agentleFS
badgidsbadgids/Story-Film-Skills/skills/ace-step-xl/SKILL.md

ace-step-xl

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Adapt score or song cues into ACE-Step 1.5 XL inputs using task type, caption, lyrics or instrumental structure, BPM, key, time signature, and temporal performance directions.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read music cue and score motif rules.

    line 24
  2. Very specific:

    Put global musical identity in caption.

    line 25
  3. Very specific:

    Put time-varying structure, section changes, performance shifts, and lyrics in lyrics.

    line 26
  4. Distinctive:

    Do not overload caption with a second-by-second timeline that belongs in structure.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

ACE-Step 1.5 XL Prompting

ACE-Step XL uses the same control pattern as ACE-Step 1.5 with a larger 4B DiT decoder.

Core fields

  • task_type: usually text2music, or another supported transform task when the source cue requires it
  • caption: overall genre, instruments, mood, atmosphere, timbre, vocal identity, production, and progression
  • lyrics: lyric text plus section and temporal performance information. For instrumental score, use [Instrumental] and structure markers as needed
  • bpm: 30 to 300 when a fixed tempo matters
  • keyscale: musical key when useful
  • timesignature: meter when useful

Workflow

  1. Read music cue and score motif rules.
  2. Put global musical identity in caption.
  3. Put time-varying structure, section changes, performance shifts, and lyrics in lyrics.
  4. Do not overload caption with a second-by-second timeline that belongs in structure.
  5. Choose XL variant only as execution metadata: xl-turbo for fast high-quality iteration, xl-sft for tunable higher-quality sampling, xl-base when the task requires base-model transform features.
  6. Save under 04_generation/prompts/ace-step-xl/<cue-id>.json.

Done

Global musical identity and temporal structure are separated cleanly, and the prompt reflects the cue's dramatic job and hit points.

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.