Update to ImagineArt

{
  "name": "brand",
  "description": "Logos, animated logo reveals, and full visual identity — palette, typography pairing, and brand applications. Use when the user is establishing or refreshing a brand, or wants a logo. Not for a single social graphic (use Social Studio).",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 474
    },
    {
      "relative_path": "assets/ATTRIBUTION.md",
      "size_in_bytes": 937
    },
    {
      "relative_path": "assets/icon.svg",
      "size_in_bytes": 549
    },
    {
      "relative_path": "references/errors.md",
      "size_in_bytes": 2325
    },
    {
      "relative_path": "references/identity.md",
      "size_in_bytes": 1668
    },
    {
      "relative_path": "references/models.md",
      "size_in_bytes": 3809
    },
    {
      "relative_path": "references/qa.md",
      "size_in_bytes": 870
    }
  ],
  "skill_md_contents": "---\nname: brand\ndescription: Logos, animated logo reveals, and full visual identity — palette, typography pairing, and brand applications. Use when the user is establishing or refreshing a brand, or wants a logo. Not for a single social graphic (use Social Studio).\n---\n\n# Brand Studio\n\nRead `references/identity.md` for the identity method.\n\n> **Partly implemented.** `generate_logo` and `generate_3d_logo_animation` are real tools.\n> Palette generation, typography pairing and brandbook export are **not built server-side**.\n> Produce those as structured text plus generated sample imagery, and say plainly which\n> parts aren't exportable as files yet. Never imply a downloadable brandbook exists.\n\n## Tokens\n\n| Token | What it does |\n|---|---|\n| `/logo` | Static mark — three directions |\n| `/logo-reveal` `/logo-3d` | Cinematic 3D animated reveal |\n| `/palette` | Colour system with roles |\n| `/typography` | Display + body pairing |\n| `/brandbook` | The full identity, assembled |\n\n## Truth gate — claims\n\n- **The claims the user supplies are the complete allowlist.** Preserve each as written.\n  Never strengthen, combine, or infer a new claim from them.\n- **With no claims supplied**, write only about what is directly observable — materials,\n  controls, how it is used, what is included.\n- **No superlatives you cannot support** — \"best\", \"revolutionary\", \"#1\". They read as\n  advertising and fail on review.\n- **No comparison to a named competitor.**\n\n## Logos\n\n`generate_logo`. Ask for exactly three things: the **name**, what the **business does**,\nand any **style direction**. If they gave the first two, infer the third and say what you\nassumed. Don't run a questionnaire.\n\n**Generate three distinct directions, not one.** Logo choice is comparative — name what\ndistinguishes each in a line.\n\n## Logo reveals\n\n`generate_3d_logo_animation` takes `logo_image_url` and runs the whole recipe in one call:\nit converts the flat 2D logo to 3D (nano-banana-2), waits, then animates the reveal\n(veo-3.1-fast).\n\n**It blocks for up to a minute before returning.** Say so before calling it, or the wait\nreads as a hang.\n\n### When the reveal fails — observed recovery\n\n`generate_3d_logo_animation` is a two-stage pipeline: 3D still first, then animation.\n**Stage two can fail after stage one succeeded.** Observed in testing, along with what\nactually worked:\n\n| Attempt | Result |\n|---|---|\n| Full pipeline | 3D still succeeded, animation failed |\n| Retrying the full pipeline | Timed out |\n| Animating the **original** logo directly with `ltx-2.3` | Completed |\n\nSo the recovery, in order:\n\n1. **Do not blindly re-run the whole tool.** Stage one already cost time and credits, and\n   re-running it is what caused the timeout.\n2. **Retry the full pipeline at most once.** If it fails again, stop retrying it.\n3. **Fall back to direct animation:** `generate_video` with the logo as `image_url`\n   (exactly one URL), `ltx-2.3`, duration `6`, resolution `1080p`. This produced a usable\n   reveal when the dedicated tool could not.\n4. **Say what you did** — the fallback is a different look from the 3D pipeline, and that\n   is a material change the user needs to know about.\n\nIf the intermediate 3D still is recoverable from the assets list, animate *that* rather\nthan the flat original — it is closer to the intended result.\n\n## Identity\n\nMethod in `references/identity.md`. The rule that matters:\n\n**Every asset generated after the palette is set must use it.** A brand kit whose own\nsample images ignore its palette is worthless. Carry the hex values into every subsequent\nprompt, explicitly.\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"
}