Update to PixVerse

{
  "description": "Explainer video: turn a topic, article or script into a complete narrated film, including editorial documentary motion graphics, animated explanations, history, kids and picture stories, in any consistent non-photoreal look.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 282
    },
    {
      "relative_path": "references/block-prompt.md",
      "size_in_bytes": 7832
    },
    {
      "relative_path": "references/branches.md",
      "size_in_bytes": 6551
    },
    {
      "relative_path": "references/channels-and-formats.md",
      "size_in_bytes": 4324
    },
    {
      "relative_path": "references/editorial-motion-graphics.md",
      "size_in_bytes": 5327
    },
    {
      "relative_path": "references/model-route.md",
      "size_in_bytes": 2705
    },
    {
      "relative_path": "references/production.md",
      "size_in_bytes": 6857
    },
    {
      "relative_path": "references/regression-cases.md",
      "size_in_bytes": 4581
    },
    {
      "relative_path": "references/script.md",
      "size_in_bytes": 5316
    },
    {
      "relative_path": "references/style-grammar.md",
      "size_in_bytes": 3252
    },
    {
      "relative_path": "references/styles-color-and-shape.md",
      "size_in_bytes": 18425
    },
    {
      "relative_path": "references/styles-drawn-and-frame.md",
      "size_in_bytes": 24079
    },
    {
      "relative_path": "references/styles-history.md",
      "size_in_bytes": 15685
    },
    {
      "relative_path": "references/styles-material-and-story.md",
      "size_in_bytes": 14385
    },
    {
      "relative_path": "references/visual-approaches.md",
      "size_in_bytes": 2683
    }
  ],
  "name": "pixverse-explainer",
  "skill_md_contents": "---\nname: pixverse-explainer\ndescription: \"Explainer video: turn a topic, article or script into a complete narrated film, including editorial documentary motion graphics, animated explanations, history, kids and picture stories, in any consistent non-photoreal look.\"\n---\n\n# Explainer Videos\n\nA faceless narrated film is a fast, concrete story told twice at once: the narrator\nsays it and the picture acts it out, phrase by phrase, in one locked look. Run the\nphases below in order. Each phase names the one file that holds its templates; open it\nwhen the phase says so and fill the templates in rather than inventing new structure.\n\n## Golden Rules\n\n1. **Story, not essay.** People, objects, dates and numbers doing things. \"A silk\n   merchant ordered a portrait of his wife. Leonardo never delivered it.\" beats\n   \"Fame can grow from an absence.\" Abstract nouns belong in neither voice nor picture.\n2. **Every spoken phrase gets a visible verb.** While the narrator says it, something\n   on screen does it: a figure walks off with the panel, glaze sheets stack, a hand\n   lifts the painting out of its frame, a crowd grows row by row.\n3. **A shot is a process, never a pose.** Motion starts on frame one and the picture\n   reaches a new state about every second. Elements enter staggered, land with weight,\n   and the next thing is already arriving. Nothing sits still for a full second.\n4. **Fill the frame.** The hero subject occupies a third to two thirds of frame\n   height. Small props lost in empty paper read as a slide deck.\n5. **Use actors.** Figures in the film's look perform the story with their bodies,\n   mouths closed; the narrator does the talking. A giant hand, a stamp, a crowd are\n   actors too. Diagrams appear when the story reaches a quantity or comparison.\n6. **One look, pasted not paraphrased.** Take the selected style's FORMULA from its\n   recipe file and paste it byte-identical into every image and video prompt. Style\n   words live only there; shot lines are pure choreography.\n7. **Compose from the roster.** Every block references its stage, cast and props\n   images. Never animate from the style key alone.\n8. **Prompts say what happens.** Write positive, visible instructions. Keep exclusions\n   to the single NEGATIVE line of the block template. No commentary, no reasons, no\n   \"this shows that…\" inside a prompt.\n9. **Narration is brisk and fills the film.** Natural TTS speed (0.95–1.05, never a\n   slowed read), each block's line filling 8.2–9.6s of its 10s window.\n10. **Words on screen come from the edit.** Generated video carries no letters or\n    digits; captions and exact labels are burned in afterwards.\n\n## Pipeline\n\n**Phase 0 — Resolve the brief.** Topic, language, duration, aspect (16:9 default),\nchannel, look, captions, music, cover. Use what the user gave; pick sensible defaults\nfor the rest, state them in one line and continue. `./references/channels-and-formats.md`\nmaps channels; Kids, talking cast, song, stills and 10-minute history load\n`./references/branches.md`. Model route: `./references/model-route.md`.\n\n**Phase 1 — Script.** Open `./references/script.md`. Research, pick the through-line,\nwrite the block lines, run its rewrite pass. Gate: every line passes the phrase→verb\ntest and the word budget.\n\n**Phase 2 — Look.** `./references/style-grammar.md` indexes the recipes; open the one\nselected recipe and copy its FORMULA, MOTION token and PALETTE LOCK, locking the accent\ncolour. Generate one style key. Gate: the key shows the look on a real subject.\n\n**Phase 3 — Roster.** Follow the roster section of `./references/production.md`:\ncast, stage plates, props, each generated with the style key attached and the FORMULA\npasted. Gate: every noun the script puts on screen has an image.\n\n**Phase 4 — Narration.** Follow `./references/production.md`: generate one take per\nblock with the locked voice, measure it, and read off the phrase clock. Gate: every\ntake fills its window.\n\n**Phase 5 — Block prompts and generation.** Open `./references/block-prompt.md`. Fill\nits template once per 10s block with shot boundaries from the phrase clock, run its\nchecklist, submit all blocks in one queue.\n\n**Phase 6 — Assemble.** Follow `./references/production.md`: check the blocks for the\nnamed defects, assemble, mix, burn captions. Deliver one film plus caption/timing files\nand sources.\n\nPrompt-only requests deliver the script with its phrase→verb tables, roster prompts,\nblock prompts on an even shot grid and estimated caption cues in one document, with no\ngeneration and without the Execution section below. A narrow request for one still or one clip uses the\nsimpler direct route.\n\n## Execution\n\nRead `../../skills-shared/production-brief.md` for reference roles and revisions.\nFor media execution follow `../../skills-shared/cli-workflow.md`; load the gateway before\nmanual CLI commands or queue specs. Resolve the plugin root from this skill's installed\npath: set `PVX=\"<absolute-plugin-root>/scripts/pvx\"` and invoke `\"${PVX}\"`. The block\ntemplate in this skill already is the finished Seedance prompt; pass it through prompt\nenhancement unchanged.\n"
}