brand-voice
Develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples. Use this skill whenever the user wants to define how a brand sounds, write a voice and tone document, audit existing copy for voice consistency, train a team or AI assistant on brand voice, or refine the personality of brand writing. Triggers on brand voice, voice and tone, tone of voice, writing voice, brand personality, copy voice, voice document, voice guidelines, how should we write, voice training, voice audit. Also triggers when the user has copy that 'feels off' and the underlying issue is voice, even if not stated explicitly.
63
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/brand-voice/SKILL.mdQuality
Discovery
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.
This is a strong skill description that excels across all dimensions. It provides specific concrete actions, comprehensive trigger terms including natural language variations, explicit 'Use when' and 'Triggers on' clauses, and occupies a clearly distinct niche. The description is thorough without being padded, and correctly uses third person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples.' Also mentions auditing copy, training teams/AI, and refining brand writing personality. | 3 / 3 |
Completeness | Clearly answers both 'what' (develop/document brand voice systems covering specific elements) and 'when' (explicit 'Use this skill whenever...' clause with multiple trigger scenarios, plus an explicit 'Triggers on' list). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'brand voice', 'voice and tone', 'tone of voice', 'writing voice', 'brand personality', 'copy voice', 'voice document', 'voice guidelines', 'how should we write', 'voice training', 'voice audit'. Also includes the natural language trigger of copy that 'feels off'. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around brand voice and tone systems specifically. The triggers are distinct and unlikely to conflict with general copywriting or branding skills due to the specificity around voice/tone documentation and auditing. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized instructional skill that provides a solid conceptual framework for brand voice documentation. Its main weaknesses are the lack of concrete, executable examples (especially the paired before/after copy examples it explicitly advocates for) and moderate verbosity in listing standard writing style decisions. The workflow is clear but lacks robust validation criteria and feedback loops.
Suggestions
Add 2-3 concrete paired examples (bad/good copy with annotations) in Layer 4 to demonstrate the format you're asking users to create — the skill explicitly says 'voice is taught through examples, not rules' but then teaches through rules alone.
Trim the vocabulary/grammar section to only include decisions that genuinely distinguish a brand voice, removing standard style choices (Oxford comma, number formatting) that Claude already understands.
Add explicit validation criteria to the stress-test step (e.g., 'Apply the voice doc to write a hero headline, an error message, and a support article — if any feel off-voice, revisit the relevant layer') and include a feedback loop back to specific layers.
Provide the referenced bundle files (voice-document-template.md and voice-frameworks.md) or remove the references to avoid broken links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some content that could be tightened. The 'When to use' / 'When NOT to use' lists, the extensive common attribute pairings, and the long tone shift table add bulk. Some of this is genuinely useful reference material, but sections like the vocabulary/grammar layer list many standard style decisions (Oxford comma, active voice) that Claude already knows about. | 2 / 3 |
Actionability | The skill provides a clear framework and workflow steps, but guidance remains at the instructional/descriptive level rather than executable. There are no concrete code examples, no filled-in template excerpts, and no actual before/after copy examples despite the skill emphasizing their importance. The paired-example library section tells you to create examples but doesn't show a single one. | 2 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced and includes a stress-test validation step (step 6), which is good. However, the validation is vague ('Does it produce on-voice copy? If not, the doc is incomplete') with no concrete criteria for what passing looks like. There's no feedback loop for iterating on layers 1-3 if the stress test fails, and no checkpoint between steps. | 2 / 3 |
Progressive Disclosure | The skill references two external files (voice-document-template.md and voice-frameworks.md) which is good progressive disclosure design. However, no bundle files are provided, so these references are broken. The main document itself is quite long and could benefit from moving the detailed tone shift table and vocabulary/grammar lists into reference files, keeping the SKILL.md as a leaner overview. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rampstackco/claude-skills
- Commit
8e70d03
- 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.