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

85

1.18x
Quality

88%

Does it follow best practices?

Impact

69%

1.18x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

59%

19%

New Feature Documentation: Audit Trail Export

Drafting workflow with Netwrix structure and linting

Criteria
Without context
With context

CLAUDE.md read step

0%

0%

Context question: what documenting

57%

100%

Context question: primary reader

57%

100%

Context question: reader outcome

57%

100%

Netwrix structure pattern

90%

100%

3-5 sections proposed

0%

0%

Examples for concepts

100%

100%

Vale linting step

0%

30%

Vale re-run until zero errors

0%

0%

Dale linting step

0%

30%

Both linter results reported

0%

37%

Final review step

100%

100%

Section decision explanation

100%

100%

68%

Improve Existing Documentation: Alert Rules

Editing workflow with prioritized analysis and linting

Criteria
Without context
With context

Reads full doc first

100%

100%

Structure issue identified

100%

100%

Clarity issue identified

100%

100%

Voice issue identified

100%

100%

Findings include specific passage

100%

100%

Findings include suggested fix

100%

100%

Edits applied by category

75%

62%

Does not reprint full doc

100%

100%

Vale linting step

0%

0%

Dale linting step

0%

0%

Both linter results reported

0%

0%

Prioritized issue list

87%

100%

80%

14%

Style Guidance: Passive Voice and Vale Violations

Style/Vale question workflow with mode detection

Criteria
Without context
With context

Reads CLAUDE.md first

30%

60%

Mode detected from argument

20%

100%

No 'what do you need?' prompt

100%

100%

Direct answer without hedging

90%

90%

Before example

100%

100%

After example

100%

100%

Before and After paired

100%

100%

Offer to apply rule

0%

20%

Workflow transition mention

0%

12%

Multiple examples

100%

100%

Vale rule named

100%

100%

Repository
netwrix/docs
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.