Video & Animation

Strips personal data from TikTok ad comments, clusters them into objections, questions, proof requests, and noise with counts, links each cluster to product facts, and drafts reply options and hook ideas for approval. Use when the user pastes TikTok comments and asks "what are people objecting to", "mine the comments for hooks", "draft replies to these comments", "what do viewers keep asking", or wants an FAQ and creative briefs built from comment themes.

Checks whether a TikTok ad group's bidding strategy fits its goal, budget, and conversion volume using the labels TikTok currently lists (Maximum Results, Target Cost per Result, value options as shown in the account) and asks for a screenshot before mapping any legacy name. Use when someone types "Maximum Results or Target Cost per Result", "Cost Cap vs Lowest Cost on TikTok", "our target CPA is too low and delivery died", "bid strategy check", or "should we use hybrid bidding".

Builds a staged TikTok budget plan with entry gates, one change per observation window, stop rules, and a recorded rollback, using T04, T05, T06, and T10 from the shared register. Use when someone types "can we scale this TikTok campaign", "double the budget on the winner", "how fast can I raise the daily budget", "scale before the sale", or "plan the budget increase for next week".

Reconciles TikTok Ads Manager conversions with GA4, Shopify, CRM, or app analytics using a baseline-ratio method, separating click-through from view-through credit, attribution window and timezone differences, and real tracking drift (T07). Use when a TikTok media buyer or client says "TikTok says 200 sales, Shopify says 90", "GA4 does not show our TikTok conversions", "TikTok ROAS looks too good", "the gap got bigger this month", or "which number do we report to the client".

Multi-agent workflow for cinematic Reels/Shorts: motion graphics, kinetic type, grading, sound, ffmpeg/Remotion. Use for any video edit, Reel, motion-graphics task or edit feedback round.

Manage AList-mounted cloud folders, organize movie and TV libraries with verified metadata IDs, preserve matched subtitles, and audit Japanese media for missing subtitles.

Монтаж сирого talking-head відео (або запису «екран + камера + окремий мікрофон», який скіл сам синхронізує й складає у спліт) у вертикальний ролик 9:16 для Reels/TikTok/Shorts — вирізає паузи й дублі, чистить звук до −14 LUFS, субтитри з підсвіченим словом, наближення на склейках, титул і плашки, картки-роботи, що вилітають ЗА СПИНОЮ спікера (Remotion + маска Robust Video Matting), повноекранні стокові вставки з переходами, фонова музика з приглушенням. Сам встановлює ffmpeg, whisper.cpp, моделі й npm-пакети, якщо їх немає. Використовуй, коли просять змонтувати / обробити / зробити рілс із відео, або /edit-video <файл>. Edit raw talking-head video into a polished vertical reel.

Use when the owner wants a motion-design or motion-graphic video / Instagram reel ad for their business — a product or feature launch, an offer or drop, a case study, a "how it works", a viral moment, "one like the last one" — or wants hook variations of one to test as trial reels. Also on first use, to set up the business's brand (SETUP.md).

视频补分辨率/升 2K/去色带/画面发糊发虚——任意视频通用（动效信息图、2D/3D 动画、实拍、录屏、电影剧集片段均可）的纯 CPU ffmpeg 修复链：deband 去色带 → hqdn3d 去压缩噪 → lanczos 放大 → CAS 锐化。零显存、零下载、免 AI、免注册。当用户发来视频说"补分辨率""升到 2K""画面糊/有色带""帮我放大""画质修复"时触发。对实拍素材同样有效；若追求实拍纹理的极致重建，可在本链基础上再叠加 AI 超分作为可选进阶。

Make a new Vox-style informational reel (9:16 explainer, "Money, Explained" series) in this repo — from topic to rendered MP4. Use when the user asks for a new reel/short/explainer on a topic, or to remake/extend an existing one.

Render a standalone coded motion asset (MP4, ProRes, or transparent MOV) with the canvas-video CLI from a Canvas 2D or Three.js scene, then hand it to HyperFrames and video-delivery-qc. Use when a request names canvas-video, Canvas 2D, or Three.js, or needs a pre-rendered coded overlay or B-roll clip to combine with Dreamina or other footage. Do not use for animation that should live inside a HyperFrames composition; route that to hyperframes.

Inspect a social video before export or delivery, including technical integrity, social-ready encoding, audio loudness, subtitle-to-speech timing, shot structure, and character/prop/scene continuity. Use for final video QC, social delivery checks, subtitle verification, or diagnosing a rendered video; do not invoke for ordinary video creation that has not reached a review or delivery stage.

Produz um vídeo com motion graphics do zero ao MP4 (Remotion + ffmpeg + Whisper) a partir de uma ideia/texto, de um áudio gravado, de um vídeo (talking head, screencast) ou de um projeto/produto (pasta de código, URL, app) para demonstrar. Pesquisa o nicho antes de desenhar, edita a fala, sincroniza animação e legenda palavra por palavra, monta trilha e efeitos com densidade controlada e faz QA olhando os frames. Use sempre que o pedido envolver vídeo animado ou editado, mesmo sem a palavra "motion" - "faz um vídeo com motion", "cria um vídeo animado", "transforma esse áudio em vídeo", "edita essa gravação com legenda", "vídeo pra Reels/TikTok/Shorts", "vídeo explicativo", "explainer", "demo animada do meu app", "motion graphics", "kinetic typography", "tipografia animada", "make a motion video", "animated video from this audio", "turn this recording into a reel", "product demo video".

MV 工程。マスター音源・カバー画像・LYRICS.md（と任意の背景ループ動画）から、歌詞が出る MV（16:9 本編・9:16 ショート・サムネ）を tools/make_mv.sh で作り、利用者に見てもらって直したい点を直し、OK が出たら song.json の approved_at を入れる。「MV を作って」「動画にして」「歌詞のタイミングがずれている」「文字を大きく」「色を変えて」「背景を動かしたい」「ループ動画を作って」「MV の見せ方を選びたい」「もっと凝りたい」と言われたとき、または new-song の MV 工程で使う。

Load environment variables from a .env file into process.env for Node.js applications. Use when configuring apps with secrets, setting up local development environments, managing API keys and database uRLs, parsing .env file contents, or populating environment variables programmatically. Always use this skill when the user mentions .env, even for simple tasks like "set up dotenv" — the skill contains critical gotchas (encrypted keys, variable expansion, command substitution) that prevent common production issues.

Render a standalone coded motion asset (MP4, ProRes, or transparent MOV) with the canvas-video CLI from a Canvas 2D or Three.js scene, then hand it to HyperFrames and video-delivery-qc. Use when a request names canvas-video, Canvas 2D, or Three.js, or needs a pre-rendered coded overlay or B-roll clip to combine with Dreamina or other footage. Do not use for animation that should live inside a HyperFrames composition; route that to hyperframes.

Генератор вірусних сценаріїв для Instagram Reels, TikTok і YouTube Shorts. Використовуй ЗАВЖДИ, коли користувач просить написати сценарій для рілс/reels/shorts/тікток, придумати хук/гачок для відео, зробити контент-план для коротких відео, адаптувати текст/ідею під формат рілс, написати сценарій для stories, створити вірусне відео, придумати чіпляючий початок для ролика, розібрати/проаналізувати рілс конкурентів, написати CTA для відео. Тригерні слова - рілс, reels, shorts, тікток, сценарій, хук, гачок, hook, вірусний ролик, ролик що залетів, сценарій відео, скрипт ролика, контент-план відео, формат відео, чіпляючий заголовок для відео, утримання уваги, 3 секунди, retention, CTA відео.

Inspect a social video before export or delivery, including technical integrity, social-ready encoding, audio loudness, subtitle-to-speech timing, shot structure, and character/prop/scene continuity. Use for final video QC, social delivery checks, subtitle verification, or diagnosing a rendered video; do not invoke for ordinary video creation that has not reached a review or delivery stage.

Use dotenvx to run commands with environment variables, manage multiple .env files, expand variables, and encrypt env files for safe commits and CI/CD.

Produce a beat-synced product launch reel / showreel / promo video in code. The pipeline captures a product URL's real brand assets, writes a style guide, measures the beat grid, and gets a shotlist approved. It then builds a deterministic seek(t) film with springs, runs 3+ scored critique rounds to 8+, and renders H.264 with synthesized music, SFX and optional Fish Audio voiceover in 16:9, 1:1, 4:5 and 9:16. Use when the user asks for a launch video, product reel, motion reel, showreel, promo, sizzle or social ad for a product or URL, or says "motion-reel".

Record captioned product walkthrough videos of any web app with Playwright + ffmpeg — proof videos for stakeholders, feature demos, bug-fix evidence

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI animation (scroll, cursor, callouts), or fusing a real image's geometry into a chart. Usually under 10s (up to ~30s), no narration or live-action subject; renders to MP4 or transparent overlay. Longer / narrated / multi-scene → /general-video. Unclear → /hyperframes.

Mandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any HyperFrames HTML composition. Also use it to inspect, diagnose, validate, preview, publish, or batch-render an existing HyperFrames project. Inputs may be a website URL, GitHub PR, Figma design or URL, text or brief, existing footage, or music. It resumes project state, captures intent when applicable, selects and installs the owning workflow, and routes domain capabilities. HyperFrames is the default output framework unless the user explicitly chooses another framework for the deliverable or asks only to record a browser session.

Agent Media OS for a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs privacy, or needs a media reveal. When the host app provides its own music or sound-effect tools, use those for music and sound effects; `resolve --type bgm|sfx` needs the heygen CLI. When `HEYGEN_API_BASE` is set, HeyGen calls go through that host with no CLI sign-in.