Loading...
Loading...
Found 7 Skills
Generate high-click-through video covers and thumbnails for Bilibili, YouTube, and Douyin using the pop-out technique: place a fully brightened cutout of the person over their own darkened original photo, with text layered in between, and reflow a single set of content into 16:9, 4:3, and 3:4 using HTML/CSS. Use this when the user wants a video cover, thumbnail, Bilibili cover, YouTube thumbnail, vertical Douyin/WeChat Channels cover, a thumbnail featuring the person, or a Codex/Agent/AI video cover. Note: this skill is exclusively for video thumbnails and follows the high-design YouTube aesthetic; for Xiaohongshu posts, infographics, or PPT-style visuals, use yuyile-social-card-skill.
Extract frames from videos at specific timestamps or intervals, find best frames, and generate thumbnail grids for previews.
Check video titles, thumbnails, and content hooks based on the MrBeast strategy to optimize click-through rate and watch time. Use this Skill when users mention "video title", "cover image", "thumbnail", "click-through rate", "CTR", "watch time", or "video opening".
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面", "视频封面", "video thumbnail", "video cover image", or provides a YouTube URL and wants the transcript/subtitle text or cover image extracted.
Process video files with ffmpeg automation. Use when: compressing videos for upload; extracting audio from video; resizing for social formats; clipping segments; merging multiple videos; generating thumbnails
Extract frames or short clips from videos using ffmpeg.
Use when creating or revising finished video thumbnails or cover images with Scenario: game trailers, boss reveals, patch updates, devlogs, or community videos needing readable composition, exact headline text and consistent characters. Not for title ideas or critique alone, in-video title cards, or a generic image without a thumbnail deliverable.