Update to Moda - Slides & Designs

{
  "description": "Canvas motion, animation, photo slideshows, and timeline composition using uploaded or existing footage — including Main Edit timeline cuts, visual tracks, and transitions. Export editable designs as mp4/gif with moda-video-motion. New audio/video generation is unavailable through this connector.",
  "included_files": [
    {
      "relative_path": "references/charts.md",
      "size_in_bytes": 5659
    },
    {
      "relative_path": "references/design-quality.md",
      "size_in_bytes": 22265
    },
    {
      "relative_path": "references/edit-code.md",
      "size_in_bytes": 16488
    },
    {
      "relative_path": "references/export.md",
      "size_in_bytes": 7949
    },
    {
      "relative_path": "references/gotchas.md",
      "size_in_bytes": 8693
    },
    {
      "relative_path": "references/markup.md",
      "size_in_bytes": 23958
    },
    {
      "relative_path": "references/omni-and-media.md",
      "size_in_bytes": 7338
    },
    {
      "relative_path": "references/reading-and-verifying.md",
      "size_in_bytes": 21129
    }
  ],
  "name": "moda-video",
  "skill_md_contents": "---\nname: moda-video\ndescription: >-\n  Canvas motion, animation, photo slideshows, and timeline composition using\n  uploaded or existing footage — including Main Edit timeline cuts,\n  visual tracks, and transitions. Export editable designs as mp4/gif with\n  moda-video-motion. New audio/video generation is unavailable through this\n  connector.\n---\n\n# moda-video\n\n**PREREQUISITE — `load_skill(\"moda-core\")` once per session** (step-0, write\ncontract, free/metered map). Already loaded? Skip ahead. If you cannot load\nit, the non-negotiables: call `moda_bootstrap` before anything; `brand_list`\nbefore creating; revision-guarded writes use `expected_revision` from your last read.\n`canvas_edit_image` captures its own target state and has no revision argument.\nOn `stale_revision`, re-read and retry once; send the canvas link\nthe moment it exists; stuck or failed? `ask_expert(\"<question>\")` — free and\nfast, never guess.\n\n## Recipes\n\n| Recipe | When it owns the ask |\n|---|---|\n| `moda-video-clip` | New audio/video generation is unavailable through this connector. |\n| `moda-video-motion` | Canvas keyframes, animated type/logos, photo slideshows, existing-clip timeline compositing (cuts, visual tracks, transitions) and mp4/gif export. |\n\nRoute motion and video composition to `moda-video-motion`. Upload existing\nfootage or select team video files; do not promise to create missing footage.\nAnimate photos, text, logos and vector designs with canvas keyframes. For an\nask requiring new generated audio or video, explain that the connector cannot\ndo it. Cutting a large folder of LOCAL footage into a film is Moda's local\ncommand-line footage lane, not this connector — it runs on the machine\nthat holds the clips (see moda.app docs: Moda for agents). A pasted canvas plus\n\"export as mp4/gif\" uses the motion/export flow.\n\n## Family facts\n\nKeep text, prices and brand marks as editable canvas layers over footage.\nInspect existing clips with `media_video_frames(video='file_…')` before using\nthem; an empty frame list means decoding failed, not that the footage is bad.\nKeyframes and clip sequencing require `canvas_create(category='animation')`;\nshader fills animate on ordinary canvases too.\n\nExport one animation page with `export(format='mp4'|'gif', page=N)`, or stitch\nvisible pages into one mp4 using `export(canvas_ref, format='mp4', scope='sequence')`.\nA canvas with a persisted Main Edit timeline exports it with\n`scope='main_edit'` (mp4 only, page-less like sequence). Stitched scopes have\nno `page` argument; gif exports remain per-page. `fps` picks the capture rate\n(mp4 24|30|60 default 30; gif 10|12|15|24 default 12). One mp4 film has an\n**18000-frame / 600 s ceiling** (600 s at 30 fps — 60 fps halves it; gif\n9000 frames / 300 s), and transitions or overlapping visual tracks lower the\ncomposited ceiling (references/export.md). Shorten or split larger\ncompositions. A page without motion is refused with `no_animation`; deliver a\nstill and the canvas link when appropriate. Screenshots capture one frame.\n\nExisting unmuted clip audio can be muxed into mp4; inspect export warnings for\n`audio_source_dropped`. This connector cannot create audio tracks, generate\nvideo, or perform generative video edits. See references/export.md for full\nexport settings and limits.\n\n## Money\n\nCanvas motion authoring, screenshots and mp4/gif exports are free. Iterate on\nthe canvas until the timing, legibility and framing work. There is no paid\nvideo/audio generation lane through this connector.\n\n## Delivering\n\nThe live canvas link first whenever a canvas exists, then the file and its\nusage receipt. One adjacency offer at most: sized stills of the same piece\n(moda-social) or a recurring cut (moda-automate).\n\n## Errors\n\nAny typed error → moda-core's recovery reference. `stale_revision`: re-read and\nretry once — it heals.\n\nSee also: moda-core — contract, routing ladder, everything Moda can do.\n\n## References\n\n| Doc | Load when |\n|---|---|\n| references/export.md | mp4/gif rules, per-page exports, warnings |\n| references/gotchas.md | the blank-static-export trap and other surprises |\n| references/reading-and-verifying.md | screenshot loop, degraded verify without vision |\n| references/markup.md, references/edit-code.md | placing a clip and authoring motion on a canvas |\n| references/design-quality.md, references/charts.md, references/omni-and-media.md | type ladder and imagery; a data page in the cut; metered-lane semantics |\n"
}