Video & Animation

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated motion-first unit, including an animated title. Route fresh creation through hyperframes before using this skill.

Finds what is wrong in one section of a product demo recording -- bugs, feature gaps, wrong-model choices -- separate from the screen-mapping pass.

Use when the user asks to make, script or produce a 60-second vertical animated explainer video about finance, investing or history in this repo ("make a video about X", "/make-explainer <topic>"). Runs research, sourced facts, a validated storyboard, a human review gate and the final narrated render.

Run the conversation -> research -> script -> voice -> video pipeline in the explainers repo (~/claude/explainers) - interview the owner to find what a video should argue, research it into a sourced fact sheet, write a script whose every beat is labelled fact / estimate / view / opinion / speculation / line, check it, narrate it with the local voice, draw the scenes in Skia (manim for charts), render and write the description. Use when the user wants to talk through ideas for a video, wants an explainer video made or changed, a script drafted or fact-checked, or mentions the explainers pipeline or Footnote the host.

Turn a topic into a finished, rendered explainer video — not a plan or a moodboard. Use when the user wants an animated explainer, a motion-design video, a "studio" that writes the script, storyboards, animates, scores, captions, and renders an MP4 from deterministic HTML. Covers 16:9 master plus 9:16 and 1:1 recomposition.

Turns a demo video into a structured, timestamped map of screens and flows for AutoTester's ingest stage.

Create research-grounded animated explainer videos from a topic and visual direction, from evidence research and story design through motion graphics, audio, rendering, and quality review.

把一段中文口播文案做成「简笔画手写风」竖屏解说视频（米白点阵纸、黑色手写字、黄色荧光笔、红色 ✓✗？、线条图标逐笔画出，MiniMax 或豆包按原文配音再逐字对齐，底部手写字幕，1080×1920 MP4）。只要用户说“简笔画视频/手绘风视频/白板动画/笔记风口播视频/把这段口播做成视频/按上次兔宝宝那种风格做视频/批量把脚本做成视频”，或给出口播稿+想要知识科普类竖屏短视频（抖音/视频号/小红书），都用这个 skill，即使没提“简笔画”三个字。配音必须用使用者自己的 MiniMax 或豆包 API Key。两家都没绑定就先停下来，引导对方绑定其中一家，不要索要 Key。支持换音色与多条批量并行。不用于：剪辑真人拍摄素材、数字人口播、PPT。

Use when the user wants a video that explains a pull request (a PR explainer, a review video, "make a video for <PR URL>"). Covers the whole workflow in this repo - fetching the PR, writing the narration, the voice, choosing and filling the diagrams, checks, rendering, the pr-director sign-off and delivery.

对比品牌在TikTok社媒上的内容表现、互动数据和讨论趋势，可结合历史数据进行分析，输出差异、证据与可执行机会，用于竞品分析、品牌对比、阶段性变化判断、品牌传播复盘和品牌策略优化。提供3个能力①关键词搜索（可按点赞/相关度排序、发布时间筛选）②博主作品获取，按主页链接或用户名批量获取公开作品列表，支持最新/最热排序 ③视频评论抓取，按视频链接或作品 ID 获取评论内容、评论者与互动数据，输出结构化 JSON（含作者、互动数据、标签、链接）。

为商品宣传提供自然 UGC／KOC 与实拍感概念展示的创作方法、导演提示词和案例 few-shot。适用于人物开箱、试用分享与产品展示，帮助 Agent 按商品和需求组织创意与生成。

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, declarative schemas, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector); debugging and troubleshooting errors or unexpected behavior on Supabase projects (HTTP errors, Postgres errors, RLS surprises, permission denied, schema cache issues, timeouts, Edge Function crashes, Realtime drops, Storage failures) and reading or querying logs (Logs Explorer, ClickHouse).

Use when the user wants a launch video, product demo video, announcement clip, "launch trailer", or a short (15–45s) video showing what their app/tool does — for X/Twitter, Product Hunt, a landing page hero, or a README. Also use to plan, script, storyboard, critique, or render such a video, or to study why a reference launch video is so engaging.

Future Captions — a video captioning studio. Transcribes a video's speech (automatic language detection, word-level timestamps), lets the user review and correct the transcript, offers text style options (hide or keep punctuation; as spoken, lowercase or UPPERCASE) and six animated caption presets (Karaoke box, Elegant serif with blur and motion, Cinema hard cut, Word by word, Dynamic karaoke with a stretchy box, Cartoon comic pop) in one or two lines, and exports the video with burned-in captions plus a transparent-background (alpha channel) captions video and an SRT file. Use this skill whenever the user opens or mentions Future Captions, uploads a video and asks for captions or subtitles, wants animated/karaoke/word-by-word/cartoon captions, needs subtitles burned into a video, or needs a captions overlay with transparency for Premiere, DaVinci Resolve, Final Cut, After Effects or CapCut.

Create vertical branded short-form videos from authorized interview or speech footage, with readable Chinese subtitles, safe reframing, and a QA gate for subtitle timing. Use for source-footage re-edits, not AI-generated talking-head video.

서비스를 실제로 쓰는 과정을 Playwright로 녹화하고 소비자 관점 자막을 입혀 5분 이하 데모 영상을 만든다. 영상 찍어줘·데모 영상·시연 영상·과정을 영상으로 요청에 쓴다. 발표 슬라이드·실습가이드는 다루지 않는다.

>- Erstellt detaillierte Shot-für-Shot-Videoprompts für Seedance 2.0 aus einem Creative Brief. Nutze diesen Skill immer, wenn der Nutzer einen Videoprompt erstellen, eine Shotlist schreiben, eine Videosequenz planen, ein Videokonzept für KI-Generierung beschreiben will oder Seedance erwähnt. Auch auslösen, wenn der Nutzer eine Szene, ein Werbekonzept, einen Brand Film, ein Produktvideo oder irgendeine visuelle Sequenz beschreibt, die in strukturierte Prompts übersetzt werden soll, selbst wenn er nicht ausdrücklich "Videoprompt" sagt. Trigger sind Sätze wie "schreib mir einen Videoprompt", "Seedance-Prompt", "Shotlist", "plan ein Video", "Videokonzept", "erstell eine Sequenz", "Brand-Film-Prompt", "Ad-Prompt" oder jedes Mal, wenn der Nutzer beschreibt, was in einem Video passieren soll, und das in generierungsfertige Prompts übersetzt werden muss.

Turn any audio or video file into subtitles fully offline on this machine — auto-detect the spoken language among 99 languages, transcribe with word-level timestamps, re-segment into readable cues, translate into Chinese, and emit original+Chinese bilingual SRT/ASS, optionally burned into the video. Use when the user uploads, drops, attaches, or names an audio/video file (mp3, wav, m4a, aac, flac, ogg, opus, wma, mp4, mkv, mov, webm, avi, ts, flv) and wants subtitles, captions, a transcript, 字幕, 听写, or 转写; or says "转字幕", "生成字幕", "做个字幕", "加字幕", "翻译这段音频", or asks what was said in a recording — including when they give no instruction beyond the file itself.

Ablauf, um ein Referenz-Video (Instagram/TikTok) mit eigenem Material in Remotion nachzubauen und danach auf TikTok und Instagram zu posten. Nutzen, wenn jemand ein Vorbild-Video zeigt und es nachgebaut haben will, Clips aus der Fotomediathek für einen Edit sucht, einen Remotion-Edit zeigen, rendern oder veröffentlichen will.

根据服装或穿搭图片制作可下载的朋友圈宣传 MP4，复用连续容器形变、LOOK 款式切换、合集、配乐及可选品牌片尾。用于图片生成服装宣传视频或复用 clothing-morph-v1 动效；拟真人物走秀、换装和神经网络图生视频不在此渲染器能力内。

Kurze Hochkant-Videos in Remotion ausbauen: neue Clips reindroppen (WhatsApp, Fotomediathek, Standbild im Chat), Sound-Design mit echten Geräuschen, fertiger Export für TikTok/Reels, dazu die Psychologie für Skript und Schnitt (Einstieg, Höhepunkt, Gesicht, Text). Nutzen, wenn jemand Clips schickt oder nennt („X hat mir Videos geschickt“, „nimm den“), Sounds unterlegen oder aussortieren will, ein Video für den Post vorbereiten lässt oder ein neues Skript für ein Kurzvideo plant.

从 YouTube 或本地访谈视频制作原生字幕金句拼接图，支持真实视频、字幕 OCR、人工选句和等字号拼接；生成有观点的读者配文，按用户要求接续 Chrome 抖音发布或排期、小红书草稿或发布，带素材校验及断点回执。

Turn a reference Instagram Reel into a script for your own Reel, tuned to your voice and repurposed from your newsletter content. Takes a Reel URL or Notion reference link, uses Apify to scrape the video, sends it to Gemini 2.5 Flash for full transcript + hook + structure analysis, then writes a new script applying the same patterns to your newsletter topic. Use this skill whenever the user says "script a reel", "reels scripting", "turn this into a reel", pastes an Instagram Reel URL, or references their Notion outlier reels database. The URL-to-video-analysis route needs APIFY_API_TOKEN and GOOGLE_AI_API_KEY; supplied input can skip the corresponding stages.