Skill detail

suno-songwriting

Generates, revises, and translates song lyrics plus compact style prompts for Suno or similar AI music generators, with genre, vocal, and structure references.

MatchDirectRecommended for Music Generation
Sourcenunaught/​suno-songwriting-skillExternal source
Reported installs142Popularity signal only

Inspect before use

Read the source instructions and check the requirements before you install this skill.

Saved source preview

SKILL.md

The saved excerpt is a snapshot from when this skill was listed. The external source remains the complete and most current version.

---
name: suno-songwriting
description: Generate, revise, translate, and adapt song lyrics plus compact style prompts for Suno or similar AI music generators. Use when the user wants ready-to-paste AI music generation lyrics, lyric tags, Suno/Udio-style prompts, vocal direction, instrumentation, genre/style wording, song structure, multilingual singable lyrics, or a clarifying interview for an AI-generated song. Do not route general music theory, ordinary artist research, or non-generation songwriting discussion here unless the requested deliverable is lyrics or a generation-ready style prompt.
---

# Suno Songwriting

## Reference Files

| File | Use |
| --- | --- |
| `references/clarifying-interview-instructions.md` | Intake ledger, interview loop, sufficiency gate, and sketch-mode exception. |
| `references/lyric-writing-instructions.md` | Lyric composition, revision, rhyme, structure, hooks, bridges, and title options. |
| `references/style-writing-instructions.md` | Suno style prompts, prompt length, ordering, genre fusion, production direction, and negative constraints. |
| `references/genre-knowledge.md` | Genre selection, genre fusion, era references, subgenre vocabulary, and production traits. |
| `references/vocal-routing-index.md` | Lightweight routing for vocal descriptions, profile resources, comparison, and voice-design depth. |
| `references/instrument-knowledge.md` | Band, orchestration, synth, rhythm section, sound palette, and arrangement vocabulary. |
| `references/lyric-tag-knowledge.md` | Bracketed lyric tags, section tags, performance cues, instrumental breaks, and tag restraint. |
| `references/translation-instructions.md` | Non-English lyrics, bilingual lyrics, translation, localization, syllable preservation, and singability. |
| `references/extended-genre-diversity-matrix.md` | Index for uncommon, historical, regional, and fusion genre vocabulary; route from here to the relevant `genres-*.md` file. |
| `references/structure-movement-tags.md` | Index for detailed structure, movement, energy, pulse, climax, drop, improvisation, and arrangement tags. |
| `references/vocal-identity-library.md` | Index for named vocal identities, voice-profile comparison, profile prompt variants, and evaluation rubrics. |

Load specialized profile, genre, and tag-family files only through their index resources when the task calls for that depth.

## Core Workflow

Use this skill to produce two coordinated outputs:

1. Lyrics suitable for Suno's lyric field, using section tags that embed any optional performance, movement, arrangement, or enriched cue tags.
2. A style prompt suitable for Suno's style prompt field, using either compact or rich production-brief form based on the user's brief.

Start by reading `references/clarifying-interview-instructions.md` for any new song, major rewrite, translation/adaptation with taste decisions, or request where the user asks for a Suno-ready result. Run the interview by default unless the user has already provided a complete brief with all critical inputs. Maintain the interview checklist from that file as an internal intake ledger: each required area must be collected from the user, inferred with reasonable confidence for low-impact details, or explicitly skipped/omitted because the area is irrelevant. Ask up to five questions per interview turn, with one unresolved input category per question; do not combine discrete categories into a single question or answer set. Continue until every critical input has been explicitly supplied by the user, and do not skip asking for a critical input merely because the user declined questions, delegated choices, requested a quick draft, or said "decide everything else." Do not treat a topic plus genre, or a topic plus mood, as a complete brief.

Hard stop: for a new song from a thin brief, do not return the final four-section output on the first response. Return an intake snapshot and clarifying questions instead.

## Draft / Sketch Mode

Use sketc
Read the full source on GitHub (opens external page)
Context

Related work