// Evaluates documentation against the team's brand guidelines. Use when reviewing docs for tone, terminology, sentence structure, and phrasing consistency.
Evaluates whether documentation sections have substantive content. Use when checking whether planned sections are complete, thin, placeholders, or missing.
Evaluates grammar, spelling, and formatting in design systems' documentation. Use when checking mechanics like spelling, punctuation, heading hierarchy, and list formatting.
Scores and evaluates documentation readability using Flesch-Kincaid metrics and qualitative analysis. Use when reviewing docs for sentence length, passive voice, jargon, and reading level.
Evaluates documentation against the team's brand guidelines. Use when reviewing docs for tone, terminology, sentence structure, and phrasing consistency.
Evaluates whether documentation sections have substantive content. Use when checking whether planned sections are complete, thin, placeholders, or missing.
Evaluates grammar, spelling, and formatting in design systems' documentation. Use when checking mechanics like spelling, punctuation, heading hierarchy, and list formatting.
| name | brand-voice-evaluation |
| description | Evaluates documentation against the team's brand guidelines. Use when reviewing docs for tone, terminology, sentence structure, and phrasing consistency. |
Hard technique for evaluating documentation against a team's brand voice guidelines.
dockit ships with a built-in style guide at @.agents/dockit/references/style-guide.md. This is the source of truth for all voice evaluation — always read it before evaluating any content.
Read the entire style guide before evaluating any content. Build a mental checklist from it.
Even without a style guide, the document should be internally consistent:
<output_format>
Each finding should include:
[severity] Section: {section name} (line ~{number})
Issue: {description of the voice issue}
Current: "{the current text}"
Suggested: "{the suggested alternative}"
Rule: "{the style guide rule this relates to, if applicable}"
Group findings by severity: violations first, then deviations, then suggestions.
End with a summary:
Voice Review Summary:
Violations: {count}
Deviations: {count}
Suggestions: {count}
Overall: {brief assessment — e.g., "Strong voice alignment with a few terminology inconsistencies"}
</output_format>