Browse skills

Remotion converts video clips into high-quality, editable images, streamlining workflows and enabling creative flexibility for visual content creators.

YouTube Clipper extracts clips from YouTube videos, saving you time and data by letting you directly share specific moments without needing to download the entire video.

Generate eye-catching YouTube thumbnails based on video titles and descriptions to boost click-through rates.

Youtube Clipper — provides AI agent assistance for software development workflows.

Webperf Media — provides AI agent assistance for software development workflows.

Justanothermusicclient Tauri Youtube Music — provides AI agent assistance for software development workflows.

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

This skill generates short GIF demos from CLI commands, providing quick visual examples and showcasing command functionality effectively.

Analyzes video clips, identifying key objects, actions, and potential sentiment within the content.

Analyzes video thumbnails for clickability, clarity, and brand consistency using Alchaincyf's AI models.

Extract frames or short clips from videos using ffmpeg.

制作哲学、心理、历史、经济、金融与科技等主题的 AI 动画解说视频。适用于 Agent 研究和组织选题、编写旁白、将 1–5 分钟视频拆成均衡的 Seedance 片段、按关键人物数量生成人物参考图、逐片段设计具体场景与多镜头视频提示词、保持旁白音色一致、制作带字封面，或规划基于 CLI 的多模态生成与拼接流程。当前正式维护的执行路径使用 LibTV CLI；查阅最新官方文档后，也可将该生产方法适配到 Higgsfield、即梦及其他同类多模态 CLI。

Make short product / skill motion videos (10–30 s, narrated feature demos up to ~60 s) the way high-end launch clips are made — kinetic type, real UI as the material, a hand that causes every reaction, beats that carry into each other instead of replacing each other, hard cuts only where they mean something — without HyperFrames or Remotion. A single HTML composition where every value is a pure function of time, built from a library of measured moves (springs, entrances, carries, contact, camera), rendered frame by frame with real shutter motion blur (1080p30 drafts, 4K60 final), with synthesised sound effects that share one room and an oracle that fails a slideshow before a human has to watch it. Use for 做个动效短片 / 产品宣传片 / 介绍视频 / 发布视频 / 15 秒 launch video / 给 skill 或 app 做个视频 / promo / teaser, for turning real pages or screen recordings into a cut, for product feature demos (产品功能演示 / 功能展示动效) where the UI is rebuilt in HTML from screenshots instead of screen-recorded (不录屏 / 复刻界面 / 截图还原 UI), for narrated cuts with voice-over and subtitles (配音 / 字幕 / 换配音) and for the same film in other languages (日语版 / 多语言 / 本地化), for adding motion vocabulary (动效库 / 转场 / 衔接), and for auditing why a motion video reads as a slideshow (像 PPT / 没节奏 / 一个一个展示 / 转场生硬).

Downloads YouTube videos in various resolutions and formats using dynamic playlists – useful for archiving content or extracting specific clips.

Convert YouTube videos to vertical short-form clips using yt-dlp, FFmpeg, and Whisper. Auto-detects highlights, crops to 9:16, and overlays subtitles.

Yt Dlp analyzes YouTube videos for specific content or patterns, useful for research, monitoring, and identifying relevant clips.