Writes or reviews lyrics with professional prosody, rhyme craft, and quality checks.

CC0-1.0Auto-check passed

Install Lyric Writer

skills CLI
$ npx skills add bitwize-music-studio/claude-ai-music-skills --skill lyric-writer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bitwize-music-studio/claude-ai-music-skills lyric-writer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bitwize-music-studio/claude-ai-music-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lyric-writer .claude/skills/lyric-writer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lyric-writer
GitHub stars
544
Token cost
~6.3k tokens
SKILL.md length
3,176 words
Files
4
Skills in repo
51
Repo updated
First seen
Licence
CC0-1.0

At a glance

Writes or reviews lyrics with professional prosody, rhyme craft, and quality checks.

  • Works in 3 steps: Read the track file → Scan existing lyrics for issues (rhyme,… → Report all violations with proposed fixes
  • Writing new lyrics
  • SKILL.md covers Your Task, Supporting Files, Core Principles and Override Support, plus 10 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Lyric Writer is an agent skill from bitwize-music-studio/claude-ai-music-skills. 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.'

Its SKILL.md is about 6.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `craft-reference.md`, `documentary-standards.md` and `examples.md`).

It works with Suno. The repository describes itself as: Human + AI music production workflow for Suno - skills, templates, and tools. The licence is CC0-1.0.

When your agent uses it

  • Writing new lyrics
  • Revising existing lyrics
  • The user says lets work on a track

Example prompts

  • “s work on a track.”
  • “Use the lyric-writer skill to write or reviews lyrics with professional prosody, rhyme craft, and quality checks”
  • “/lyric-writer”

Requirements

  • Pre-approved tools (allowed-tools): Read, Edit, Write, Grep, Glob, bitwize-music-mcp

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

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

What it can do on your machine

Read from SKILL.md and the folder at commit 58f32c2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Edit
    • Write
    • Grep
    • Glob
    • bitwize-music-mcp

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lyric Writer loads about 6.3k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 3,176 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~6.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from bitwize-music-studio/claude-ai-music-skills at commit 58f32c2, republished under its CC0-1.0 licence (© bitwize-music-studio). 3,176 words, ~6,295 tokens.

Download SKILL.mdSave it as .claude/skills/lyric-writer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
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.'
allowed-tools
Read, Edit, Write, Grep, Glob, bitwize-music-mcp
argument-hint
<track-file-path or "write lyrics for [concept]">
model
opus
effort
max

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


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:

PassFocusGoal
1 — TightenCut filler, compress language, remove redundancyEvery word earns its place
2 — StrengthenUpgrade weak imagery, sharpen sensory detail, replace generic with specificLines that stick
3 — Flow & EarRead-aloud test, smooth transitions, singability at target BPMSounds right when sung

See 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.
  • Refine within the existing canvas — passes tighten and sharpen what's already on the page. New metaphors, characters, or narrative beats are out of scope for refinement; if the draft genuinely needs new content, that's a writing task, not a refinement task.
  • Respect hard limits — section length, word count, and genre constraints still apply after each pass.
  • Respect override preferences — if the user's lyric-writing-guide.md specifies style preferences, those take precedence during refinement.

Override Support

Check for custom lyric writing preferences:

Loading Override
  1. Call load_override("lyric-writing-guide.md") — returns override content if found (auto-resolves path from config)
  2. If found: read and incorporate as additional context
  3. If not found: use base guidelines only
Override File Format

{overrides}/lyric-writing-guide.md:

markdown
# Lyric Writing Guide

## Style Preferences
- Prefer first-person narrative
- Avoid religious imagery
- Use vivid sensory details
- Keep verses 4-6 lines max

## Vocabulary
- Avoid: utilize, commence, endeavor (too formal)
- Prefer: simple, direct language

## Themes
- Focus on: technology, alienation, urban decay
- Avoid: love songs, party anthems

## Custom Rules
- Never use the word "baby" in lyrics
- Avoid clichés: "heart of gold", "burning bright"
How to Use Override
  1. Load at invocation start
  2. Use as additional context when writing lyrics
  3. Apply preferences alongside base principles
  4. Override preferences take precedence if conflicting

Example:

  • Base says: "Show don't tell"
  • Override says: "Prefer first-person narrative"
  • Result: Show emotion through first-person actions/observations

Prosody (Syllable Stress)

Prosody is matching stressed syllables to strong musical beats.

Rules:

  • Stressed syllables land on downbeats (beats 1 and 3)
  • Multi-syllable words need natural emphasis: HAP-py, not hap-PY
  • High melody notes = emphasized words

Test: Speak the lyric. If emphasis feels wrong, rewrite it.


Rhyme Techniques

See craft-reference.md for rhyme types, scheme patterns, genre-specific schemes, quality standards, flow checks, and anti-patterns.

Show Don't Tell

ACTION - What would someone DO feeling this emotion?
  • ❌ "My heart is breaking"
  • ✅ "She fell to her knees as he packed his bag"
IMAGERY - Nouns that can be seen/touched
  • ❌ "I felt so sad"
  • ✅ "Coffee gone cold on the counter"
SENSORY DETAIL - Engage multiple senses
  • Sight, sound, smell, touch, taste, organic (body), kinesthetic (motion)

Section balance: Verses = sensory details. Choruses = emotional statements.


Verse/Chorus Contrast

ElementVerseChorus
LyricsObservational, narrativeEmotional, universal
EnergyBuildingPeak
DetailSpecific sensoryAbstract emotional
No Verse-Chorus Echo

A verse must never repeat a key phrase, image, or rhyme word that appears in the chorus it leads into. The chorus is the hook — if the verse already said it, the chorus loses its impact.

What to check — before finalizing any track, compare:

  1. The last 2 lines of every verse/section that precedes a chorus
  2. The first 2 lines of the chorus

Flag any of these overlaps:

  • Exact phrase: Same words appear in both (e.g., "digital heart" / "digital heart")
  • Same rhyme word: Verse ends on "start," chorus opens on "start"
  • Restated hook: Verse paraphrases the chorus hook in different words
  • Shared imagery: Verse uses the chorus's signature image (e.g., both say "warehouse")

Red flags:

  • Last line of verse contains ANY phrase from the chorus first line
  • A signature chorus word (the hook word) appears anywhere in the preceding verse
  • The verse "gives away" the chorus before it hits

Fix:

  1. Rewrite the verse line to use DIFFERENT imagery that SETS UP the chorus
  2. The verse should create tension or expectation — the chorus resolves it
  3. Complementary, not redundant: verse says "spark," chorus says "start"

Scope: This applies to EVERY verse-to-chorus transition in the track, not just the first one. Check all of them. Also check bridge-to-chorus transitions.

Example:

Bad:

This is where the future of tech TV got its start. [Chorus] Five-three-five York Street — where the future got its start,

Good:

This is where it all began, the very first spark. [Chorus] Five-three-five York Street — where the future got its start,


Hook & Title Placement

  • Title in first or last line of chorus
  • Repeat title at song's beginning AND end
  • Give title priority: rhythmic accent, melodic peak

Line Length, Song Length & Section Limits

See craft-reference.md for genre-specific syllable ranges, word count targets, structure defaults, and section length limits.

Lyric Density & Pacing

See craft-reference.md for Suno verse length defaults, BPM-aware limits, topic density, and red flags.

Point of View & Tense

POV: Choose one and maintain it

  • First (I/me) - most intimate
  • Second (you) - draws listener in
  • Third (he/she/they) - storyteller distance

Tense: Stay consistent within sections

  • Present - immediate, powerful
  • Past - distance, reflection

Lyric Pitfalls Checklist

Before finalizing:

  • Forced emphasis (stressed syllables on wrong beats)
  • Inverted word order for rhyme
  • Predictable rhymes (moon/June, fire/desire)
  • Pronoun inconsistency
  • Tense jumping without reason
  • Too specific (alienating names/places)
  • Too vague (abstractions without imagery)
  • Twin verses (V2 = V1 reworded — V2 must advance the story, deepen emotion, or shift perspective, not just rephrase V1. Example: V1 "Streets are cold, I walk alone" → bad V2 "Roads are freezing, I'm by myself" (same idea reworded) → good V2 "Found your old coat in the closet / Still smells like smoke and home" (new detail, emotional shift))
  • No hook
  • Disingenuous voice
  • Section too long for genre (check Section Length Limits table)
  • Orphan lines (line should rhyme with a partner per genre scheme but doesn't)
  • Wrong rhyme scheme for genre (e.g., AABB couplets in a folk ballad)
  • Filler phrases padding lines for rhyme or quote setup
  • Inconsistent syllable counts within a verse (tolerance varies by genre)
  • Verse exceeds Suno line limit for genre (check genre README's Density/pacing default)
  • 8-line verse at BPM under 100 (too dense for Suno — split or trim)
  • Too many proper nouns in a single verse (max 3 introductions per verse)
  • Density mismatch (Musical Direction says "laid back" but verses are packed)
  • Verse-chorus echo (verse repeats chorus phrase, rhyme word, hook, or signature imagery)
  • Invented contractions (signal'd, TV'd — Suno only handles standard pronoun/auxiliary contractions)
  • Pronunciation table not enforced (word in table but standard spelling in Suno lyrics)

Pronunciation

Always use phonetic spelling for tricky words:

TypeExampleWrite As
NamesRamos, SinaloaRah-mohs, Sin-ah-lo-ah
AcronymsGPS, FBIG-P-S, F-B-I
Tech termsLinux, SQLLin-ucks, sequel
Numbersninety-three'93
Homographslive (verb)lyve or liv
Homograph Handling (Suno Pronunciation)

Suno renders pronunciation literally from spelling alone — context cues are invisible to the model. Every homograph in the lyrics needs an explicit user decision recorded in the Pronunciation Notes table, then applied as phonetic spelling in the Suno Lyrics Box only.

Why this matters: Even when a sentence makes the intended reading obvious to a human reader, Suno's TTS picks one pronunciation and locks it in. Wrong choice → wrong vocal line on every regen.

Workflow across skills:

lyric-writer (FLAGS) → pronunciation-specialist (RESOLVES) → lyric-reviewer (VERIFIES)

Your role as writer — flag, batch-ask, apply:

  1. Identify: Flag every homograph in the lyrics during phonetic review (use the table below as a baseline; it is not exhaustive).
  2. Batch-ask: When a track contains multiple homographs, present them in a single user message — numbered list with both pronunciation options per word — and accept all decisions in one user reply. Per-word back-and-forth balloons the conversation and breaks flow.
  3. Apply: Replace with phonetic spelling in Suno lyric lines only. Streaming/distributor lyrics keep standard English spelling.
  4. Document: Add each resolved homograph to the track's Pronunciation Notes table with the user's chosen reading.

The pronunciation-specialist resolves complex cases (regional accents, character voices, dialect markers). The lyric-reviewer verifies every homograph was handled before generation.

Common homographs — every one needs an explicit user decision: (Canonical homograph reference: ${CLAUDE_PLUGIN_ROOT}/reference/suno/pronunciation-guide.md. Keep this table in sync.)

WordPronunciation APhoneticPronunciation BPhonetic
livereal-time/broadcastlyvereside/existlive
readpresent tensereedpast tensered
leadto guideleedmetalled
woundinjurywoondpast of windwownd
closeto shutklozenearbyklohs
basslow soundbayssthe fishbas
tearfrom cryingteerto riptare
windair movementwihndto turnwynd

Rules:

  • Every homograph in the phonetic checklist must trace to a recorded user decision in the Pronunciation Notes table — "context clear" is not a valid resolution.
  • The user is the only authority on which pronunciation is intended. Ask when in doubt; treat ambiguity as a flag, not a judgment call.
  • Phonetic spellings live in the Suno Lyrics Box only. Streaming/distributor lyrics use standard English.
  • Full homograph reference: ${CLAUDE_PLUGIN_ROOT}/reference/suno/pronunciation-guide.md
Show full SKILL.md (1,207 more words)Show less
No Invented Contractions (Suno)

Suno only recognizes standard English contractions. Never use made-up contractions by appending 'd, 'll, etc. to nouns, brand names, or non-standard words.

Standard (OK for Suno): they'd, he'd, you'd, she'd, we'd, I'd, wouldn't, couldn't, shouldn't

Invented (will break Suno): signal'd, TV'd, network'd, podcast'd, channel'd

Fix: Spell it out — "signal would" not "signal'd", "TV could" not "TV'd"

Rule: If the base word isn't a pronoun or standard auxiliary verb, don't contract it. Suno will mispronounce or skip invented contractions.

Pronunciation Table Enforcement (Suno)

Every entry in a track's Pronunciation Notes table MUST be applied as phonetic spelling in the Suno lyric lines. The pronunciation table is not documentation — it is a checklist of required substitutions.

Process (before finalizing any track for Suno generation):

  1. Read the track's Pronunciation Notes table top to bottom
  2. For EACH entry, search the Suno lyrics for the standard spelling
  3. If found, replace with the phonetic spelling
  4. If the phonetic is already applied, confirm it matches the table

Verification format — update the Phonetic Review Checklist:

  • ❌ "Potrero" in pronunciation table but "Potrero" in Suno lyrics — FAIL
  • ✅ "poh-TREH-roh" in Suno lyrics matches pronunciation table — PASS

Rules:

  • The pronunciation table is the source of truth for Suno spelling. Every entry must appear as its phonetic form in the Suno Lyrics Box.
  • Every Suno lyric line that contains a tabled word uses the phonetic spelling — every verse, every chorus repeat, every bridge.
  • Phonetics belong in the Suno Lyrics Box only; streaming lyrics keep standard spelling.
  • When uncertain whether a word needs phonetic treatment, ask the user — better to flag and confirm than ship a guess.

Common failures:

  • Word added to pronunciation table during track creation but never applied to lyrics
  • Phonetic applied in one verse but missed in another (chorus repeat, bridge)
  • New lyric edit introduces a word that's already in the table but isn't phonetic

Anti-pattern:

WRONG:   Pronunciation Table: Potrero → poh-TREH-roh
         Suno Lyrics: "Potrero Hill, industrial..."

CORRECT: Pronunciation Table: Potrero → poh-TREH-roh
         Suno Lyrics: "poh-TREH-roh Hill, in-DUST-ree-ul..."

Documentary Standards

For true crime/documentary tracks, see documentary-standards.md.

The Five Rules:

  1. Third-person narrator only — render the story from outside the subject; the narrator describes, not impersonates.
  2. Quote only what's in the source record — verbatim, with citation. Anything in quotation marks must be traceable to testimony, transcript, or recorded statement.
  3. Internal states require testimony — render thoughts, feelings, or motivations only when a source (interview, statement, court record) supports them.
  4. Actions must be in the record — render only events that appear in the source material; no invented beats, no implied scenes.
  5. Confine factual claims to what sources affirm — absence of evidence is not a claim. "Nobody saw" needs a source asserting that, not a gap in the record.

Cross-Track Referencing (Concept Albums)

When to Activate

Activate when all of these are true:

  • Album type is Narrative, Thematic, Character Study, Documentary, or OST
  • Current track number is > 1 (track 01 establishes — it doesn't reference)
Process
  1. Read album context: Album README → Concept, Structure, Motifs & Threads sections
  2. Read previous tracks: Tracks 1 through N-1 (lyrics, concept, cross-references)
  3. Identify 1–3 callback opportunities: Look for lyrical images, phrases, character moments, or thematic threads that can be echoed, inverted, or resolved
  4. Draft with references woven in: Integrate naturally — the reference should feel like part of this track, not a footnote
  5. Document: Update the track's Cross-References section AND the album's Motifs & Threads table
Reference Density by Album Position
PositionTarget ReferencesRationale
Track 010Establishes motifs — nothing to reference yet
Tracks 02–04 (early)1–2Light callbacks; building the vocabulary
Tracks 05–08 (mid)2–3Weaving threads together; peak density
Final 1–2 tracks2–4Resolving threads; bookend with track 01
Reference Types
TypeWhat It DoesExample
CallbackEchoes an earlier lyric or image in new contextTrack 01: "the door was red" → Track 07: "red doors don't open twice"
MotifRecurring thematic element that gains meaning"static" appearing across tracks as technology fails
Character threadSame character reappears or is referencedTrack 03 introduces a witness; Track 08 shows their testimony
Contrast/InversionDeliberately flips an earlier ideaTrack 02: "the signal's strong" → Track 09: "nothing but noise"
ResolutionResolves tension or question from earlier trackTrack 04 asks "who called the cops?" → Track 11 answers it
Quality Rules
  • Subtle over heavy — a single echoed image beats a quoted line. The listener should feel the connection, not be hit with it.
  • New context required — a callback must mean something different in its new location. Same phrase, same meaning = lazy repetition, not a callback.
  • Don't force it — if no natural callback opportunity exists, write the track without one. Forced references hurt worse than no references.
  • Bookend rule — the final track should echo at least one element from track 01, creating a sense of closure.
  • Track must stand alone first — every track must work as a complete song without the callbacks. References are a bonus layer, not a crutch.
Anti-Patterns
  • ❌ Quoting whole lines from earlier tracks verbatim (lazy — transform the reference)
  • ❌ Forward references to tracks not yet written (breaks the writing flow; only backward references)
  • ❌ Referencing every previous track in a single song (overwhelming — pick 1–3 strongest connections)
  • ❌ Making the callback the hook or chorus (callbacks belong in verses/bridges — the hook should stand alone)
  • ❌ Explaining the reference in the lyrics ("just like track three said…")

Working On a Track

When asked to work on a track, immediately scan for:

  • Weak/awkward lines, forced rhymes
  • Prosody problems
  • POV or tense inconsistencies
  • Twin verses
  • Missing hook or buried title
  • Factual inaccuracies
  • Pronunciation risks

Report all issues with proposed fixes, then proceed.


Workflow

As the lyric writer, you:

  1. Receive track concept - From album-conceptualizer or user 1.5. Load album context - (Concept albums only) Read album README and previous tracks for cross-referencing opportunities. See "Cross-Track Referencing" section.
  2. Draft initial lyrics - Apply core principles, weaving in callbacks where appropriate
  3. Run quality checks - Verify rhyme, POV, tense, structure (13-point check) 3.5. Run refinement passes - Default: 1 pass. Tighten, strengthen, polish. See "Iterative Refinement Passes" section.
  4. Scan for pronunciation risks - Check proper nouns, homographs
  5. Apply phonetic fixes - Replace risky words
  6. Verify against sources - If documentary track
  7. Finalize lyrics - Update Lyrics Box, Streaming Lyrics, Cross-References, and Motifs & Threads table (concept albums)
  8. Hand off to Suno engineer - Automatically invoke /bitwize-music:suno-engineer with the track file path to populate the Style Box and Suno Inputs section. Do not wait for the user to request this — it is the natural next step after lyrics are finalized.

Remember

  1. Load override first - Call load_override("lyric-writing-guide.md") at invocation. Why: the user's vocabulary preferences, theme avoidances, and custom rules outrank base craft guidelines and must be in context before the first line is drafted.
  2. Watch your rhymes - No self-rhymes, no lazy patterns
  3. Prosody matters - Stressed syllables on strong beats
  4. Show don't tell - Action, imagery, sensory detail
  5. V2 ≠ V1 - Second verse must develop, not twin
  6. Pronunciation is critical - Phonetic spelling for risky words
  7. Documentary = legal risk - Follow the five rules
  8. Apply user preferences - Override guide preferences take precedence
  9. Concept albums connect - Read previous tracks, weave 1–3 callbacks, update Motifs & Threads table
  10. Refine before presenting - Run refinement passes (default: 1), show Refinement Log with before→after for each change

Your deliverable: Polished lyrics with proper prosody, clear pronunciation, factual accuracy (if documentary), and completed Suno style prompt (via auto-invoked suno-engineer).

© bitwize-music-studio, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in skills/lyric-writer of bitwize-music-studio/claude-ai-music-skills.

  • SKILL.md
  • craft-reference.md
  • documentary-standards.md
  • examples.md

Open the folder on GitHubat commit 58f32c2

Compare with similar skills

Lyric Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lyric Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lyric Writer this skillbitwize-music-studio/claude-ai-music-skills544—~6.3kAutomated safety check: PassCC0-1.0
AI Media GeneratorHao0321/ai-media-generator260—~5.6kAutomated safety check: PassMIT
Mira Historysandeco/mira-animator218—~4kAutomated safety check: PassCustom licence
AI Music And Soundsocial-media-skills/skills134—~1.9kAutomated safety check: PassMIT
Prismer Songwriting And AI MusicPrismer-AI/PrismerCloud1.6k6 repos~2.9kAutomated safety check: PassMIT
Extensiondaiki-beppu/youtube-automation169—~520Automated safety check: PassCustom licence

Similar skills

  • AI Media Generator

    Hao0321/ai-media-generator

    為使用者產生高品質的 AI 生圖、生影片、生音樂提示詞,並在需要時透過瀏覽器自動化實際送到目標平台。涵蓋 OiiOii、Kling 3.0/O-series、Seedance 2.0/2.5、Suno v5.5、Seedream 5.0/4.0、Vidu Q3、Midjourney V8.1、Flux 1.1 Pro / Kontext、Runway Gen-4.5 /…

    260 GitHub stars~5.6k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Mira History

    sandeco/mira-animator

    Transforma o texto de uma história (normalmente infantil) numa animação narrada no Mira: cenas com câmera e clima, atores em SVG, narração, música e QR para o celular.

    218 GitHub stars~4k tokensUpdated 26 days ago
    Documents & OfficeAuto-check passed
  • AI Music And Sound

    social-media-skills/skills

    The AI music + sound-design skill for social -- original/licensed audio beds and sound design for Reels/TikToks/Shorts/videos.

    134 GitHub stars~1.9k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed
  • Prismer Songwriting And AI Music

    Prismer-AI/PrismerCloud

    Songwriting craft and Suno AI music prompts. An agent skill from Prismer-AI/PrismerCloud.

    1.6k GitHub starsUsed in 6 repos~2.9k tokens
    Media & CreativeAuto-check passed
  • Extension

    daiki-beppu/youtube-automation

    A skill your agent uses when Chrome 拡張(suno-helper / distrokid-helper / community-helper)の導入・更新、または拡張向け collection server の起動・停止を行うとき。「拡張入れて」「extension 更新」「サーバー起動」で発動。排他的な --install / --update /…

    169 GitHub stars~520 tokensUpdated 3 days ago
    Auto-check passed
  • Music

    daiki-beppu/youtube-automation

    A skill your agent uses when 音楽制作を状態判定付きで一括実行または一段だけ実行するとき。Suno UI 投入用の Style / プロンプト生成は --prompt、Suno ボーカル曲の歌詞生成は --lyric、musicengine に応じた音源生成は --generate、Suno 音源の一括 DL とマスター化は --master…

    169 GitHub stars~1.4k tokensUpdated 3 days ago
    Auto-check passed

More from bitwize-music-studio/claude-ai-music-skills

All 51 skills in this repo
  • Album Conceptualizer

    bitwize-music-studio/claude-ai-music-skills

    Designs album concepts, tracklist architecture, and thematic planning through 7 structured phases.

    544 GitHub stars~3.6k tokensUpdated 3 days ago
    Auto-check passed
  • Album Dashboard

    bitwize-music-studio/claude-ai-music-skills

    Shows a structured progress dashboard for an album with percentage complete per phase, blocking items, and status breakdown.

    544 GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed
  • Album Ideas

    bitwize-music-studio/claude-ai-music-skills

    Tracks and manages album ideas including brainstorming, planning, and status updates.

    544 GitHub stars~2.2k tokensUpdated 3 days ago
    Auto-check passed
  • Clipboard

    bitwize-music-studio/claude-ai-music-skills

    Copies track content (lyrics, style prompts, streaming lyrics) to the system clipboard.

    544 GitHub stars~1.4k tokensUpdated 3 days ago
    Auto-check: notes
  • Cloud Uploader

    bitwize-music-studio/claude-ai-music-skills

    Uploads promo videos and content to Cloudflare R2 or AWS S3.

    544 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check: notes
  • Configure

    bitwize-music-studio/claude-ai-music-skills

    Sets up or edits the plugin configuration file interactively.

    544 GitHub stars~2.2k tokensUpdated 3 days ago
    Auto-check: notes

Works with

Questions about Lyric Writer

What does Lyric Writer do?

Writes or reviews lyrics with professional prosody, rhyme craft, and quality checks. Lyric Writer is an agent skill from bitwize-music-studio/claude-ai-music-skills. Writes or reviews lyrics with professional prosody, rhyme craft, and quality checks.

When should I use Lyric Writer?

Lyric Writer fits situations like: writing new lyrics; revising existing lyrics; the user says lets work on a track.

How do I install Lyric Writer in Claude Code?

Run `npx skills add bitwize-music-studio/claude-ai-music-skills --skill lyric-writer -a claude-code`. Or copy the skill folder (skills/lyric-writer in bitwize-music-studio/claude-ai-music-skills) into .claude/skills/lyric-writer in your project. Claude Code loads it when a task matches its description.

How do I install Lyric Writer in Codex?

Run `npx skills add bitwize-music-studio/claude-ai-music-skills --skill lyric-writer -a codex`. Or copy the skill folder (skills/lyric-writer in bitwize-music-studio/claude-ai-music-skills) into .agents/skills/lyric-writer in your project. Codex loads it when a task matches its description.

Can I use Lyric Writer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bitwize-music-studio/claude-ai-music-skills --skill lyric-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lyric-writer, .gemini/skills/lyric-writer, .github/skills/lyric-writer and .opencode/skills/lyric-writer in your project.

What does Lyric Writer need to run?

SKILL.md names no scripts, command-line tools or credentials: Lyric Writer is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Edit, Write, Grep, Glob, bitwize-music-mcp.

Does Lyric Writer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Lyric Writer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Lyric Writer use?

Lyric Writer is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lyric Writer use?

About 6.3k tokens (SKILL.md is roughly 25k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Lyric Writer?

Skills that share tags, products or a category with Lyric Writer: AI Media Generator (Hao0321/ai-media-generator, 260 stars), Mira History (sandeco/mira-animator, 218 stars), AI Music And Sound (social-media-skills/skills, 134 stars) and Prismer Songwriting And AI Music (Prismer-AI/PrismerCloud, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lyric Writer?

bitwize-music-studio (a GitHub organization) maintains it in bitwize-music-studio/claude-ai-music-skills, which has 544 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on October 7, 2026.

Source: bitwize-music-studio/claude-ai-music-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.