Acestep Songwriting logo

Acestep Songwriting

Organization
ace-step
acestep-songwriting

Music songwriting guide for ACE-Step. Provides professional knowledge on writing captions, lyrics, choosing BPM/key/duration, and structuring songs. Use this skill when users want to create, write, or plan a song before generating it with ACE-Step.

Overview

Publisherace-step
Repositoryace-step-skills
Skill nameacestep-songwriting
Stars
99
Forks
20
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ace-step on GitHub. Read the source before you install it.

Installation

Install the Acestep Songwriting AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ace-step/ace-step-skills/tree/main/skills/acestep-songwriting
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ace-step/ace-step-skills.git /tmp/ace-step-skills
mkdir -p .claude/skills
cp -r /tmp/ace-step-skills/skills/acestep-songwriting .claude/skills/acestep-songwriting
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Acestep Songwriting in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Acestep Songwriting on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Acestep Songwriting is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ACE-Step Songwriting Guide

Professional music creation knowledge for writing captions, lyrics, and choosing music parameters for ACE-Step.

Output Format

After using this guide, produce two things for the acestep skill:

  1. Caption (-c): Style/genre/instruments/emotion description
  2. Lyrics (-l): Complete structured lyrics with tags
  3. Parameters: --duration, --bpm, --key, --time-signature, --language

Caption: The Most Important Input

Caption is the most important factor affecting generated music.

Supports multiple formats: simple style words, comma-separated tags, complex natural language descriptions.

Common Dimensions

DimensionExamples
Style/Genrepop, rock, jazz, electronic, hip-hop, R&B, folk, classical, lo-fi, synthwave
Emotion/Atmospheremelancholic, uplifting, energetic, dreamy, dark, nostalgic, euphoric, intimate
Instrumentsacoustic guitar, piano, synth pads, 808 drums, strings, brass, electric bass
Timbre Texturewarm, bright, crisp, muddy, airy, punchy, lush, raw, polished
Era Reference80s synth-pop, 90s grunge, 2010s EDM, vintage soul, modern trap
Production Stylelo-fi, high-fidelity, live recording, studio-polished, bedroom pop
Vocal Characteristicsfemale vocal, male vocal, breathy, powerful, falsetto, raspy, choir
Speed/Rhythmslow tempo, mid-tempo, fast-paced, groovy, driving, laid-back
Structure Hintsbuilding intro, catchy chorus, dramatic bridge, fade-out ending

Caption Writing Principles

  1. Specific beats vague — "sad piano ballad with female breathy vocal" > "a sad song"
  2. Combine multiple dimensions — style+emotion+instruments+timbre anchors direction precisely
  3. Use references well — "in the style of 80s synthwave" conveys complex aesthetic quickly
  4. Texture words are useful — warm, crisp, airy, punchy influence mixing and timbre
  5. Don't pursue perfection — Caption is a starting point, iterate based on results
  6. Granularity determines freedom — Less detail = more model creativity; more detail = more control
  7. Avoid conflicting words — "classical strings" + "hardcore metal" degrades output
    • Fix: Repetition reinforcement — Repeat the elements you want more
    • Fix: Conflict to evolution — "Start with soft strings, middle becomes metal rock, end turns to hip-hop"
  8. Don't put BPM/key/tempo in Caption — Use dedicated parameters instead

Lyrics: The Temporal Script

Lyrics controls how music unfolds over time. It carries:

  • Lyric text itself
  • Structure tags ([Verse], [Chorus], [Bridge]...)
  • Vocal style hints ([raspy vocal], [whispered]...)
  • Instrumental sections ([guitar solo], [drum break]...)
  • Energy changes ([building energy], [explosive drop]...)

Structure Tags

CategoryTagDescription
Basic Structure[Intro]Opening, establish atmosphere
[Verse] / [Verse 1]Verse, narrative progression
[Pre-Chorus]Pre-chorus, build energy
[Chorus]Chorus, emotional climax
[Bridge]Bridge, transition or elevation
[Outro]Ending, conclusion
Dynamic Sections[Build]Energy gradually rising
[Drop]Electronic music energy release
[Breakdown]Reduced instrumentation, space
Instrumental[Instrumental]Pure instrumental, no vocals
[Guitar Solo]Guitar solo
[Piano Interlude]Piano interlude
Special[Fade Out]Fade out ending
[Silence]Silence

Combining Tags

Use - for finer control, but keep it concise:

✅ [Chorus - anthemic]
❌ [Chorus - anthemic - stacked harmonies - high energy - powerful - epic]

Put complex style descriptions in Caption, not in tags.

Caption-Lyrics Consistency

Models are not good at resolving conflicts. Checklist:

  • Instruments in Caption ↔ Instrumental section tags in Lyrics
  • Emotion in Caption ↔ Energy tags in Lyrics
  • Vocal description in Caption ↔ Vocal control tags in Lyrics

Vocal Control Tags

TagEffect
[raspy vocal]Raspy, textured vocals
[whispered]Whispered
[falsetto]Falsetto
[powerful belting]Powerful, high-pitched singing
[spoken word]Rap/recitation
[harmonies]Layered harmonies
[call and response]Call and response
[ad-lib]Improvised embellishments

Energy and Emotion Tags

TagEffect
[high energy]High energy, passionate
[low energy]Low energy, restrained
[building energy]Increasing energy
[explosive]Explosive energy
[melancholic]Melancholic
[euphoric]Euphoric
[dreamy]Dreamy
[aggressive]Aggressive

Lyric Writing Tips

  1. 6-10 syllables per line — Model aligns syllables to beats; keep similar counts for lines in same position (±1-2)
  2. Uppercase = stronger intensity — WE ARE THE CHAMPIONS! (shouting) vs walking through the streets (normal)
  3. Parentheses = background vocals — We rise together (together)
  4. Extend vowels — Feeeling so aliiive (use cautiously, effects unstable)
  5. Clear section separation — Blank lines between sections

Avoiding "AI-flavored" Lyrics

Red FlagDescription
Adjective stacking"neon skies, electric hearts, endless dreams" — vague imagery filler
Rhyme chaosInconsistent patterns or forced rhymes breaking meaning
Blurred boundariesLyric content crosses structure tags
No breathing roomLines too long to sing in one breath
Mixed metaphorsWater → fire → flying — listeners can't anchor

Metaphor discipline: One core metaphor per song, explore its multiple aspects.


Music Metadata

Most of the time, let LM auto-infer. Only set manually when you have clear requirements.

ParameterRangeDescription
bpm30–300Slow 60–80, mid 90–120, fast 130–180
keyscaleKeye.g. C Major, Am. Common keys (C, G, D, Am, Em) most stable
timesignatureTime sig4/4 (most common), 3/4 (waltz), 6/8 (swing)
vocal_languageLanguageUsually auto-detected from lyrics
durationSecondsSee duration calculation below

When to Set Manually

ScenarioSet
Daily generationLet LM auto-infer
Clear tempo requirementbpm
Specific style (waltz)timesignature=3/4
Match other materialbpm + duration
Specific key colorkeyscale

Duration Calculation

Estimation Method

  • Intro/Outro: 5-10 seconds each
  • Instrumental sections: 5-15 seconds each
  • Typical structures:
    • 2 verses + 2 choruses: 120-150s minimum
    • 2 verses + 2 choruses + bridge: 180-240s minimum
    • Full song with intro/outro: 210-270s (3.5-4.5 min)

BPM and Duration Relationship

  • Slower BPM (60-80): Need MORE duration for same lyrics
  • Medium BPM (100-130): Standard duration
  • Faster BPM (150-180): Can fit more lyrics, but still need breathing room

Rule of thumb: When in doubt, estimate longer. A song too short feels rushed.


Note: Lyrics tags (piano, powerful, whispered) are consistent with Caption (piano ballad, building to powerful chorus, intimate).

Frequently asked questions

What does the Acestep Songwriting AI skill do?

Music songwriting guide for ACE-Step. Provides professional knowledge on writing captions, lyrics, choosing BPM/key/duration, and structuring songs. Use this skill when users want to create, write, or plan a song before generating it with ACE-Step.

Why use Acestep Songwriting on TypingMind?

Because you install it once and use it with any model. Acestep Songwriting is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Acestep Songwriting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ace-step/ace-step-skills/tree/main/skills/acestep-songwriting. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Acestep Songwriting?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Acestep Songwriting?

As many as you like. As long as a model supports skills, you can use Acestep Songwriting with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Acestep Songwriting AI skill free?

It is published on GitHub by ace-step. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇