{"skill":{"slug":"video-frame-analyzer","displayName":"Video Frame Analyzer","summary":"AI漫剧/短剧视频智能帧分析工具。自动提取关键帧 → 多模态逐帧解读 → 输出完整分析报告（剧情大纲、镜头语言、角色设定、台词整理、商业改编建议）。适用于抖音/视频号短剧拆解、竞品分析、改编策划。","tags":{"latest":"0.1.0"},"stats":{"comments":0,"downloads":93,"installsAllTime":0,"installsCurrent":0,"stars":1,"versions":1},"createdAt":1778581868112,"updatedAt":1778582208969},"latestVersion":{"version":"0.1.0","createdAt":1778581868112,"changelog":"Initial release of video-frame-analyzer skill.\n\n- Automatically extracts key frames from AI short-drama videos.\n- Performs multimodal frame-by-frame analysis (visual, dialogue, shot type, narrative, emotion).\n- Outputs a complete structured report: plot summary, cinematography, character design, dialogue, business adaptation suggestions.\n- Workflow optimized to handle context limits: analyzes frames in small batches, writes results incrementally.\n- Supports popular video formats (mp4, mov, avi); works with multimodal models like GLM-5v-Turbo or GPT-4o.\n- Useful for short-video deconstruction, competitor analysis, and content adaptation planning.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"roseryztzhoutong","userId":"s17evc052jzn6pdgd36h1jdae986kjg6","displayName":"roseryztzhoutong","image":"https://avatars.githubusercontent.com/u/272734640?v=4"},"moderation":null}