Update to PixVerse

{
  "description": "Unboxing video: build a believable package-opening sequence whose reveal leads to the actual product, with consistent hands, packaging and sound.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 297
    },
    {
      "relative_path": "references/production.md",
      "size_in_bytes": 8373
    }
  ],
  "name": "pixverse-unbox-video",
  "skill_md_contents": "---\nname: pixverse-unbox-video\ndescription: \"Unboxing video: build a believable package-opening sequence whose reveal leads to the actual product, with consistent hands, packaging and sound.\"\n---\n\n# Unboxing Video\n\nWhen this workflow generates images or video, apply `../../skills-shared/quality-policy.md`:\nSunburst 2K/high for images, Seedance 2.5 1080p with automatic prompt enhancement for video,\nand a stopped upgrade/fallback choice for Free/Basic or model-entitlement rejection.\n\n\nMake the reveal follow the package's real construction. Read `./references/production.md`\nbefore the board or prompt: the four-part arc, opening branches, timing, performance,\nhand allocation and closing transition are core production rules.\n\n## Establish The States\n\nInspect the outer package, opening mechanism, inner tray and verified contents. The standard\narc begins with a closed package. If only an open reference exists, reconstruct a closed\nstate only when the visible parts support it; otherwise resolve missing evidence. Preserve\nan explicit already-open brief, but do not silently choose it for a requested full unboxing.\n\nUse four active 9:16 slots on a 21:9 board: PACKED → REVEAL → PRODUCT-FOCUS → SATISFACTION.\nCreate and refine the board, then use clean board + creator + product for the video.\nOne package in cut 1; its correct opening ends that cut. The product emerges in cut 2;\nthe package may remain at an edge there, then disappears for cuts 3–4. One product and\ntwo explicitly assigned hands; don't re-open or re-pack between beats.\n\nUse a visible creator by default, preserving an explicit hands-only request. Default POV is\nfixed → fixed → fixed close-up → selfie. For 12s, allocate 3 / 3.5 / 2.5 / 3 seconds.\nWrite four timed Cut sections. Usually there are three hard cuts; on an eligible closing\nclip the reference requires one continuous Pick-Up instead of the final boundary.\n\n## Write The Performance\n\nEach cut describes one distinct action in motion, real grip/weight, at least five small\nobservable changes and its exact dialogue/sound. First sound within .4s; natural anticipation,\none real reveal peak, detail observation, satisfied resolution. Keep mouths unobstructed\nfor visible speech. No slow-lift/slow-rotate/long-hold default. The reference supplies\nthe package-specific mechanics and caption/ending rules; do not substitute a generic box.\n\nIf a long opening exceeds a credible short shot, divide it at a real state change. Do not cover impossible package motion with a rapid cut and claim the demonstration was checked.\n\n## Finish\n\nCheck hands, lid geometry, contents count, insert and the reveal's clarity. Preserve native package sounds when useful. For a reaction line, keep spoken experience fictional or user-supplied instead of asserting a real testimonial. Add captions only when requested. Deliver the completed edit; repair only the broken state or transition.\n\n## Execution\n\nRead `../../skills-shared/production-brief.md` for reference roles, prompt construction and revisions.\nFor media execution, follow `../../skills-shared/cli-workflow.md`; load the gateway before manual\nCLI commands or queue specs. Resolve the plugin root from this skill's installed path:\nset `PVX=\"<absolute-plugin-root>/scripts/pvx\"` and invoke `\"${PVX}\"` with the documented arguments.\nPrompt-only work ends with the usable plan and prompts; it needs no account or generation calls.\n"
}