edit-greek-reel
Edit a raw talking-head video into a polished short-form reel with karaoke subtitles. Trims silence, adds Manrope Bold subtitles, zoom effects, SFX, and image overlays. Supports any language. Usage - /edit-greek-reel <path-to-video> [options]
weibo-video
微博视频上传工具。当用户需要上传本地视频文件到微博时激活。 支持大文件分片上传，自动计算 MD5 校验值，显示上传进度。
youtube-content-creator
Transforms video concepts into production-ready scripts with exact spoken lines, forward-pulling hooks between every beat, and a demo-first structure. Takes a concepts.md file and applies the ideal-mechanics.md playbook.
youtube-ingestion
Ingest YouTube videos into the vault. Triggers when user pastes a YouTube URL (youtube.com/watch or youtu.be). Fetches transcript using yt-dlp, extracts metadata, creates transcript note and summary note. User may provide additional context about the video.
nano-banana-pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
media-transcoding
FFmpeg-based media transcoding workflows with preset-driven conversions, batch processing, and safe backups for web/mobile/archive outputs.
nano-banana-pro-zh
使用 Nano Banana Pro (Gemini 3 Pro Image) 生成/编辑图像。用于图像创建或修改请求，支持文生图和图生图；支持 1K/2K/4K 分辨率；可使用 --input-image 参数编辑现有图像。
compositing
使用 Remotion 合成最终视频。当需要将片头、录屏、配音、片尾组合成完整视频时使用。包含动画效果、时间线管理、多尺寸模板和故障处理。
imagemagick
You are an expert in ImageMagick, the powerful command-line tool for creating, editing, compositing, and converting images. You help developers automate image processing pipelines using ImageMagick's `convert`, `mogrify`, `composite`, and `identify` commands — batch resizing, format conversion, watermarking, thumbnail generation, PDF manipulation, and complex image compositing for web applications, print production, and data visualization.
cloudinary
Manage images and videos with Cloudinary. Use when a user asks to optimize images, add image transformations, implement responsive images, upload media, or serve optimized assets from a CDN.
svgo
Optimize SVG files with SVGO — remove unnecessary metadata, minify paths, merge shapes, configure plugins, and integrate into build pipelines. Use when tasks involve reducing SVG file size, cleaning up exported SVGs from design tools, building icon systems, or automating SVG optimization in CI/CD.
nano-banana-pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
video-frames
Extract frames or short clips from videos using ffmpeg.
whisper-transcribe-docker
Speech-to-text (逐字稿/转写) in Docker using faster-whisper (local, no API key). Use when you already have an audio file (e.g. from `media-audio-download`) and need a transcript with optional timestamps for summarization.
media-audio-download
Download audio tracks from video links for transcription/summarization. Docker-first (no host Python): uses yt-dlp+ffmpeg for Bilibili and Playwright extraction for Xiaohongshu note pages. Use when a platform skill needs an audio file for STT (e.g. Bilibili “No subtitles found”, Xiaohongshu video notes), or when the user asks “把这个视频音频下载下来/做逐字稿”.