Update to OpenArt

{
  "description": "Build Talking Head Video through OpenArt MCP when one person addressing the camera is the main format. Use for direct-to-camera explanations, product recommendations, teaching, opinions, announcements and spokesperson messages, with expressive delivery and meaningful same-shot demonstrations. Casual or polished setups are supported. Explicit UGC lifestyle or professionally staged PGC briefs retain their dedicated skills; edited ads with B-roll fall outside this skill.",
  "included_files": [
    {
      "relative_path": "README.md",
      "size_in_bytes": 2786
    },
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 352
    },
    {
      "relative_path": "references/creative-preflight.md",
      "size_in_bytes": 5446
    },
    {
      "relative_path": "references/generation-approval.md",
      "size_in_bytes": 8362
    },
    {
      "relative_path": "references/intake-and-script.md",
      "size_in_bytes": 5271
    },
    {
      "relative_path": "references/intent-and-script-development.md",
      "size_in_bytes": 10663
    },
    {
      "relative_path": "references/music-and-sound.md",
      "size_in_bytes": 3943
    },
    {
      "relative_path": "references/openart-execution.md",
      "size_in_bytes": 3915
    },
    {
      "relative_path": "references/opening-hooks.md",
      "size_in_bytes": 4636
    },
    {
      "relative_path": "references/performance-and-prompts.md",
      "size_in_bytes": 4423
    },
    {
      "relative_path": "references/product-understanding.md",
      "size_in_bytes": 6399
    },
    {
      "relative_path": "references/recommendation-examples.md",
      "size_in_bytes": 7828
    },
    {
      "relative_path": "references/recommendation-writing.md",
      "size_in_bytes": 12002
    },
    {
      "relative_path": "references/reference-understanding.md",
      "size_in_bytes": 3654
    },
    {
      "relative_path": "references/review-and-delivery.md",
      "size_in_bytes": 4705
    },
    {
      "relative_path": "references/segmentation-and-continuity.md",
      "size_in_bytes": 2413
    },
    {
      "relative_path": "references/video-experience.md",
      "size_in_bytes": 10376
    }
  ],
  "name": "talking-head",
  "skill_md_contents": "---\nname: talking-head\ndescription: Build Talking Head Video through OpenArt MCP when one person addressing the camera is the main format. Use for direct-to-camera explanations, product recommendations, teaching, opinions, announcements and spokesperson messages, with expressive delivery and meaningful same-shot demonstrations. Casual or polished setups are supported. Explicit UGC lifestyle or professionally staged PGC briefs retain their dedicated skills; edited ads with B-roll fall outside this skill.\n---\n\n# Build Talking Head Video\n\nBefore interpreting any brief, script or timecoded draft, read\n[intent and script development](references/intent-and-script-development.md). Preserve the intended message,\nrequired facts and exact keywords; actively improve expression, reasoning, actions and flexible beat timing\nin this skill's style. Input detail is not an instruction to execute verbatim. Explicit exact-execution\nconstraints and an approved version requested unchanged remain locked.\n\nWhen the Script Plan revises supplied creative input, END that response by briefly explaining what changed\nand why, then ask whether to use the revised script or follow the original input exactly. Resolve that\nversion choice before generation under [generation approval](references/generation-approval.md);\na Draft/full-quality choice alone is not acceptance of the rewrite.\n\nBefore authoring, read [shared video experience](references/video-experience.md) and\n[product understanding](references/product-understanding.md). Before a generation decision, read\n[generation approval](references/generation-approval.md), including native question UI and wording examples.\nComplete the full prompt and matching readable Script Plan before presenting the plan; include every\nspoken and added on-screen word. Default to Seedance 2.5 Draft preview. Explicit high-quality/full-quality\ndelivery defaults directly to Seedance 2.5, not another model. Reuse explicit approval and approval waivers.\n\nThe person addressing the viewer is the organizing form. A continuous shot can contain a question,\ndemonstration, closer look, reaction and useful conclusion. Do not reduce the video to a motionless face\nreading short slogans. Choose the setup from the message and audience rather than automatically imposing\neither UGC informality or PGC studio polish. High-quality delivery describes the render choice, not a genre.\nAn explicitly requested Talking Head video stays here even when it shares craft with UGC or PGC.\n\nRead supporting guides when their decision arises; [README](README.md) explains installation and outputs.\nUse the user's conversation language and commissioned speech/text languages. Honor analysis-only and\nprompt-only requests without generating media.\n\n## Establish what the person is helping the viewer understand\n\nRead [intake and script](references/intake-and-script.md). Establish the message, audience, presenter,\nsetting, tone, language, ratio, desired duration and actual generation scope. Reuse supplied information;\nask only about meaningful gaps. For non-product explanation, do not demand product images or promotional copy.\n\nFor uploaded reference videos, read [reference understanding](references/reference-understanding.md).\nInspect complete picture and sound, including phrasing, pauses, emotional emphasis, product handling and\nthe ending. Distinguish observation from inference and identity from creative inspiration. If the user\nsupplies only a social-video URL, request the file; there is no link downloader in this skill.\n\nA real presenter's recording can guide identity/performance within the live model's supported capabilities.\nPhotos establish appearance, not voice. Direct a fictional presenter when no real identity is requested;\ndo not force personal uploads or invent real testimony, credentials, product trials or use history.\n\n## Author the opening and the useful conversation\n\nRead [opening hooks](references/opening-hooks.md). The first 3–5 seconds should establish a relevant reason\nto watch: a specific question, familiar situation, worthwhile curiosity or visible operation. In product\npromotions, the product is visible from the first image, naturally held or used. It need not be named in\nthe first sentence. Non-product videos start with their relevant subject rather than a fabricated product.\n\nBefore developing or improving recommendation copy, read [recommendation writing](references/recommendation-writing.md)\nand the [latte reference](references/recommendation-examples.md). Transfer the connection between supported\ndetails, visible use and everyday relevance; do not copy a creator's biography or catchphrases. Teaching\nand opinion videos use the same connected reasoning without a forced offer or CTA.\n\nRead [creative preflight](references/creative-preflight.md) and\n[performance and prompts](references/performance-and-prompts.md). Write the complete native prompt first\nor alongside its matching Script Plan. Direct meaningful shifts in intention, gaze, selective emphasis,\nnatural pace and physically plausible handling. Give useful actions enough time without stalling the thought.\nShow timed plan rows even for a single take so the user can review speech, action and text together.\n\nKeep the presenter as the visual anchor throughout each clip. Default to a continuous shot with same-shot\nproduct demonstration when relevant. Native captions or short labels can be planned when requested or\nuseful to the brief, but all exact text belongs in both prompt and Script Plan. Explicit clean-footage\nrequests omit added text. No B-roll montage, external dubbing, local editing or hidden later composition\nis included. Resolve a request requiring those capabilities rather than promising an unfinished pipeline.\n\nRead [music and sound](references/music-and-sound.md). Promotional takes normally include fitting light\nBGM beneath intelligible speech. Podcasts, interview-like delivery, sound-led demonstrations and explicit\ndialogue-only requests may remain unscored. Put the actual decision in the prompt and readable plan.\n\nRead [OpenArt execution](references/openart-execution.md) before fixing references, duration or clip count.\nResolve actual Seedance 2.5 Draft or full-quality capabilities, references, audio, duration and pricing\nthrough live tools. Read [segmentation and continuity](references/segmentation-and-continuity.md) when the\nspeech exceeds the live request limit or variants are requested. Prefer one take when it fits; otherwise split\nat complete thoughts, preserve voice/identity/product continuity and explain the separate-clip delivery.\nDo not label unassembled clips as one uninterrupted video or rush dialogue to fit.\n\n## Generate the selected version\n\nSubmit the stored authorized prompt version with its selected settings through\n[OpenArt execution](references/openart-execution.md); save the receipt and recover outstanding jobs before\ncreating replacements.\n\nFollow the shared experience for preview review, revisions and an authorized same-video HD upgrade.\nDo not substitute a fresh random generation for an upgrade or silently change the video model.\n\n## Review and deliver\n\nUse [review and delivery](references/review-and-delivery.md). Check the full performance and opening,\nspeech including brand names/prices, product appearance/actions, lip sync, exact planned text, music and\nending. A screenshot or successful job is not proof of human delivery. Mark unavailable checks unverified.\n\nDeliver the selected preview or full-quality original video, or the explicitly agreed ordered clip set,\nwith its Script Plan/prompt version, settings, receipts and honest review status. Show a preview as a\npreview, and offer only the upgrade that the actual selected result supports.\n"
}