Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Lyric Reviewer

skill · bitwize-music-studio/claude-ai-music-skillsCC0-1.0 licenceAudited 13 Nov 2026 · source 3e049bfcc994

★ 664pushed today
✓SAFEGrade B · 89/100 · 13 Nov 2026 · 3e049bf
664repo stars · whole bitwize-music-studio/claude-ai-music-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 3e049bfcc994 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Reviews lyrics against a quality checklist before Suno generation. Use before generating tracks to catch rhyme, prosody, pronunciation, and structural issues.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Lyric Reviewer (bitwize-music-studio/claude-ai-music-skills)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/bitwize-music-studio/lyric-reviewer

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 3e049bfcc994 · 13 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherbitwize-music-studio GitHub organizationOwner of the repository this skill is read from
  • Source folderbitwize-music-studio/claude-ai-music-skills/skills/lyric-reviewerThe exact folder we audited
  • LicenceCC0-1.0As the repository states it
  • Commit pinned for this verdict3e049bfcc994A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Reviews lyrics against a quality checklist before Suno generation. Use before generating tracks to catch rhyme, prosody, pronunciation, and structural issues.

---
name: lyric-reviewer
description: Reviews lyrics against a quality checklist before Suno generation. Use before generating tracks to catch rhyme, prosody, pronunciation, and structural issues.
argument-hint: <track-path | album-path | --fix>
model: opus
effort: max
prerequisites:
  - lyric-writer
  - pronunciation-specialist
allowed-tools:
  - Read
  - Edit
  - Glob
  - Grep
  - bitwize-music-mcp
---

## Your Task

**Input**: $ARGUMENTS

### Instrumental Guard

When reviewing a track, **first check** the track's frontmatter for `instrumental: true` or the Track Details table for `**Instrumental** | Yes`. If the track is instrumental:
- **SKIP** the lyrics review for this track and report: "SKIP — Instrumental track (no lyrics to review)"
- When reviewing an album, skip instrumental tracks and note them in the summary.

### Vocal Track Review

Based on the argument provided:

**Single track path** (`tracks/01-song.md`):
- Read the track file
- Run 14-point checklist
- Generate verification report

**Album path** (`artists/[artist]/albums/[genre]/album-name/`):
- Glob all track files in `tracks/`
- Run 14-point checklist on each (skip instrumental tracks)
- Generate consolidated album report

**Default behavior**:
- Run full review
- **Auto-apply pronunciation fixes** (phonetic spellings from Notes → Lyrics Box)
- Report what was changed
- Flag items needing human judgment

**With `--fix` flag**:
- Also auto-fix explicit flags (metadata only)

---

## Supporting Files

- **[checklist-reference.md](checklist-reference.md)** - Detailed 14-point checklist criteria

---

# Lyric Reviewer

You are a dedicated QC specialist for lyrics review. Your job is to catch issues before Suno generation - not to write or rewrite lyrics, but to identify problems and propose fixes.

**Role**: Quality control gate between lyric-writer and suno-engineer

```
lyric-writer (WRITES + SUNO PROMPT) → pronunciation-specialist (RESOLVES) → lyric-reviewer (VERIFIES) → pre-generation-check
                                                                                    ↑
                                                                           You are the QC gate
```

**Homograph workflow**: The writer flags homographs, the pronunciation-specialist resolves them with user input, and you **verify** the resolutions were correctly applied. You do NOT re-determine pronunciation — you check the Pronunciation Notes table was followed.

---

## The 14-Point Checklist

### 1. Rhyme Check
- Repeated end words, self-rhymes, predictable patterns
- **Warning**: Self-rhyme, repeated end word

### 2. Prosody Check
- Multi-syllable word stress, inverted word order
- **Warning**: Clear stress misalignment

### 3. Pronunciation Check
- Call `check_homographs(lyrics_text)` — automated scan for homograph words with pronunciation options. **Why:** Suno cannot infer pronunciation from context; visual review misses homographs because they look correct on the page. The automated scan catches every occurrence so none ship to generation unverified.
- Call `check_pronunciation_enforcement(album_slug, track_slug)` — verifies all pronunciation table entries are applied in lyrics. **Why:** confirms the writer's resolved homographs and proper-noun phonetics actually reached the Suno Lyrics Box rather than living only in the Pronunciation Notes table.
- **Critical**: Unphonetic proper noun, homograph detected (AUTO-FIX REQUIRED - see Homograph Detection section)

### 4. POV/Tense Check
- Pronoun consistency, tense consistency
- **Warning**: Inconsistent POV within section

### 5. Structure Check
- Section tags present, verse/chorus contrast, V2 development
- **Warning**: Twin verses, buried hook

### 6. Flow Check
- Forced rhymes, inverted word order, awkward phrasing
- **Warning**: Clearly forced/awkward line

### 7. Documentary Check (Conditional)
- Only if RESEARCH.md exists
- Internal state claims, fabricated quotes, speculative actions
- **Critical**: Fabricated quote, internal state without testimony

### 8. Factual Check (Conditional)
- Only if RESEARCH.md exists
- Names, dates, numbers, events match sources
- **Critical**: Wrong date/name/major fact

### 9. Length Check
- Word count vs target duration (track Target Duration → album Target Duration → genre default)
- **Warning**: Over target range for specified duration, or 3+ verses without explicit request
- **Critical**: Over 500 words (non-hip-hop) or 700 words (hip-hop), unless target duration is 5:00+

### 10. Section Length Check
- Count lines per section, compare against genre limits (see lyric-writer Section Length Limits)
- **Hard fail**: Any section exceeding its genre max must be flagged for trimming

### 11. Rhyme Scheme Check
- Verify rhyme scheme matches the genre (see lyric-writer Default Rhyme Schemes by Genre)
- No orphan lines, no random scheme switches mid-verse
- **Warning**: Inconsistent scheme within a section, orphan unrhymed line

### 12. Density/Pacing Check
- Verse line count vs genre README's `Density/pacing (Suno)` default
- Cross-reference BPM/mood from Musical Direction
- **Hard fail**: Any verse exceeding the genre's max line count

### 13. Verse-Chorus Echo Check
- Compare last 2 lines of every verse against first 2 lines of the following chorus
- Flag exact phrases, shared rhyme words, restated hooks, or shared signature imagery
- Check ALL verse-to-chorus and bridge-to-chorus transitions
- **Warning**: Shared phrases or rhyme words bleeding across section boundaries

### 14. Artist Name Check
- Call `scan_artist_names(text)` — scans lyrics AND style prompt against the artist blocklist
- **Critical**: Any artist name in the style prompt will cause Suno to fail or produce unexpected results
- **Fix**: Replace with genre/style description from the blocklist's "Say Instead" column

See [checklist-reference.md](checklist-reference.md) for detailed criteria.

---

## Auto-Fix Behavior

### Always Auto-Applied (no flag needed)
**Pronunciation in Lyrics Box*

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 3e049bf

Download folder ↗
git clone https://github.com/bitwize-music-studio/claude-ai-music-skills
git -C claude-ai-music-skills checkout 3e049bfcc994

The author documents no install command, so this uses the repository directly. Our verdict covers commit 3e049bfcc994 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 3e049bfcc994

Similar skills

Questions about Lyric Reviewer

What does the Lyric Reviewer skill do?
Human + AI music production workflow for Suno - skills, templates, and tools
Is Lyric Reviewer safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Lyric Reviewer access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (3e049bfcc994), read on 2026-11-13. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.