Video & Animation

This skill should be used when the user asks for the finished video file - "exportier das", "render das fertig", "mach das final", "renderte das Video", "mach den Endexport", "bau das Video zusammen", "mach es fertig für YouTube", "gib mir die MP4", "export the final", "render the final cut", "make the master", "export for TikTok", "give me the mp4". Covers segment rendering with the cache, guarded concat, the one-pass audio, loudness normalisation and the single mux.

This skill should be used when the user asks to decide what the video is actually about before any mechanical cutting - "bau die Story", "was soll ins Video", "was kann raus", "welche Themen bleiben", "kürz das auf 6 Minuten", "mach daraus ein kurzes Video", "wo ist der Hook", "sortier die Themen", "worum geht es hier eigentlich", "build the story", "decide what stays", "structure this", "cut this down to N minutes", "find the hook", "reorder the topics". This is the CONTENT-selection pass that writes the "story" block in project.json; it runs after transcribe and before cut-rough.

This skill should be used when the user asks for mechanical tightening of material that is already selected - "mach den Rohschnitt", "bau den Rohschnitt", "schneid die Ähms raus", "nimm die Füllwörter raus", "entferne die Pausen", "kürz die Pausen", "schneid die Versprecher raus", "mach den Radioschnitt", "straff das", "build the rough cut", "cut the fillers", "remove the ums", "tighten the pauses", "trim the dead air", "cut the retakes", "radio edit". Turns kept story blocks into enabled segments in project.json. Does not decide what the video is about - that is cut-story.

>- TẠO BỘ CONTENT VIRAL cho MỌI chủ đề/ngành (làm đẹp, F&B, giáo dục, tài chính, công nghệ, BĐS, B2B, thương hiệu cá nhân, cửa hàng địa phương…): đọc brief → vẽ bản đồ khán giả (người xem chính B + người trung gian O, nỗi đau / lợi ích / tò mò) → nghĩ rộng ~30 ý tưởng theo ma trận góc tiếp cận (trực tiếp + gián tiếp, STEPPS) → tự CHẤM ĐIỂM và LOẠI ý yếu → trả 10 chủ đề dễ viral nhất kèm lý do người ta sẽ chia sẻ → viết KỊCH BẢN chi tiết (3 hook, nhịp từng giây, hình, chữ trên màn hình, caption, CTA) và chuyển thể sang nhiều định dạng/lịch đăng. Dùng khi người dùng nói "content viral", "ý tưởng viral", "kịch bản viral", "nghĩ content", "kịch bản TikTok/Reels/Shorts", "bộ content", "lịch content", "chủ đề cho kênh", "hook", "viral script", hoặc gọi /tao-content-viral.

Bibliothèques MonteurOS — formats de reel (Split carte, Avant/après, Recréer ce contenu viral), styles de référence (palette, polices, cartes), ta charte, et cartes animées Hyperframes prêtes à poser (écrans 3D, rail des étapes, médaillon nom, liste surlignée, marqueurs de section, boot « étape », stat courbe + compteur, titre barre, programme/chapitres, citation). Utiliser pour « fais un split », « format avant/après », « ajoute une carte / une infographie / un chiffre animé », « quels styles as-tu », ou pour créer une nouvelle carte ou un nouveau format.

Turn an Indonesian topic prompt into a finished TikTok video (1080x1920 MP4 with voiceover and word-synced captions) using the Klip pipeline in this repo. Use when the user says /klip, "buat video tentang …", "make a TikTok about …", or asks to render a Klip spec.

Mine source material (YouTube lectures, talks, our own past episodes) for citable quotes and turn them into timestamped clips and Citation lower-third cues for the podcast. Use when asked to transcribe a source video, find what someone said about X, pull quotes or clips for an episode, or make citations / lower thirds from a talk or lecture.

Arabic short-video editor (any dialect). Edits talking-head videos and screen recordings, or builds an MG-led video from an idea with no footage - retakes and silences cut, Arabic RTL captions and hook, premium motion graphics, SFX, music, -14 LUFS master, cover - for 9:16, 16:9 or both. Delivers the MP4 plus a project for Resolve, Premiere, After Effects, CapCut or Final Cut. Asks a few questions on first use, keeps the user's brand kit, offers style cards, learns styles from videos, links and MG sites the user shows it, and learns the user's rules after each video. Use when the user asks to edit a video («منتجلي هذا الفيديو», «سوّي مونتاج», «أضف ترجمة», «قص الصمت», «بستايل …», "edit my video"), make a video from an idea («ما عندي فيديو، عندي فكرة», «فكرة فيديو عن…»), learn a style («تعلّم من هذا الفيديو», «هذا الموشن يعجبني»), save a brand («احفظ هويتي», «اقترح لي هوية») or change settings («غيّر إعداداتي»).

Cut silences and dead weight (fillers, repeated takes, false starts) out of a talking-head video BEFORE building the edit - call the measured /auto-trim API instead of hand-rolling ffmpeg, review the dead-weight candidates it returns, and do the one job only a human/AI can do (spotting repeated POINTS). Read this when the brief enables "Tự động cắt ngắn video" (autoCut) or the user complains that the video still has dead weight/silences.

Esta skill deve ser usada para produzir um corte vertical (1080×1920) para Reels do Instagram e TikTok, do começo ao fim e sem nenhuma API (nasceu no canal de cortes do Raul Sena) — pesquisar e baixar a fonte sem tomar bloqueio, ranquear as falas, escrever o roteiro, cortar sem comer palavra, conferir fala, áudio e imagem quadro a quadro, animar a metade de cima em papel recortado no HyperFrames e renderizar. Usar também quando pedirem só uma etapa ("baixa esse vídeo", "faz o roteiro", "corta esse trecho", "confere as emendas", "anima", "renderiza", "qual corte rende mais", "faz um reels"). O app de edição é o HyperFrames e quem ouve o áudio é o Whisper local.

FAÍSCA, motion de alta energia feito em código (HTML + GSAP + HyperFrames), sem crédito de geração. Tipografia cinética pesada, uma cor neon sobre preto com grade de pontos, cometa com rastro, explosão de faíscas, corte com laser, legenda com marca-texto, letras em 3D, câmera atravessando a letra e desfoque de movimento real no MP4. Use quando pedirem "faísca", "FAÍSCA", "motion faísca", "vídeo faísca", "no estilo faísca", "motion neon", "motion com laser e faíscas", "kinetic typography de alta energia", "Reel de motion com brilho neon", "recria esse Reel com esse movimento" ou "motion com trilha própria".

Escribe el copy de un video para redes sociales con SEO - títulos, descripciones, hooks, llamados a la acción, hashtags, bloque de redes y comentario fijado - adaptado a YouTube, Shorts, TikTok, Instagram Reels y Facebook Reels, en uno o varios idiomas. Úsala cuando pidan título, descripción, caption, hashtags, palabras clave o CTA para un video, o como paso de copy dentro de la skill publicar.

**Model check.** If you are Claude Opus 5.5 and the invocation doesn't ask for the full workflow (`--full`, "use the full brag") or for voiceover (`--voice`, which brag-slim doesn't do), switch to brag-slim: read `<skill-dir>/slim.md` (the /brag-slim skill, bundled here) and follow it for the rest of this run instead of this file. Pass along the user's input, and pass any other options (`--no-music`, `--title`, …) as plain-language direction. Tell the user in one line first, e.g. "You're on Opus 5.5, so I'm using /brag-slim: I build the whole video myself. Say 'use the full brag' to switch back." If you are any other model, or can't tell which model you are, skip this check.

Llena campo por campo la pantalla "Crear reel" de Facebook - descripción, personas, ubicación, sentimiento, portada, audio, subtítulos (.srt), audiodescripciones, transcripciones, destinatarios, remixes, etiqueta de IA, grupos, historia, lista de reproducción y promoción. Úsala cuando vayan a subir un reel o video a Facebook o pregunten qué poner en un campo de Facebook.

GSAP animation reference for HyperFrames. Covers gsap.to(), from(), fromTo(), easing, stagger, defaults, timelines (gsap.timeline(), position parameter, labels, nesting, playback), and performance (transforms, will-change, quickTo). Use when writing GSAP animations in HyperFrames compositions.

HyperFrames CLI tool — hyperframes init, lint, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark. Use when scaffolding a project, linting or validating compositions, previewing in the studio, rendering to video, transcribing audio, generating TTS, or troubleshooting the HyperFrames environment.

Edit a raw talking-head video through transcription, silence trimming, mistake review, visual storytelling, motion graphics, and verified HyperFrames rendering. Use for a complete edit; route a single requested operation directly to its specialist skill.

Edita criativos verticais de Instagram (AgroPerforma / Fábrica Blindada) com HyperFrames a partir de takes brutos 4K — escolhe o canal de áudio certo, corta pausas, engasgos e recomeços pelo áudio, monta legenda estática + motions no estilo da marca (tarjas verde/azul, elipse, check, seta), aplica LUT e degradê, zoom calmo com rosto centralizado sem barra preta, fade no fim e renderiza 4K 24 fps. Use quando o pedido for editar/cortar criativos AgroPerforma ou Fábrica Blindada, "passar na fila para edição", fazer variações de gancho, ou corrigir um criativo já entregue.

使用免費本機工具剪輯現有影片與照片，製作繁體中文字幕、電影感片頭、姓名條、文字動畫與轉場，保留可修改專案。適用於學校活動、訪談、紀念影片與一般影片剪輯。

用大语言模型写代码、逐帧渲染科普/讲解短视频（不用任何视频生成模型）。内置 16 种画风（皮影、古地图、3D 拆解、比例尺、Kurzgesagt 式信息图、3Blue1Brown 式数学、水墨、卡点金句等）的完整提示词、精简提示词和可运行示例，外加确定性截帧渲染、抽帧自检、免费 TTS 旁白、字幕和配乐工具。Use when the user wants to make an explainer / 科普 / 讲解 / 动画短视频 with code (HTML Canvas, SVG, Three.js, WebGL), asks for a specific visual style from the catalog, wants a "代码做的视频" or "AI 写代码出片", or needs to render a deterministic web animation to mp4/GIF.

Agent 2 of the video editing pipeline. Finds and removes spoken mistakes — stutters, repeated words, false starts, and retakes (re-recorded lines) — from a talking-head recording. Use after cut-silences, when asked to cut mistakes, remove stutters / repeats / filler restarts, clean up flubs, or keep the best take. Works review-gated: it proposes every cut with context and a reason for approval, then renders only the approved cuts via ffmpeg. Requires a word-level transcript.

Agent 1 of the video editing pipeline. Removes silences and dead air from a talking-head recording. Use when asked to cut silences, trim pauses, remove dead air / gaps, or tighten the pacing of a raw video, given a word-level transcript. Produces an edit list (EDL), a re-timed transcript for downstream agents, and optionally the cut video via ffmpeg. Does NOT cut mistakes, repeats, or false starts — that is the cut-mistakes agent.

使用 Remotion、FFmpeg、Shotcut 與 CPU 語音辨識，在沒有獨立顯示卡或資源有限的電腦剪輯現有影片與照片，製作繁體字幕、片頭、姓名條及轉場，保留可修改專案。適用於學校活動、訪談、紀念影片；需要 DaVinci Resolve 原生專案時使用相應剪輯技能。

封面与标题 A/B：为带货短视频生成多套封面（自动挑选清晰帧或用干净素材图 + 不同标题与版式）和多组标题/文案，导出 3:4 / 9:16 封面文件和对比图，并给出 A/B 测试方法与记录表。Use when the user wants a video cover, 封面, 首图, thumbnail, 标题, 文案, title variants, A/B test covers for 抖音 / 视频号 / 小红书 / TikTok, or wants to improve click-through rate.