Update to OpenArt

{
  "description": "Generate professional presenter-led PGC footage with Seedance through OpenArt MCP. Use for camera-facing product reviews, expert explainers, educational presentations and scripted spokesperson takes with deliberate lighting and stable camera framing. Includes intake, full reference analysis, script, performance, multi-clip continuity and audiovisual QA. Deliver individual takes with native speech, without B-roll or post-production. Casual phone-native lifestyle sharing belongs to UGC.",
  "included_files": [
    {
      "relative_path": "README.md",
      "size_in_bytes": 4013
    },
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 339
    },
    {
      "relative_path": "references/creative-preflight.md",
      "size_in_bytes": 5448
    },
    {
      "relative_path": "references/generation-approval.md",
      "size_in_bytes": 8362
    },
    {
      "relative_path": "references/intake-and-script.md",
      "size_in_bytes": 5017
    },
    {
      "relative_path": "references/intent-and-script-development.md",
      "size_in_bytes": 10663
    },
    {
      "relative_path": "references/music-and-sound.md",
      "size_in_bytes": 3946
    },
    {
      "relative_path": "references/openart-execution.md",
      "size_in_bytes": 3847
    },
    {
      "relative_path": "references/opening-hooks.md",
      "size_in_bytes": 4636
    },
    {
      "relative_path": "references/performance-and-prompts.md",
      "size_in_bytes": 4329
    },
    {
      "relative_path": "references/product-understanding.md",
      "size_in_bytes": 6399
    },
    {
      "relative_path": "references/recommendation-examples.md",
      "size_in_bytes": 7822
    },
    {
      "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": 4515
    },
    {
      "relative_path": "references/segmentation-and-continuity.md",
      "size_in_bytes": 2413
    },
    {
      "relative_path": "references/video-experience.md",
      "size_in_bytes": 10376
    }
  ],
  "name": "pgc",
  "skill_md_contents": "---\nname: pgc\ndescription: Generate professional presenter-led PGC footage with Seedance through OpenArt MCP. Use for camera-facing product reviews, expert explainers, educational presentations and scripted spokesperson takes with deliberate lighting and stable camera framing. Includes intake, full reference analysis, script, performance, multi-clip continuity and audiovisual QA. Deliver individual takes with native speech, without B-roll or post-production. Casual phone-native lifestyle sharing belongs to UGC.\n---\n\n# OpenArt PGC\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 its matching readable Script Plan before showing either for approval; keep\nall spoken and on-screen text in that same version. Default to Seedance 2.5 Draft preview; explicit\nhigh-quality/full-quality delivery defaults directly to Seedance 2.5. Reuse clear approval or an explicit\napproval waiver. These shared rules own the experience flow across every video and variant.\nFor presenter-led promotions, also read [opening hooks](references/opening-hooks.md): establish relevance\nin the first 3–5 seconds and show the product from the first image without forcing a spoken brand pitch.\n\nRead the entrypoint and these shared workflow guides, then follow the relevant references linked below.\nSupporting Markdown is loaded on demand, not automatically in full. Read reference-analysis guides\nfor uploaded reference videos, product research for product URLs, direction before authoring, OpenArt\nexecution before fixing references, duration or request counts, and review before acceptance. Follow nested\nlinks when that decision requires them.\n\nPGC here means deliberately produced, camera-facing presenter footage: a considered camera position,\ncontrolled lighting, clear sound and purposeful explanation. A studio, desk, workshop or well-lit home setup\ncan all fit. The speaker can be warm and conversational; professional does not mean rigid or an announcer voice.\nUse this route for reviews, explainers, tutorials and spokesperson presentations within the footage boundary.\nCasual selfie-style daily sharing is a different creative mode, not a lower-quality version of PGC.\n\nMake clean presenter footage ready for the user's later editing. Deliver one or more independent Seedance\nclips with their generated speech, appropriate native background music and generation records. Music is\nnormally light and subordinate to the explanation; omit it for unscored formats or explicit clean-dialogue requests.\nDo not concatenate, trim, composite, caption, add music in post, dub through an external pipeline, or create a\nfinal advertising edit. OpenArt Dub Video can make a language version of an accepted take; see\n[OpenArt execution](references/openart-execution.md).\nThis workflow does not require Hypit CLI or its project formats.\nFor installation and input/output expectations, see [README](README.md).\n\nMatch the user's conversation language and requested spoken language. A prompt's direction language does not\ndetermine the language of its dialogue. Honor an explicit prompt-only request without submitting generation.\n\nBefore authoring or revising prompts, read [creative preflight](references/creative-preflight.md).\nProduct images and a short brief are a valid starting point; actively design progression and\nperformance within this skill's boundary. Audit the final prompt for unjustified restrictions before submission.\n\n## Establish the footage brief\n\nRead existing decisions and material before asking questions. Establish the intended message, presenter,\nspoken language, aspect ratio, target speech length, requested Seedance version if any, and fixed choices.\nUse [intake and script](references/intake-and-script.md) to classify references, develop missing copy, and record\nwhat stays or changes. Do not demand personal uploads when a fictional presenter is appropriate.\n\nFor a supplied video, use [reference understanding](references/reference-understanding.md): examine the whole\nsource, including sound and ending, and separate its performance from its editing and graphic treatment.\nTransfer the requested delivery, framing and rhetorical structure into presenter footage. A creative reference\ndoes not automatically supply the target person's identity, voice or product claims.\n\nIf the user needs an exact edit of source footage or a finished ad with supporting visuals, explain that this\nfootage workflow covers the generation stage only. Do not silently promise that a new take preserves source pixels,\ntiming or audio, or expand the delivery into post-production.\n\nBefore developing or improving copy, read [recommendation writing](references/recommendation-writing.md) and\n[latte reference script](references/recommendation-examples.md). Build specific reasons and meaningful same-shot\nproduct use before adding performance directions. Professional presentation still needs human warmth,\naudience relevance and naturally integrated commercial information.\n\n## Direct and divide the performance\n\nRead [performance and prompts](references/performance-and-prompts.md) for identity, voice, physical action,\nreference binding and exact dialogue. Use existing references directly when supported. An optional still-image\ngeneration through OpenArt MCP may establish a missing identity/scene anchor; it is a dependency, not B-roll.\nRead [music and sound](references/music-and-sound.md) to choose a fitting music treatment or a deliberate\nunscored exception, and retain that decision in each prompt and listening review.\n\nRead [segmentation and continuity](references/segmentation-and-continuity.md) when speech needs multiple requests\nor when making variants. Keep a short performance in one take if supported; split longer speech at complete\nthoughts within the live model limits. Every clip remains a continuous presenter shot. Preserve full script coverage\nwithout forcing rapid speech or silently dropping words. Deliver ordered raw clips; there is no assembly step.\n\n## Generate through OpenArt MCP\n\nApply [OpenArt execution](references/openart-execution.md), read while planning, before fixing references, voice\nor clip lengths. List available Seedance models/modes and inspect the exact input schema. Check native speech/audio and\nreference support. Model identifiers, durations and reference limits are not constants supplied by this skill.\n\nResolve actual uploaded media and supported attachment labels. Submit complete authored prompts and save task IDs\nand request receipts immediately. Honor authorized scope, reuse accepted takes, and recover outstanding jobs before\nsubmitting replacements. When the selected capability cannot produce the requested speech or reference fidelity,\nreport that gap; do not silently switch to another model family, a silent video, or an external dubbing pipeline.\n\n## Review and hand off footage\n\nUse [review and delivery](references/review-and-delivery.md) for each clip and for consistency across the set.\nCheck complete speech, pronunciation, lip sync, identity, wardrobe, gaze, hands, framing, audio, and unwanted\ncuts or graphics. A first frame, contact sheet, transcript, or successful job alone does not establish acceptance.\n\nRegenerate only a failed passage within the authorized scope. Do not hide defects with B-roll, trim away incorrect\nspeech, or splice audio as a repair. Preserve successful takes and record unresolved issues precisely.\n\nDeliver original generated clip files or accessible output links, their order and script mapping, prompts,\ngeneration receipts, and per-clip QA status. If playback was unavailable, mark affected checks as unverified.\nA multi-clip delivery is raw footage, not a continuous finished video.\n"
}