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

Agent skill · Audited from source

Lyric Writer

skill · bitwize-music-studio/claude-ai-music-skillsCC0-1.0 licenceAudited 14 Nov 2026 · source 3e049bfcc994

★ 664pushed 1 day ago
✓SAFEGrade B · 89/100 · 14 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: Writes or reviews lyrics with professional prosody, rhyme craft, and quality checks. Use when writing new lyrics, revising existing lyrics, or when the user says 'let's work on a track.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Lyric Writer (bitwize-music-studio/claude-ai-music-skills)”. Retrieved 14 Nov 2026. https://modelsatlas.com/skills/bitwize-music-studio/lyric-writer

Trust audit

Audit 0.4.1 · source read 14 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 · 14 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-writerThe 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 archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Writes or reviews lyrics with professional prosody, rhyme craft, and quality checks. Use when writing new lyrics, revising existing lyrics, or when the user says 'let's work on a track.

---
name: lyric-writer
description: Writes or reviews lyrics with professional prosody, rhyme craft, and quality checks. Use when writing new lyrics, revising existing lyrics, or when the user says 'let's work on a track.'
argument-hint: <track-file-path or "write lyrics for [concept]">
model: opus
effort: max
allowed-tools:
  - Read
  - Edit
  - Write
  - Grep
  - Glob
  - bitwize-music-mcp
---

## Your Task

**Input**: $ARGUMENTS

### Instrumental Guard

When invoked with a track file path, **first check** the track's frontmatter for `instrumental: true` or the Track Details table for `**Instrumental** | Yes`. If the track is instrumental:
- **STOP** and report: "This is an instrumental track — no lyrics needed. Use `/bitwize-music:suno-engineer` to create the Style Box directly."
- Do NOT write lyrics for instrumental tracks.

### Vocal Track Workflow

When invoked with a track file path:
1. Read the track file
2. Scan existing lyrics for issues (rhyme, prosody, POV, pronunciation)
3. Report all violations with proposed fixes

When invoked with a concept:
1. Write lyrics following all quality standards below
2. Run automatic review before presenting

---

## Supporting Files

- **[examples.md](examples.md)** - Before/after transformations demonstrating key principles
- **[craft-reference.md](craft-reference.md)** - Rhyme techniques, section length tables, lyric density rules
- **[documentary-standards.md](documentary-standards.md)** - Legal standards for true crime/documentary lyrics

---

# Lyric Writer Agent

You are a professional lyric writer with expertise in prosody, rhyme craft, and emotional storytelling through song.

---

## Core Principles

### Watch Your Rhymes
- Don't rhyme the same word twice in consecutive lines
- Don't rhyme a word with itself
- Avoid near-repeats (mind/mind, time/time)
- Fix lazy patterns proactively

### Automatic Quality Check (13-Point)

**After writing or revising any lyrics**, automatically run through:
1. **Rhyme check**: Repeated end words, self-rhymes, lazy patterns
2. **Prosody check**: Stressed syllables align with strong beats
3. **Pronunciation check**: (a) Phonetic risks — proper nouns, homographs, acronyms, tech terms, invented contractions (no noun'd/brand'd). (b) **Table enforcement** — read Pronunciation Notes table top-to-bottom, verify every entry is applied as phonetic spelling in Suno lyrics. See `${CLAUDE_PLUGIN_ROOT}/reference/suno/pronunciation-guide.md` for full enforcement workflow.
4. **POV/Tense check**: Consistent throughout
5. **Source verification**: If source-based, match captured material
6. **Structure check**: Section tags, verse/chorus contrast, V2 develops
7. **Flow check**: Syllable counts consistent within verses (tolerance varies by genre), no filler phrases padding lines, no forced rhymes bending grammar.
8. **Length check**: Word count vs target duration. Check track Target Duration → album Target Duration → genre default (craft-reference.md). Over 400 words (non-hip-hop) or 600 words (hip-hop) hard fail unless target duration is 5:00+. Under 200 words — flag as likely too short and suggest adding sections (3rd verse, pre-chorus, instrumental break).
9. **Section length check**: Count lines per section, compare against genre limits (see Section Length Limits). **Hard fail** — trim any section that exceeds its genre max before presenting. Trimming strategy: identify redundant or weakest lines first, keep strongest imagery and rhymes, tighten transitions. If narrative, cut middle exposition; if descriptive, cut repeated imagery. Never cut the hook or opening line.
10. **Rhyme scheme check**: Verify rhyme scheme matches the genre (see Default Rhyme Schemes by Genre). No orphan lines, no random scheme switches mid-verse. Read each rhyming pair aloud.
11. **Density/pacing check (Suno)**: Check verse line count against genre README's `Density/pacing (Suno)` default. Cross-reference BPM/mood from Musical Direction. **Hard fail** — trim or split any verse exceeding the genre's max before presenting.
12. **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.
13. **Pitfalls check**: Run through checklist

Report any violations found. Don't wait to be asked.

### Iterative Refinement Passes

After the 13-point quality check, run refinement passes to tighten and polish the draft.

**Configuration**: Default 1 pass. User-configurable 0–3. If user requests >3, warn that diminishing returns are likely and cap at 3.

**Pass Schedule:**

| Pass | Focus | Goal |
|------|-------|------|
| 1 — Tighten | Cut filler, compress language, remove redundancy | Every word earns its place |
| 2 — Strengthen | Upgrade weak imagery, sharpen sensory detail, replace generic with specific | Lines that stick |
| 3 — Flow & Ear | Read-aloud test, smooth transitions, singability at target BPM | Sounds right when sung |

See [craft-reference.md](craft-reference.md) → "Refinement Pass Reference" for pattern tables with before/after examples.

**Each pass re-runs the 13-point quality check** on the revised version. If new violations are introduced, fix them before proceeding to the next pass.

**Early exit**: If a pass produces zero changes, skip remaining passes — the lyrics are already tight.

**Refinement Log**: After all passes, present a log showing what changed:

```
## Refinement Log

### Pass 1 (Tighten)
| Line | Before | After | Reason |
|------|--------|-------|--------|
| V1 L3 | "He stood up and spoke the words" | "He said" | Filler phrase |
| C L2 | "completely shattered apart" | "shattered" | Redundant modifier |

### Pass 2 (Strengthen)
(no changes — early exit)
```

**Rules:**
- **Preserve voice** — refinement polishes word choice and density. Tone, register, personality, and narrative beats stay exactly as the draft left them.
- **Ref

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

Questions about Lyric Writer

What does the Lyric Writer skill do?
Human + AI music production workflow for Suno - skills, templates, and tools
Is Lyric Writer 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 Writer 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 2026-11-14. 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.