Update to EzUGC

{
  "description": "Create AI UGC video ads with EzUGC, meaning talking-head creator ads with script, avatar, voiceover, and captions. Use when the user wants UGC, a UGC ad, a TikTok/Reels product review, or \"create a UGC video\". Cinematic or silent product clips use ai-video-generation instead.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 193
    }
  ],
  "name": "ugc-generation",
  "skill_md_contents": "---\nname: ugc-generation\ndescription: Create AI UGC video ads with EzUGC, meaning talking-head creator ads with script, avatar, voiceover, and captions. Use when the user wants UGC, a UGC ad, a TikTok/Reels product review, or \"create a UGC video\". Cinematic or silent product clips use ai-video-generation instead.\n---\n\n# UGC Generation\n\nUse this skill when the user wants an **AI UGC ad**: a creator talking to camera about a product, with a script, avatar, voiceover, and captions.\n\nThe plugin is already connected through OAuth. Call `whoami`, then `get_usage`, before generating. If `whoami` fails, tell the user to reconnect the EzUGC plugin. Never use app cookies or a browser session.\n\nNever mention USD, provider cost, or credit-to-dollar rates. Quota is remaining videos this billing cycle (`get_usage`).\n\n## Quick start\n\n1. Call `whoami`, then `get_usage`. Stop on auth failure. Report remaining videos this cycle.\n2. Call `generate_ugc_video`. Prefer `wait: true`.\n3. Report the real video URL from the job. A UGC render takes a few minutes; if the job is still running, give the job id and poll `get_job` until it completes. Never invent a result.\n\nExample:\n\n```json\n{\n  \"prompt\": \"15s Reels ad for a vitamin C serum. Hook on dull skin, show the bottle, end on a shop-now CTA.\",\n  \"platform\": \"instagram_reels\",\n  \"duration\": 15,\n  \"aspectRatio\": \"9:16\"\n}\n```\n\n## Tool\n\nCall **`generate_ugc_video`**.\n\n| Arg | Required | Notes |\n| --- | --- | --- |\n| `prompt` | yes | Creative brief (product, audience, hook, CTA). |\n| `script` | no | Exact spoken words. Omit to auto-write the script. |\n| `productImageUrls` | no | Public https product photos. |\n| `platform` | no | e.g. `instagram_reels`, `tiktok`, `youtube_shorts`. |\n| `duration` | no | Target seconds. Keep spoken pacing around 2.5 words per second if a script is supplied. |\n| `aspectRatio` | no | `9:16` (default for UGC), `16:9`, `1:1`. |\n| brand refs | no | `brandId` / `brandSlug` / `useDefaultBrand`. |\n| `wait` | no | Default true. |\n\nIf they want it on-brand and have a website: `list_brands`, then `create_brand` if needed, then pass `useDefaultBrand: true` (or `generate_brand_video`).\n\n## Ambiguous briefs\n\nIf they might mean a silent product clip instead of a talking-head UGC ad, ask once.\n\n- Talking-head UGC ad: this skill.\n- Cinematic / b-roll / named model (Veo, Kling, Runway): `ai-video-generation`.\n\n## Script guidance\n\n- Keep spoken pacing around 2.5 words per second unless they ask otherwise.\n- If the requested runtime and script length conflict, flag it before sending the job.\n- Keep prompts concrete: product, audience, hook, proof, CTA.\n\n## Hard rules\n\n- Never invent a job or video URL.\n- Do not dump provider names, task ids, or raw upstream errors to the user.\n- Write **Nano Banana** with a space if an image step comes up.\n- Do not post videos to Instagram, TikTok, or other public platforms.\n"
}