razbakov/website-voice-audit
skills/website-voice-audit/SKILL.md
Use when reviewing a website's UI copy, content, and meta for brand voice consistency. Triggers include launching a new site, rebranding, noticing inconsistent tone across pages, or preparing content for SEO. Checks nav, CTAs, author bios, meta descriptions, blog posts, project descriptions, config files, and locale files against brand voice guidelines.
$ install --global
skillsauthnpx skillsauth add razbakov/skills website-voice-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 18, 2026, 5:07 AM10.8s1 file scanned
SKILL.md
- name:
- website-voice-audit
- description:
- Use when reviewing a website's UI copy, content, and meta for brand voice consistency. Triggers include launching a new site, rebranding, noticing inconsistent tone across pages, or preparing content for SEO. Checks nav, CTAs, author bios, meta descriptions, blog posts, project descriptions, config files, and locale files against brand voice guidelines.
Website Voice Audit
Systematically audit every text surface of a website against its brand voice guidelines. Produce a report of violations with concrete fixes.
When to Use
- Before a site launch or rebrand
- When copy feels inconsistent across pages
- After migrating content from another site/template
- When blog posts span different time periods (voice drift)
- When locale files were translated without voice review
Audit Checklist
1. Read Brand Voice Guidelines First
Find the voice/tone definition (usually in CLAUDE.md, brand docs, or style guide). Extract:
- Tone keywords (e.g., "direct, reflective, authentic")
- Words to use (e.g., "build, ship, validate")
- Words to avoid (e.g., "synergy, leverage, empower, impactful")
- Writing style (first person? casual? process-oriented?)
- CTA style (e.g., "Let's talk" > "Schedule a consultation")
2. Audit Every Text Surface
Check each surface against the guidelines. Read the actual files, don't guess.
| Surface | Where to find | Common violations |
|---|---|---|
| Site config | config.json, nuxt.config.ts | Generic description, dead marketing copy |
| Navigation | Nav components, i18n files | Corporate labels ("Schedule a Consultation") |
| Homepage | Hero, subtitle, CTAs | Template filler, banned words |
| About page | Bio, section headings, CTAs | LinkedIn-style corporate bio |
| Blog subtitles | i18n files, page components | Generic ("Sharing insights on topics I'm passionate about") |
| Author bio | Blog post template | Mismatch with personal voice |
| CTA fallbacks | i18n files | "Ready to Get Started?" / "Take the next step" |
| Blog posts | Content markdown files | Voice drift across years, emoji abuse, marketing hype |
| Project descriptions | Content markdown files | Third-person pitch deck voice vs first-person |
| Meta descriptions | useSeoMeta, i18n files | Generic or missing |
| Footer | App/layout component | Boilerplate |
| Empty states | Page components | Dev-facing text in production |
| All locale files | i18n directory | Translations that don't match voice |
3. Classify Violations
For each violation, note:
- File and line — exact location
- Current text — what it says now
- Problem — why it violates the voice (reference specific guideline)
- Fix — concrete replacement text
4. Prioritize
| Priority | Description | |---|---| | P0 | Uses explicitly banned words | | P1 | Dead/template copy visible to users | | P2 | Inconsistent with voice but not terrible | | P3 | Could be better but functional |
Report Format
## Voice Audit: [site name]
### Voice Guidelines Summary
- Tone: ...
- Words to use: ...
- Words to avoid: ...
### Violations Found
| Priority | Location | Current | Problem | Fix |
|---|---|---|---|---|
### Blog Post Voice Assessment
| Post | Voice match | Issues |
|---|---|---|
### Recommendations
1. ...
Blog Post Rewrites
When rewriting blog posts to match voice:
- Keep: frontmatter (dates, images, links, tags, CTAs), core ideas, code blocks, internal links
- Remove: emojis in headers, marketing hype, exclamation-mark emphasis, "Perfect For" audience sections, "Ready to revolutionize?" CTAs
- Rewrite: titles, descriptions, section structure, all body copy
- Dispatch parallel agents for independent post rewrites (one agent per post)
- Spot-check each rewrite: grep for emojis, verify no banned words, read opening and closing paragraphs
Common Mistakes
- Auditing only English and forgetting locale files
- Fixing UI text but leaving meta descriptions in old voice
- Rewriting blog posts without preserving frontmatter links and CTAs
- Not checking config files for dead/unused marketing copy
- Over-correcting: CV pages should stay professional, not match casual blog voice
Related Skills
razbakov/skills/handoff
tools
VerifiedTrustedCommunity
--- name: handoff description: Get an agent past a browser/UI wall it can't (or must not) cross on its own — a login-gated dashboard, a CAPTCHA, a 2FA prompt, an API that keeps rejecting the write, or an irreversible click that policy says a human must make. This skill is an ESCALATION LADDER, not a first move: it tells you to try the automated browser surfaces FIRST (Chrome-in-Claude, computer-use, an autonomous browser sub-agent) and only fall back to the Handoff app — a wrapper browser that h
3SKILL.mdUpdated Jul 17, 2026
razbakov/summarize-youtube
documentation
VerifiedTrustedCommunity
Summarize one or more YouTube videos from their links. Use this whenever the user pastes a youtube.com or youtu.be URL (or several) and wants to know what it's about — phrasings like "summarize to telegram", "tldr these videos", "what do these say", "summary of this talk", or just dropping links with no instruction at all. Fetches each video's real transcript via yt-dlp (not the page text, which never contains the transcript), cleans the captions, and writes a per-video summary. Default delivery is Telegram; honor any other surface the user names ("to my notes", "just here in chat", "email it"). Trigger even when the user only pastes bare links — bare YouTube links almost always mean "tell me what's in these".
3SKILL.mdUpdated Jun 15, 2026
razbakov/skills/daily-digest
data-ai
VerifiedTrustedCommunity
Daily Digest — Chief-of-Staff role consolidates the six top-managers into one Telegram message to the Commander, instead of six. Implements the protocol from agent-proactivity.md.
3SKILL.mdUpdated Jun 15, 2026
razbakov/instagram-launch-grid
development
VerifiedTrustedCommunity
Seed a new or empty Instagram account with a 9-post grid (3×3) so the profile looks established the moment a new visitor lands. Designed for festivals, new businesses, product launches, conferences, communities — any time an empty IG profile would hurt conversion from external traffic (QR scans, flyer drops, cross-promo). Generates assets via /image-from-gemini (per content-publishing rules — never HTML), writes captions with hashtag sets, and outputs a posting order + cadence plan. Trigger generously: phrases like '9 posts for instagram', 'fill my IG', 'starter grid', 'launch grid', 'instagram seed', '9-post grid', 'IG account not to look empty', 'first instagram posts', 'feed bootstrap', '3x3 grid', 'instagram launch content'. Even if the user mentions only one piece (just the images, just the captions, just the order), use this skill — the grid only works as an integrated bundle.
3SKILL.mdUpdated May 21, 2026