Voice Check — AI skill for Claude Code
Scans a draft for AI tells against config/voice.md.
How to install Voice Check
Installs to ~/.claude/commands/enderlopez2307-dotcom-career-coach-os-voice-check.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/enderlopez2307-dotcom/career-coach-os/HEAD/.claude/commands/voice-check.md -o ~/.claude/commands/enderlopez2307-dotcom-career-coach-os-voice-check.md Restart Claude Code, or start a new session, for it to be picked up.
What Voice Check does
description: Scans a draft for AI tells against config/voice.md. Returns PASS, REWRITE (with the fix), or DO NOT SEND.
**Agent:** `coach` · runs in this session or inline within another command.
Task
Check the draft against `config/voice.md`'s hard rules and against the general tells: em dashes, hedging openers ("Honestly," "To be honest"), formulaic closers ("At the end of the day"), rule-of-three lists, balanced parallel clauses, generic flattery, slogans, self-positioning. Check
Alternatives in AI
- PRD: Agent Builder — Create Your Own Sub-Agent — Your ecosystem, your rules 1.9k ★
- Academic Humanizer — Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying clai 1.1k ★
- PromptEnhance — Rewrite the following prompt to be clearer, more specific, and more effective for an AI assistant 250 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Slopbuster
Strips the AI tells out of prose, code, and academic writing. 152 patterns from real AI-vs-human analysis, two
Humanizer Claude Skill
Agent skill that removes AI tells from prose and scores how human it reads. Markdown-safe CLI: --check scores
Validate Voice
Run the Pass-C checks on generated output (facts, AI tells, repetition)
Prompt Optimize
One-shot prompt rewrite — diagnose a rough draft, steer you to the right workflow archetype (linear, TDD, suba
AI Tells Validator
Detect and rewrite AI-sounding text. Grounded in the live Wikipedia 'Signs of AI writing' catalog.
Ast Grep Skill
LLM-neutral skill for AST-aware search and rewrite across 25 languages, wrapping ast-grep (sg) with offline pa
Related Agents
Resume Judge
Scores a resume or letter draft against the anchored rubric in templates/rubric-resume.md and returns per-dime
LinkedIn Post Reviewer
Reviews a LinkedIn post draft against the quality checklist. Grades A/B/C/D. Returns specific violations with
Draft Reviewer
Review AND FIX any draft for AI slop, writing craft, and voice consistency. Runs three quality checks, then ap