Type one idea, get a full 30-second Shorts plan: timed scenes, narration, captions, and ready-to-paste Seedance 2.0 / KingAI prompts for every scene. Built for faceless channels and AI video creators.
“Turn one idea into a production-ready Short with a final script, exact shot timing, storyboards, generator-ready visual prompts, captions, titles, and A/B variants.”
I've spent hundreds of hours testing AI video production workflows — what visual styles actually render well, how to structure prompts for consistent output, and how to go from zero to upload-ready assets efficiently. This blueprint distills that into one guided system: 12 visual style DNA libraries, scene prompt builder, TTS-ready voiceover scripts, captions, and hashtags — all from a single workflow. No experience needed to produce professional short-form content.
Surgically trim awkward pauses, dragging breaths, and robotic TTS dead air in 0.4s. Built for TikTok, Reels, Shorts, and podcasts to boost audience retention by 15%-25%. Features studio-grade 10ms anti-click cosine crossfading and 50ms voice-head safety buffers to guarantee crisp, zero-artifact broadcast audio.
把短剧剧本或剧情片段，拆成可执行的专业拍摄脚本、人物/场景/道具图片生成提示词、16:9导演分镜工作板和 Jimeng/Dreamina 视频提示词。适合AI短剧创作者、导演、编剧和视频团队，重点解决剧情被改写、人物站位混乱、道具连续性丢失、分镜与视频提示词不一致、演员表演空、镜头语言太泛、上下CUT衔接断裂等问题。
I’ve created and shaped social content with nearly 200M views across YouTube, TikTok, and Instagram, and the pattern is clear: people do not connect with text that sounds polished but empty. They respond to voice, opinion, rhythm, and specific details. This Skill applies that editorial judgment to AI drafts by spotting obvious AI tells, repeated language habits, and stiff structure, then rewriting with stronger voice while keeping the original meaning intact.
本技能用于创作面向美国/海外市场的 AI 漫剧**剧本**（Webtoon 竖屏漫剧、Tapas、TikTok 短剧漫剧等），按固定流程产出剧本并交付**英中双语版本**。剧本正文采用**镜头级字段**（SHOT/ACTION/DIALOG/VO/SFX），读感是剧本而非分镜表，镜头数量由剧情自然决定。台词与旁白（DIALOG/VO）按严格规范设计，并经过四级复核逐轮把关。 **任务边界**：本技能只负责剧本创作，**不生成任何 AI 视频提示词**（无内置转换工具、无视频模型参数）。
Send a topic, get one complete faceless short-form video plan back in a single reply: three hooks with their visuals, a second-by-second shot list timed by speech rather than character count, TTS-ready narration, stock-footage search terms per shot, captions and tags for TikTok, Reels and YouTube Shorts, a cover-frame spec, and a retention review that names the seconds where viewers leave. Thirty requests is a month of daily uploads.
Find generic AI residue in blogs, social posts, newsletters, and marketing copy, then repair it back into your own voice. This agent flags template-like phrasing, hollow CTAs, fake certainty, and over-polished structure, then gives a clearer, more specific rewrite focused on authentic voice and specificity, not artificial detection outcomes.