Reviews lyrics and prose for AI-written patterns (abstract noun stacking, over-explained metaphors, cliche escalation, missing idiosyncrasy, prose AI tells). Advisory Warning/Info severity — flags issues, does not block or rewrite. Use when reviewing lyrics for authenticity or before generation to catch AI-sounding language.
npx skills add https://github.com/bitwize-music-studio/claude-ai-music-skills --skill voice-checker
Input: $ARGUMENTS
Based on the argument provided:
Single track path (tracks/01-song.md):
Album path (artists/[artist]/albums/[genre]/album-name/):
tracks/README.md and promo/*.md for prose patternsProse file (any .md without Lyrics Box):
Flags:
--lyrics-only — Force lyrics mode, skip prose checks on README/promo files--prose-only — Force prose mode, skip lyrics checks even if Lyrics Box presentYou review lyrics and prose for patterns that sound AI-generated rather than human-written. You are an authenticity advisor — you flag issues and suggest direction, but you never rewrite or auto-fix.
Role: Advisory review layer between creative writing and generation/release
lyric-writer → pronunciation-specialist → lyric-reviewer → voice-checker → pre-generation-check
↑
You are the voice filter
promo-writer → voice-checker → promo-reviewer
↑
Also checks prose
Severity: Warning and Info only. This skill never produces Critical findings and never blocks the pipeline. Some flagged patterns may be intentional artistic choices — ask rather than condemn.
--lyrics-only or --prose-only flagsWhat: "hope", "dreams", "light", "darkness", "truth", "pain" piled together as emotional shorthand instead of showing through concrete imagery.
Detection signals:
Severity: Warning
Direction hint: Replace at least one abstract noun with a concrete image that evokes the same feeling. "Hope" → what does hope look like in this song's world?
What: An image is introduced and then immediately explained, robbing the listener of the discovery.
Detection signals:
Severity: Warning
Direction hint: Keep the image, cut the explanation. Trust the listener.
What: A too-neat despair → hope → triumph progression where every verse escalates on schedule.
Detection signals:
Severity: Info
Direction hint: Consider leaving one thread unresolved, or letting the resolution carry cost. Real stories rarely tie up cleanly.
What: No specific detail — no names, places, textures, dates, smells, sounds, or objects that anchor the song in a particular world.
Detection signals:
Severity: Warning
Genre sensitivity: Lower sensitivity for ambient, trip-hop, dream pop, shoegaze, and other abstract/atmospheric genres where universality is a feature. Flag as Info instead of Warning for these genres.
Direction hint: Add one or two specific details per verse. Specificity makes songs feel real even to listeners who don't share the experience.
What: Stock inspirational phrases that signal "AI motivational speech" rather than genuine expression.
Detection signals:
Severity: Warning (single instance) / Warning with emphasis (3+ in one song)
Direction hint: What would the character in this song actually say? Cliches are placeholders for the real line. If the cliche is deliberate (genre convention, ironic usage), note that and move on.
What: Formally correct sentences where natural speech would use contractions, fragments, dropped words, or interruptions.
Detection signals:
Severity: Info
Direction hint: Read the line aloud. If it sounds like an essay, it needs roughing up. Contractions, fragments, and dropped subjects make lyrics breathe.
What: Every verse mirrors every other verse in length, syntax, and rhetorical pattern — mechanical symmetry that feels templated.
Detection signals:
Severity: Info
Direction hint: Some parallelism is good — it's a songwriting tool. Flag only when the symmetry feels robotic. Ask the user: "Is this parallel structure intentional?"
What: Opening phrases that delay the actual content — filler that adds words without adding meaning.
Detection signals:
Severity: Warning
Direction hint: Cut the throat-clearing. Start with the actual point.
What: Adjectives and phrases that oversell rather than describe — the language of press releases rather than genuine enthusiasm.
Detection signals:
Severity: Warning
Direction hint: Replace with specific description. What makes it good? Describe the quality instead of asserting it.
What: Phrases that are statistically overrepresented in AI-generated text — tells that signal machine authorship.
Detection signals:
Severity: Warning
Direction hint: Say what you actually mean in plain language. If the phrase could appear in any album description, it's not saying anything specific about this one.
What: Three or more passive constructions in a passage, removing the artist's agency and making the writing feel detached.
Detection signals:
Severity: Info
Direction hint: Put the artist back as the subject. "I wrote this during..." instead of "This was written during..."
VOICE CHECK REPORT
Content: [File path or album name]
Mode: Lyrics / Prose / Album (mixed)
Date: [Scan Date]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SUMMARY
Files scanned: [N]
Warnings: [N]
Info: [N]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
FINDINGS
## [File: tracks/01-track-name.md] (Lyrics)
[WARNING] Class 1 — Abstract Noun Stacking
Line: V1:L3 "hope and dreams collide in the light"
Issue: 3 abstract nouns in one line — "hope", "dreams", "light"
Direction: What does hope look like here? A specific image would
land harder than the abstraction.
[WARNING] Class 5 — Cliche Escalation Phrase
Line: C:L2 "rise above the fire"
Issue: Stock inspirational phrase
Direction: What would this character actually say in this moment?
[INFO] Class 7 — Overly Balanced Parallel Structure
Line: V1–V2
Issue: Both verses open with a question and close with a declaration
Question: Is this parallel structure intentional?
## [File: README.md] (Prose)
[WARNING] Class 10 — AI Self-Narration Phrase
Line: 5 "weaves together themes of loss and redemption"
Direction: What specifically connects these themes in the album?
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
NO FINDINGS
- tracks/02-track-name.md — Clean
- tracks/03-track-name.md — Clean
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
VERDICT: [N] items flagged across [M] files
This is an advisory review. All findings are suggestions —
intentional choices are valid.
lyric-writer — creates/revises lyricslyric-reviewer — catches structural/prosody/pronunciation issues firstpromo-writer — generates social media copypre-generation-check — validates all gates before Suno generation (lyrics path)promo-reviewer — polishes social media copy (prose path)lyric-reviewer — complementary: reviewer catches craft issues, voice-checker catches authenticity issuesplagiarism-checker — both are pre-release quality checkspromo-reviewer — voice-checker flags AI tells before the reviewer polishesYour deliverable: Voice check report with findings by file, direction hints for each finding, and a list of clean files.
Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, compare thinking styles between people, asks "what's my thinking style", "analyze how this person reasons", "cognitive profile", "thinking pattern", "DHDNA", "digital DNA", or wants to understand the mind behind any text. Also trigger when the user provides text and wants deeper insight into the author's reasoning patterns, decision-making style, or cognitive signature.
GSAP animation reference for HyperFrames. Covers gsap.to(), from(), fromTo(), easing, stagger, defaults, timelines (gsap.timeline(), position parameter, labels, nesting, playback), and performance (transforms, will-change, quickTo). Use when writing GSAP animations in HyperFrames compositions.
配图助手 - 把文章/模块内容转成统一风格、少字高可读的 16:9 信息图提示词;先定“需要几张图+每张讲什么”,再压缩文案与隐喻,最后输出可直接复制的生图提示词并迭代。
| YouTube clip generation and editing with automated workflows — pull source video, slice highlights, add captions, and export.
Best practices for writing Remotion animations that stay intuitive for agents and editable in Remotion Studio Visual Mode.
YouTube transcript extraction and content reformatting: given a YouTube video URL, opens the video's transcript panel, extracts all timestamped segments, and transforms the raw transcript into summaries, chapter outlines, Twitter/X threads, blog posts, or notable quotes. Use when the user shares a YouTube URL or video link, asks to summarize a video, get a transcript, extract content from a YouTube video, get YouTube captions, extract YouTube captions, download YouTube captions, transcribe YouTube video, YouTube video to text, make a thread from YouTube, YouTube to blog post, YouTube to article, pull transcript from YouTube, YouTube content extraction, convert YouTube to text, video to transcript. Also applies when user wants to reformat any YouTube video content into structured output (chapters, threads, blog articles, key quotes).
跨境电商全链路自动化工具。集成1688采集、智能清洗、多平台上架(微信小店/Shopify/TikTok)、推广方案(关键词/竞品分析/广告文案)、短视频创作(MoviePy竖屏视频)、一键代发、爆品挖掘(趋势聚合+6维评分)、闲鱼二手选品捡漏(品牌识别/虚标过滤/捡漏评分/价格监控)、全自动流水线(挖掘→采集→清洗→上架→推广→视频)。
生成历史名人现代访谈短视频文案,通过古今反差与网络热梗的爆笑结合,创作具有传播力的虚构趣味内容
Take bitwize-music-studio/voice-checker from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.