This skill should be used when the user asks "check frame rate", "is this CFR or VFR", "video has duplicate frames", "video stutters", "frame rate issues", "why does video judder", or wants to analyze frame rate characteristics and detect timing problems.
Add chapters to videos by transcribing, analyzing, and generating structured markdown documents with YouTube chapter markers. Optionally generate highlight videos.
魔镜 demo 技能。用户说“魔镜拍照”“帮我拍一张”“魔镜请拍照”时，用 soarmmoce-real-con 的本地摄像头抓拍脚本把照片保存到这个 skill 的工作空间；用户说“谁最美”“选最美的人”“把最美的人变成皇后”“生成皇后视频”时，从工作空间照片里选出最佳候选，先把本地照片上传成 ArtsAPI 可访问的公网图片 URL，再调用 ArtsAPI 图生视频生成皇后变身视频并优先保存到本地。
Process images with the Sharp library for Node.js — resize, convert formats, composite, apply effects, and manage metadata. Use when the user mentions "sharp", "image processing", "resize image", "convert image", "image format", "jpeg quality", "png compression", "webp", "avif", "image thumbnail", "crop image", "watermark", "overlay image", "blur image", "sharpen image", "image metadata", "EXIF", "ICC profile", "colour space", "alpha channel", "animated gif", "image pipeline", or asks how to manipulate images in Node.js/TypeScript. Also use for "sharp constructor", "sharp cache", "sharp concurrency", "toFile", "toBuffer", or any Sharp API method.
Unified workflow combining video-clean and video-add-chapters with transcript reuse and chapter remapping
Create clean, subtitle-ready `.srt` subtitles for a local audio or video file using Whisper CLI. Use this when the user asks to transcribe a local media file, generate subtitles, create captions, or make an `.srt` for a specific local file path.
Upscale and enhance image and video resolution using AI
AI-powered image editing with style transfer and object removal
Remotion video production — scenes, transitions, OffthreadVideo, audio mixing, multi-scene timelines, and rendering output
AI video & audio summarizer. Summarize YouTube videos, Bilibili videos, podcasts, TikTok, Twitter/X, Xiaohongshu, and any online video or audio. Use when the user wants to summarize a video, extract transcripts/subtitles, get chapter-by-chapter summaries, or understand video content quickly. Triggers: "summarize this video", "what's this video about", "extract subtitles", "总结这个视频", "帮我看看这个视频讲了什么", "video summary", "podcast notes", "YouTube summary", "B站总结", "get transcript", "video to notes". Works via bibi CLI (macOS/Windows) or OpenAPI (Linux / any platform without CLI).
Image, video, and audio processing using FFmpeg, ImageMagick, Sharp, and web-optimized media pipelines
Image optimization — next/image, responsive sizes, priority loading, blur placeholders, WebP/AVIF, CDN loaders, lazy loading
Use when user asks to convert, compress, trim, resize, extract audio, add subtitles, create GIFs, or process video/audio files
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
Replicate motion effects from reference videos. Use when user wants to copy/clone/replicate an existing motion effect, compare generated effects with originals, or iterate on effect accuracy.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
Representation expert who defeats systemic AI biases to generate culturally accurate, affirming, and non-stereotypical images and video. Adapted from msitarzewski/agency-agents.
