By ttfake92-lab
Turn scripts and story ideas into AI video prompts with image references, scene breakdowns, and sound design, then build spoken-video compositions as Remotion projects and generate high-CTR thumbnails for Bilibili, YouTube, or TikTok.
把脚本、故事节拍或镜头想法转成图片参考型 AI 视频提示词,包含图片参考绑定、秒级动作、声音设计和硬约束。使用场景:用户需要 AI 视频提示词、Seedance 提示词、图片参考视频生成、脚本转视频提示词、多图参考、首尾帧、全能参考、视频提示词,或希望把脚本转成可直接复制使用的完整视频提示词。
Turn a full script, story, or voiceover draft into structured, cinematic video-generation prompts — automatically segmented scene-by-scene. Best for structured-prompt video tools like Seedance 2.0, Kling, and Jimeng (即梦). Use this skill whenever a user pastes a script / story / 口播稿 / 分镜脚本 and wants it turned into video prompts, asks to write a video prompt, generate a storyboard, split a script into shots, or describe a cinematic scene for video AI. Each segment gets a complete prompt: 基础设定 (characters), 道具 (props), 场景 (scene), 声音 (sound), 氛围与画质 (mood & quality), 画面内容 (shots — auto-decomposed into a shot list or a long take, each with 景别/构图/运镜). Also trigger on keywords: video prompt, video generation, AI video, text-to-video, storyboard, 分镜, 拆分镜, 视频提示词, 视频生成, 脚本转视频, Seedance, Kling, 即梦, cinematic prompt, shot list, camera movement. Trigger even if the user only has a rough one-sentence idea — treat it as a single segment and flesh it out.
Build 16:9 spoken-video compositions as standalone Remotion projects with React, TypeScript, frame-based animation, estimated durations, and direct mp4 rendering. Use when the user wants video files, Remotion, mp4 export, frame-accurate motion, post-production voiceover, or theme-driven video templates; do not use for click-driven web presentations.
生成 B站 / YouTube / 抖音 的高点击「视频封面 / 缩略图」——pop-out 技法:抠图人物全亮叠在自己那张被压暗的原图上、文字压在中间,一套内容用 HTML/CSS 重排成 16:9 / 4:3 / 3:4 三种比例。当用户要视频封面、缩略图、thumbnail、B站封面、YouTube 封面、抖音/视频号竖封面、把人物放封面上、Codex/Agent/AI 视频封面时使用。注意:这是「视频封面」专用,走 YouTube 高设计感美学;要小红书图文/信息图/PPT 风请用 yuyile-social-card-skill。
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of skills for AI coding agents. Skills are packaged instructions that extend agent capabilities — for content creators, video producers, and prompt engineers.
npx skills@latest add ttfake92-lab/skills
Pick the skills you want, and which coding agents you want to install them on.
Bam — you're ready to go.
yyl-video-thumbnail has been added to the repository manifest, so npx skills@latest add ttfake92-lab/skills can discover it together with the existing skills.This repository currently includes four content-creation skills. They cover adjacent stages of an AI video workflow:
| Skill | What It Does | Best For |
|---|---|---|
AI-video-prompt | Turns scripts or story beats into image-reference prompts with second-by-second action, sound, and hard constraints. | Seedance 2.0, multi-image reference prompts, first/end frame continuity, production control prompts. |
mx-shell-prompt | Turns scripts, stories, voiceovers, or rough ideas into structured cinematic prompts. | Text-to-video tools, storyboard prompts, shot lists, camera language. |
yyl-remotion-video | Turns scripts, articles, notes, or outlines into Remotion projects that can render mp4. | Frame-accurate explainers, product demos, command-line films, silent clips for post-production voiceover. |
yyl-video-thumbnail | Generates high-CTR video thumbnails with pop-out technique — darkened base, yellow keyword text, full-brightness cutout subject. | Bilibili, YouTube, Douyin/TikTok covers, AI tool demos, command-line film posters. |
Use AI-video-prompt when your next step is generating footage in image-reference workflows such as Seedance-style multi-image generation. It focuses on locking image roles, character continuity, time-coded motion, sound design, spatial logic, and hard failure-prevention constraints.
Use mx-shell-prompt when your next step is sending prompts to video generation tools such as Seedance 2.0, Kling, Jimeng, Sora, Runway, or Pika. It focuses on cinematic language: characters, props, scenes, sound, mood, shot sizes, composition, and camera movement.
Use yyl-remotion-video when your next step is building a real Remotion project and exporting an mp4. It focuses on React/TypeScript implementation, timeline timing, frame-based animation, still-frame checks, and theme-driven video templates.
Use yyl-video-thumbnail when your video is done and you need a click-worthy cover image. It focuses on the pop-out visual technique, three ratio outputs per brief, and three distinct aesthetic templates — poster, command-panel, and film-edit.
mx-shell-prompt to break a script into cinematic blocks and shot ideas.AI-video-prompt when the output needs image-reference prompts with precise constraints.yyl-remotion-video when you want a deterministic 16:9 Remotion clip instead of model-generated footage.yyl-video-thumbnail to generate a high-CTR cover image once the video is ready.MIT
AI Agent 技能集合 — 面向内容创作者、视频制作人和提示词工程师。
npx claudepluginhub ttfake92-lab/skillsAI video generation — describe what you want, Pexo picks the best model across 10+ engines (Seedance, Kling, Veo, Sora) and returns a finished, multi-shot video with music, subtitles, and transitions. Includes the Pexo agent plus image, audio, director, and model-prompting skills.
The creative suite for AI agents — motion graphics, asset generation, and video rendering via Remotion + @oanim/core
Full video production pipeline for Remotion — gives Claude eyes (video analysis), voice (TTS/voiceover), ears (music/SFX), stock footage, AI image/video generation, TikTok captions, 3D content, and more. By Dojo Coding Labs.
Transform text scripts into professional videos with AI voiceovers, stock footage, and Remotion rendering. Advanced features include direct filesystem access, environment management, and whitelisted command execution.
Plan, brief, and prepare YouTube videos from idea to filming-ready. Create video briefs, generate topic ideas, optimize titles and thumbnails, build structured outlines, write scripts, and design on-screen excalidraw visuals.
Complete YouTube content production workflow: research competitors, generate video ideas, build briefs, craft titles and thumbnails, and create detailed video outlines with demo prep checklists.