Stress-Test Your Brand Voice Before Publishing
Catch tone drift and inconsistency across channels with a systematic audit prompt
Your Instagram captions sound playful while your emails feel corporate, and your Arabic posts carry a formality your English never intended. Every writer interprets your brand voice guide differently, and you only notice the mismatch after content goes live.
That is the gap this drop closes. It is a content & writing skill built for Claude, and it takes about ten minutes to set up the first time. After that it runs in under a minute.
Who should use it
Marketing managers and content leads who already have brand guidelines but notice their voice sounds different across platforms, campaigns or writers
How it works
The skill file does five things, in this order.
1. Collect real samples from every channel. Pull three recent pieces from each platform: website, social, email, support responses, ads in both languages.
2. Run the voice consistency audit. Feed all samples into the audit prompt below and ask Claude to score consistency, flag deviations and identify patterns.
3. Map the gap between stated and actual voice. Compare Claude's findings against your official brand voice guide to see where reality diverges from intent.
4. Identify high-risk divergence points. Look for mismatches that damage trust: formal Arabic with casual English, or playful ads leading to stiff landing pages.
5. Create channel-specific guard rails. Build mini-checklists for each platform that translate your brand voice into concrete dos and don'ts writers can follow.
What comes back
A diagnostic report showing exactly where your brand voice breaks down, plus concrete fixes for each channel and language
The mistake to avoid
Run this audit quarterly, not once. Brand voice drift is gradual, and new team members or platform features introduce fresh inconsistencies over time.
Running it
Save this as SKILL.md inside a folder named after the skill, then drop the folder into your Claude Code skills directory or upload it to a Claude Project. Claude reads the frontmatter to decide when the skill applies, so keep the description line intact. For a one-off run, paste the prompt block directly.
Where this fits
On its own, one skill saves an hour a week. The compounding happens when three or four of them run in sequence on the same input, the same transcript that produces a scope of work also produces the follow-up email and the project brief. That is the point at which it stops being a prompt and starts being an internal tool. If you want that wired into the systems your team already uses, that is the work 67 Digital does.
In the file
You are a brand voice auditor. I will provide multiple content samples from different channels and languages.
My stated brand voice principles are:
{brand_voice_guidelines}
Here are content samples organized by channel:
Website: {website_samples}
Social media: {social_samples}
Email: {email_samples}
Customer support: {support_samples}
Advertising: {ad_samples}
For each sample:
1. Score voice consistency against the stated guidelines on a scale of 1-10
2. Identify specific phrases or patterns that deviate from the stated voice
3. Note any differences in tone between English and Arabic versions
4. Flag jarring transitions when a customer moves from one channel to another
Then provide:
- An overall consistency score across all channels
- The three most significant voice breaks and their business impact
- Patterns showing which channels or languages drift most
- Concrete rewrites of the worst offenders
- Specific guardrails for each channel to prevent future drift
Format your analysis as a table for easy sharing with the team.