Media AI Skills

Summarize videos, transcripts, articles, documents, and pasted text into concise takeaways.

Turn an approved script, provided talking-head/voiceover media, and gathered assets into a polished, creator-grade vertical (9:16) short rendered with HyperFrames. Encodes a non-negotiable…

Professional video ad creation with Remotion — Instagram Reels (9:16), website explainers (16:9), and carousels (4:5). Use when creating video ads, animated social content, or educational explainer…

YouTube research through the TubeAI connector (MCP). Explores 400M+ YouTube videos and 4M+ channels to find video ideas and outliers, research niches and competitors, work out titles, study…

Research a topic (a company, service, website, or product) and render a short promo video as an MP4 drawn entirely in code, in one of the bundled styles or any style the user describes or shows. The…

Edits raw recordings into videos for social media using Remotion. Best for Instagram Reels (9:16), but also suitable for other platforms like TikTok, LinkedIn and YouTube (incl. 16:9). Use for any…

Turn any source — a GitHub repo, a technical article or blog URL, a PDF, a local project folder, or pasted notes — into a dense dark "terminal blueprint" architecture diagram with a structure fitted…

Use when a user gives a brand URL and wants a premium launch, demo, or marketing video. Zero-manual workflow — Claude runs the V2 orchestrator itself (scrapes brand evidence, auto-installs missing…

Apply designed cinematic captions to an existing HyperFrames video by selecting hero words from speech, building ordered mixed-case stacks, placing type around a speaker, and using subject-aware…

Generate and edit images, videos, speech, and music with PixVerse CLI; run effect templates, MiniApps, and connected Canvas workflows. Use for PixVerse generation, asset management, and creative…

把一首古诗、一阕词（或一句诗、一段短文）做成 20–80 秒的「代码画的水墨手绘风 2D 动画」——一个红点小角色把诗走一遍，题签逐句写字，带朗诵，末句边念边写，红印章收尾；配乐和音效用 numpy 合成，封面是第一帧，最后给上传版和实测帖草稿。用户说「把 XX 这首诗 / 这首词做成动画」「做一条诗词动画 / 古诗动画 /…

二次元漫画 ／ 游戏 PV —— 宣传片线方向之一：15 秒以内的动漫、漫画或游戏 PV：角色宣传、觉醒、战斗、世界观与抽卡活动。

Create educational videos using Remotion with Kurzgesagt/回形针 style. Use when users want to: (1) create teaching or educational videos, (2) design video storyboards, (3) produce animated explainer…

Use this skill when the user provides 抖音 (Douyin), B站 (Bilibili), 快手 (Kuaishou), 小红书 (Xiaohongshu), or 微博 (Weibo) video URLs and wants to download videos, extract metadata, transcribe audio with local…

阿杭AI博主系列视频制作入口。用于AI博主口播剪辑、剪后逐字稿和对应封面，选择本系列参数后调用另行安装的剪辑引擎与封面Skill。

面向 AI Agent 的视频剪辑技能套件，把各大剪辑博主与专业后期经验内化为可决策、可复现的规则。当用户想剪一条视频、问任何剪辑怎么做（口播精剪、加音乐/卡点、贴 B-roll、调色、关键帧/运动、变速/补帧、抠像/蒙版/合成、二维或平面跟踪贴合、多机位采访、转场衔接、节奏垮了怎么救、导出参数与平台画幅），或让你自动出一版初剪时，务必使用本技能。它先判断意图（答疑 / 反问澄清 /…

Universal Android device control with vision feedback. Supports Termux phones, ADB-only devices, and emulators. Use for phone automation, AI companionship, or mobile app testing.

WCAG 2.2 compliance, ARIA authoring patterns, screen reader and keyboard navigation, color contrast, and cognitive/neurodiversity accommodations. Use when auditing accessibility, fixing a11y…

Organize files using the PARA method (Building a Second Brain). Intelligent categorization into Projects, Areas, Resources, and Archive with inbox workflow. Triggers on "organize my files", "organize…

Load this skill immediately whenever a project contains an ACCESSIBILITY.md file, or whenever you are contributing to the mgifford/ACCESSIBILITY.md repository. Absolutely always read ACCESSIBILITY.md…

把小宇宙（Xiaoyuzhou FM）单集播客转成结构化的 Markdown 笔记。工作流为：解析小宇宙单集链接 → 拿到音频直链、shownotes、章节（有官方转录则直接用）→ 转录音频 → 判断内容类型（财经/科技商业/人物访谈/知识科普/通用）→ 套用对应的笔记模板 → 输出 .md…

根据商品图片自动生成专业广告视频；包含商品扣图、信息识别、脚本创作、分镜设计、视频生成和后期合成全流程；适用于商品推广、电商营销、品牌宣传等场景

Create, revise, compress, translate, diagnose, and production-plan prompts for Dreamina/Seedance 2.5. Use when the user mentions Seedance 2.5, Dreamina 2.5, text/image/video/audio-to-video, multimodal…

Download videos from 1800+ platforms (YouTube, Bilibili, Twitter/X, TikTok, Vimeo, Instagram, etc.) and generate complete resource package with video, audio, subtitles, and AI summary. Actions:…

Practice spoken English or learn from English videos, especially AI videos, with contextual vocabulary explanations, brief quizzes, and linked Obsidian records and weekly reviews.

本地媒体预处理、零外部音视频 API 的视频阅读与问答——把视频处理成带时间戳的语音转写、代表性画面和通用视听审查包，并可根据证据不足的时间窗增量补帧。当用户要理解、总结、转写、抽帧或核对本地视频及 YouTube、B站等视频链接，并要求带时间戳引用、画面与文稿交叉验证或自适应细看关键片段时使用。适用任何具备命令行与图片读取能力的 AI Agent。

跨智能体、本地优先的多源蒸馏与迁移工作流。用于收录或蒸馏代码仓库、网站、App、UI/交互、图片与品牌、视频、音频、文章、文档、书籍、课程及混合素材，形成带证据的可迁移画像、再生成规范、产品方案和本地方法库；也用于把画像应用到新主题或新 idea 并验收结果。

Use when converting static image sequences (sequence boards) into motion prompts for AI video generation platforms (Runway, Pika, SVD), or describing temporal movement for video synthesis

Convert a HyperFrames project (HTML/GSAP video compositions) into an editable Adobe After Effects project (.aep) with real layers and keyframes, not a rendered video. Text stays live text, cards…

Make product launch films and single shots in the style of Apple and Linear launch films, from 38 recipes (HyperFrames, HTML + GSAP rendered to MP4). Use when the user asks for a product launch film,…

Decide what to borrow, adapt, or write before building something. Use when the user describes an app, tool, CLI, or feature they want to build and needs to know which parts already exist as…

将文章、Markdown 口播稿、SRT 字幕、旁白音频或已有插图制作成可续跑的白板手绘视频项目；开始前确认统一保存目录，支持轮廓与铺色同路径的整图斜向扫描、语义分层曲线蒙版、固定手部画笔、字幕交付确认、场景合成和首中末帧质检。用户要求制作、继续、重渲染或检查白板动画、知识讲解视频、手绘口播视频时使用。

Search and understand videos without embeddings. Use when the user asks about the content of a video file or video URL - finding moments ("when does X happen"), finding a person or object from a…

从 B 站教育/讲课视频生成带截图的 DOCX 学习笔记。下载视频+字幕→全覆盖抽帧→OCR去重→AI视觉打分→提取图中内容→融合生成DOCX。

Analyzes video files by extracting frames, detecting scene changes, and optionally transcribing audio. Produces structured markdown analysis with timeline, visual descriptions, and key moments. Use…

Use when the user drops or points at a local talking-head video and wants the kinetic supers + rapid camera reposition prompt for video-to-video AI (one real take turned into split-second camera snaps…

Generate and integrate local sound effects and other audio. Use when asked to build, finish or improve a game, edit a video, animate a scene, or create an interactive application or website where…

Generate images and video from text prompts via the mediagen CLI, across Gemini, OpenAI and Kie AI. Use when asked to create, generate, render, or edit an image or a video — a logo, an illustration, a…

Transcribe and critically analyze audio/video content. Accepts a .vtt file, an audio file (.m4a, .mp3, .wav, etc.), or a URL (YouTube or other yt-dlp-supported sites). Generates a structured markdown…

Develop TypeScript/Three.js games in isolated workspaces, plan games and create, edit, upgrade, animate, and prepare production-ready game assets with Meowa. Use for Game Designer research and design…

Turn a bilibili/B站 course video or BV id into a course knowledge base plus an optional teacher persona skill. Use when the user gives a BV id / bilibili link for a course, lecture series or 网课 and…

Turn ONE long video into native TikTok + Reels + Shorts posts — the four stations: CUT (word-level transcript, best moments, 9:16 reframe), CAPTION (burned word captions + per-platform caption text),…

Stage 7 of the Software Factory - the proof video. Turns a build's acceptance criteria into a narrated MP4 - Playwright drives the real app criterion by criterion while a voice explains what's being…

Design systems, motion, mood boards, spatial layout, visual assets, Design Context profiles, and a global Inspiration Library from screenshots, website URLs, inspiration images, music, or fuzzy…

Direct and render films made entirely in JavaScript, from an idea to a frame-exact MP4, working like a film director. Take the brief, then ask where the sound comes from (the person's audio file, a…

Audit mobile applications (iOS and Android) against RAAM 1.1 (Luxembourg Mobile Accessibility Assessment Framework). Use when reviewing existing mobile app code for accessibility compliance,…

Анимация, в которой объект собирается из деталей LEGO по шагам, в стиле фирменной инструкции. Все нарисовано кодом на Canvas 2D, без картинок и 3D-движка, рендер в mp4 вертикально 1080x1920 или…

WCAG conformance, BFSG compliance, semantic HTML, ARIA, keyboard navigation, contrast, forms, and assistive technologies. Defines binding rules for accessible web interfaces per WCAG 2.1 AA.

Accessibility and inclusive design to WCAG 2.2 AA - contrast, keyboard and focus, semantic HTML and ARIA, screen readers, forms, motion and seizure safety, touch targets, reflow/zoom, alt text,…

Advise on and critique UI/UX design work through the lens of Luke Wroblewski's published principles, using his MCP archive to retrieve relevant writings, presentations, videos, and other source…

Direct and render polished short motion-graphics reels, brand films, and kinetic showcases in code. Use for a punchy product or identity reel, or when existing animation feels static, sparse,…