Update to ImagineArt

{
  "name": "music",
  "description": "Music, jingles and soundtracks. Use when the user wants audio generated — a track, a background bed, a jingle for an ad. Not for adding captions or subtitles to a video (use Social Studio).",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 465
    },
    {
      "relative_path": "assets/ATTRIBUTION.md",
      "size_in_bytes": 935
    },
    {
      "relative_path": "assets/icon.svg",
      "size_in_bytes": 306
    },
    {
      "relative_path": "references/errors.md",
      "size_in_bytes": 2325
    },
    {
      "relative_path": "references/models.md",
      "size_in_bytes": 3809
    },
    {
      "relative_path": "references/qa.md",
      "size_in_bytes": 369
    }
  ],
  "skill_md_contents": "---\nname: music\ndescription: Music, jingles and soundtracks. Use when the user wants audio generated — a track, a background bed, a jingle for an ad. Not for adding captions or subtitles to a video (use Social Studio).\n---\n\n# Sound\n\n## Tokens\n\n`/music` `/soundtrack` `/jingle` `/bed`\n\n## Workflow\n\n`generate_music`. The audio widget polls itself — don't call `fetch_music_status`. On a\ntext-only host, poll it with `sync: true` until `complete` or `error`.\n\n## Ask for the three things that matter\n\n**Genre, mood, and length.** Length matters most — a bed for a 15-second ad and a track\nfor a three-minute video are different requests.\n\nIf they're scoring something they already generated, **match its duration** rather than\nasking. Look it up rather than making them tell you.\n\n## Useful defaults\n\n- Scoring an ad → instrumental, no vocals, a clear build in the last third\n- Background bed → low-dynamic, nothing that competes with a voiceover\n- Jingle → short, hook-forward, memorable in under 10 seconds\n\n## Paywall\n\nMusic generation requires a paid organization. Relay subscription refusals verbatim —\nthey carry the upgrade link.\n\n## Conventions\n\nNever print `org_id`, `folder_id`, or raw asset uuids.\n\n## When something fails\n\nRead `references/errors.md`. Identify the kind of failure before responding: pending jobs\nare waited on, technical errors retried at most twice, unsupported capabilities stated\nplainly, safety refusals never routed around, and every material change disclosed.\n\n## QA before delivery\n\nRun `references/qa.md` before calling this finished. Inspect the actual output — never\nclaim quality you have not observed, and say plainly what you could not verify.\n"
}