Update to MixMatter

{
  "description": "Turn a user-supplied still image into a short video or motion concept using subtle parallax, camera movement, light flow, or source-appropriate subject motion. Use when the requested deliverable is animated or video. Do not use for a static image, sticker, or captioned meme. Use the host's native video capability when available; otherwise provide a production-ready motion brief or storyboard without claiming a video was rendered.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 104
    }
  ],
  "name": "mixmatter-motion",
  "skill_md_contents": "---\r\nname: mixmatter-motion\ndescription: >-\n  Turn a user-supplied still image into a short video or motion concept using subtle parallax, camera movement, light\n  flow, or source-appropriate subject motion. Use when the requested deliverable is animated or video. Do not use for a\n  static image, sticker, or captioned meme. Use the host's native video capability when available; otherwise provide a\n  production-ready motion brief or storyboard without claiming a video was rendered.\n---\r\n\r\n# MixMatter Motion 3.0\n\nAnimate the source without breaking its identity, physics, or composition.\n\n## Motion plan\n\n1. Read the still image and separate foreground, subject, middle ground, and background only where the image supports that separation.\n2. Identify protected regions: faces, hands, readable text, logos, architecture, and rigid geometry.\n3. Choose one dominant motion idea. Do not stack multiple camera and subject effects merely to make the result look busy.\n4. Honor the selected duration, strength, and loop behavior.\n5. Generate with the host's native video tool. If unavailable, return a concise shot specification and say that rendering was not performed.\n\n## Mode interpretations\n\n- `Parallax`: restrained layer separation with plausible depth; avoid cardboard cutout artifacts.\n- `Push in`: one smooth camera move with a stable focal anchor.\n- `Light flow`: animate light, reflections, haze, water, or shadow only where physically plausible.\n- `Subject motion`: use small source-consistent motion such as breathing, fabric, foliage, water, or an intentional gesture.\n\n## Stability rules\n\n- Keep identity-bearing features stable across frames.\n- Do not morph text, signage, faces, fingers, or rigid lines.\n- For loops, match end framing, velocity, lighting, and subject pose to the opening.\n- Prefer subtle motion at `Subtle`, one readable effect at `Balanced`, and controlled emphasis at `Bold`; bold never means chaotic.\n- Do not invent audio unless requested.\n\n## Delivery check\n\nReview the first frame, midpoint, and final frame for identity drift, edge tearing, geometry wobble, unwanted text mutation, abrupt speed changes, and loop discontinuity.\n"
}