agentleFS
sergeeeysergeeey/Claude-cod-top-2026/skills/extensions/suno-music/SKILL.md

suno-music

Skill9 starsChanged 6 months agoMITView on GitHub

EDM / Future Bass: Rap / Drill:

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    USE when creating music prompts or discussing audio production.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- BSV — Brief Skill View | поиск: BSV Скил : suno-music TL;DR : Генерация музыки через Suno AI API Вызов : 'создай музыку', 'suno:', 'музыкальный трек' НЕ для : Аудио не для Suno -->

name: suno-music description: > [STATUS: draft] [CONFIDENCE: medium] [REVIEWED: 2026-03-13] USE when creating music prompts or discussing audio production. Triggers: Suno, track, BPM, music, prompt music, frequencies, beat, genre, EDM, hardstyle, hyperpop, rap, drill, track, beat.

Suno Music Prompt Engineering

Track Generation Principles

BPM by Genre

GenreBPMCharacter
Lo-fi / Chill70-90Relaxation, focus
Hip-hop / Rap80-100Groove, head-nod
Pop / Dance-pop110-130Energy, mainstream
House / EDM120-130Steady groove, club
Hardstyle150-160Aggression, raw energy
Drum & Bass170-180High energy

Frequency Engineering

  • Sub-bass (20-60 Hz): physical sensation, "chest hit"
  • Bass (60-250 Hz): warmth, fullness
  • Mids (250-2000 Hz): vocals, main instruments
  • Presence (2-6 kHz): clarity, "in your face"
  • Air (6-20 kHz): sparkle, space, cymbals

Build-Up Principles (neurophysiology)

  1. Tension build: gradual layer addition (4-8 bars)
  2. Riser: ascending sweep/noise before drop (2-4 bars)
  3. Silence gap: 0.5-1 sec silence before drop (anticipation peak)
  4. Drop: maximum energy, bass + kick, all layers at once
  5. Dopamine cycle: build → drop → breakdown → build (repeat every 32-64 bars)

Suno Prompt Templates

EDM / Future Bass:

[Verse] atmospheric synths, soft vocals, building energy
[Pre-Chorus] rising tension, layered pads, snare rolls
[Chorus] massive drop, supersaw chords, punchy kick, euphoric
[Bridge] stripped back, piano, vocal chops

Hardstyle:

[Intro] dark atmosphere, reverse bass teaser
[Build] rising pitch, snare roll crescendo, crowd noise
[Drop] hard kick, distorted bass, 150 BPM, raw energy
[Mid-section] melodic break, emotional chords, female vocals

Rap / Drill:

[Intro] 808 slide, dark piano, trap hi-hats
[Verse] aggressive flow, rapid delivery, ad-libs
[Hook] catchy melody, autotune, repetitive phrase
[Bridge] beat switch, tempo change, ambient

Tips

  • Suno generates better with specific instruments ("distorted 808", not "bass")
  • Emotional words work: "euphoric", "melancholic", "aggressive", "dreamy"
  • [Verse][Chorus] structure gives better results than free-form
  • Track length: 2-4 min optimal, >4 min = repetitions

Gotchas

  • BPM must match genre conventions — 140 BPM hardstyle, not 120
  • Frequency engineering is subjective — test with headphones, not laptop speakers

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.