Voice Audit — Security skill for Claude Code
Audit the app for voice drift.
How to install Voice Audit
Installs to ~/.claude/commands/frankxai-vibeclubs-voice-audit.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/frankxai/vibeclubs/HEAD/.claude/commands/voice-audit.md -o ~/.claude/commands/frankxai-vibeclubs-voice-audit.md Restart Claude Code, or start a new session, for it to be picked up.
What Voice Audit does
description: Audit the app for voice drift. Fails loud on forbidden vocabulary.
Scan `apps/web` and `apps/extension` for words that violate the voice system (see `VISION.md §voice` and `feedback_voice.md` in memory).
Run:
rg -n -i --type ts --type tsx --type md \
"\\b(community|members|users|rooms|spaces|engage|connect|unlock|empower|revolutionize|disrupt|platform-powered|cloud tier|anchor|stamp|witness|field|residency|operator)\\b" \
apps/web apps/extension README.md
Alternatives in Security
- Brand Strategy — Define or audit a brand — positioning, visual identity system, voice and tone, and brand architecture 309 ★
- Security Audit — Audit de securite complet d'une web app (OWASP Top 10, CWE/CVE, headers, auth, paywall, infra) 80 ★
- Buildable Review — Audit the current prototype against its Buildable app spec, archetype expectations, and local-first guardrails 53 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Audit Agent Friendly
Run the AGENT_READINESS_CHECKLIST.md against a page (or the whole site) and report what fails.
Fenceline
Audit coding-agent session logs for boundary violations after the fact — forbidden commands, escapes outside a
Sound Haptic
Audit or apply One UI sound and haptic: when to fire, semantic vocabulary, silent mode, visible equivalents
Sir
Security runtime for AI coding agents — quiet on normal coding, loud on dangerous transitions.
Delva OS
Build a personal AI operating system in one sitting: CLAUDE.md router, a real knowledge directory, a voice fil
Content Voice Audit
A Claude skill that gives a fast, sourced read on an organization's public voice (website, social, newsletter)
Related Agents
Morty Gate Remediator
Mechanical fixer of toolchain drift (prettier, eslint autofix, type-assertion cleanup, spec-mock alignment). F
Hcs Policy Reviewer
Reviews HCS policy changes (tiers, gateway rules, approval-grant semantics) for duplication, escalation holes,
Cicd Troubleshooter
Layer-6 diagnostic agent for CI/CD failures. Use when: passes locally fails in CI, secrets not injected, wrong