Video & Animation

Research Instagram Reels with the reels_* MCP tools: read Reels from their URLs (details, timestamped transcript, real frames), extract hooks, quotes and on-screen text across many Reels, compare how creators open their Reels, and collect Reel links from web pages. Use for requests like 'analyze the hooks of these Reels', 'what do these creators say about X', 'find Reels about Y and break down how they open'.

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.

Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link or asks to bring a Figma design, frame, logo, brand, or animation into a video/composition.

Best practices for the Remotion Shorts factory in this repo. Use when editing ShortVideo, pipeline phases, animations, FFmpeg post-process, or adding animation libraries.

>- CarVendors Video Studio v4 — the team's one skill for CarVendors.co.uk videos (B&F Cars Northampton as featured dealer). Main job: re-edit the ~200 old @bnf_cars TikTok videos (Google Drive, folders 1-200) into polished, rebranded CarVendors Reels / TikTok / YouTube Shorts in bulk, cheaply: attention hook (played in full) → one transition → the whole original video → outro, fixed logo badge, old text kept/covered/removed, premium text on key beats, music, loudness, QA, shared hook-usage ledger. Works on Mac and Windows. Use for any CarVendors / B&F video request: "edit video 7", "plan 1-20", "render the ready ones", "which hooks were used", new ads, voiceovers, captions. Do not use this brand for other clients.

规划、制作或诊断建筑与场景的穿越机视频，覆盖航线叙事、连续运动、净空、原生时序和视频交付。适用于 FPV 飞行镜头，不用于把普通慢速漫游直接包装成已验收穿越机成片。

Cria vídeos promocionais de motion design premium (9:16 / 16:9, 60fps, com SFX/música) para produtos, SaaS, relógios etc. a partir de HTML+Playwright+ffmpeg. Use para pedidos de motion, vídeo de anúncio, reels, promo animado.

将用户提供的科普文章和已有音频直接制作成白板讲解视频，自动完成解释图、分步分镜、音频对齐、字幕、重点标注与渲染，交付 MP4 和可编辑工程。用于“文章加音频生成视频”及后续修改；不用于仅讨论方案、只写文章或只做素材包。

This skill should be used when the user asks for subtitles or on-screen text of what is being said - "brenn die Untertitel ein", "mach Untertitel", "Untertitel drauf", "leg Untertitel drüber", "brenn die Subs ein", "mach die Captions", "Wort für Wort Untertitel", "Karaoke-Untertitel", "korrigier den Untertitel-Text", "burn in the captions", "add subtitles", "burn the subs", "word-by-word captions", "fix a caption typo". Covers ASS generation, the pixel-width grouping rule for German, the font table, and burn-in through libass.

用 OpenMontage（開源 AI 影片製作流水線，<SKILLS_DIR>/OpenMontage）做 Josh 的影片時的「本家規則」轉接層。適用：長片剪成多支短片（clip-factory）、真實螢幕錄製教學（screen-demo）、翻譯配音（localization-dub）、Podcast 轉影片（podcast-repurpose）、「照這支參考影片做」（reference video 分析）、無旁白紀錄片蒙太奇（documentary-montage），以及幫 stock-footage-reel 加抓 NASA／國會圖書館／NARA／Archive.org 老片。觸發語：「用 OpenMontage」、「長片切短片」、「照這支 Reel 做」、「翻譯配音」、「螢幕教學影片」。

收到「做一支影片／Reel」時先用：判斷影片類型、轉給對應的影片 skill，套用共用本家規則並交給事實編輯。只做草稿，不發文。

为培训/讲解视频自动添加中英文双语字幕（转写+翻译+硬字幕合成），并按主题/角色拆分成 10 分钟以内短视频。Use when 用户要求：给视频加中英字幕、培训视频双语字幕、视频转写并翻译英文字幕、外籍员工字幕支持、把培训视频按主题/角色/章节拆分成短视频、碎片化学习视频切分，或每年制度修订后对培训视频字幕做微调并重新渲染。核心能力：Qwen3-Omni 结合参考文档/制度文档做高精度中文转写（解决 whisper/funasr 专业术语识别差的问题），faster-whisper 提取时间轴，拼音全局对齐，术语表驱动的中译英，输出双语 SRT + 硬字幕视频 + 可编辑字幕工程文件（支持后续微调重渲染，无需重新转写）。命令：python3 scripts/pipeline.py build|render|split|status。

Edit any footage (event, talking head, interview, demo, tutorial, announcement, behind-the-scenes) into an Instagram Reel or LinkedIn video matched to the user's references, with designed motion, captions, original score, cover and post caption, using the claude-video-studio framework.

Apple / OpenAI-style product launch film or premium spec ad (30–60 s) — minimal supers, big product moments, signature transition, piano/pulse score, end-card lockup. Shots come from code (HyperFrames scenes), Higgsfield AI image→video, or real product footage, all assembled and rendered in HyperFrames. Includes the fold-cut builder (shots hinge shut/open on the centre line).

Fast CapCut-style chop-cut reel with a story — showreels, hype edits, launch teasers, "make it punchy". One canvas engine on a beat grid (punch-ins on cuts, flash frames, impact shakes, whip pans, speed ramps, freeze frames) rendered in HyperFrames, in 16:9 and 9:16 from one edit, with an original synthesized score locked to the cuts.

Guided studio for narrated, fact-checked explainer videos in a Vox-style editorial look (bold collage, flat colour fields, marker annotations, big numbers) or a paper-diorama documentary look. One idea in → sourced script in 10-second blocks → style key + per-scene prompts (or free code-built collage scenes) → offline voiceover fitted to each block → HyperFrames cut with captions, animated number callouts and an original score, in 16:9 and/or 9:16. Use for "Vox-style video", "explainer", "animated explainer", "data-driven video", "make a video about X", "why does X happen".

Painterly and illustrated animation — Kurzgesagt-style flat science explainers ("what's inside", scale, mechanisms), art-history styles (Van Gogh, Monet, Lichtenstein, Kusama, Matisse, cubism, ink wash, 8-bit, Roman mosaic, cave painting, Persian miniature…). Uses the huashu-art-motion canvas engine with CUSTOM scenes, renders MP4s, and assembles/scores them in HyperFrames. Also the claude-animation plugin for hand-drawn 2D.

Add styled, word-synced captions (and an optional scroll-stopping hook) to a talking video. The user gives a video; you transcribe it, show every caption style rendered on their own footage, they pick a style and hook, and you render the captioned MP4. Use when the user uploads/gives a video and says "caption this", "add captions/subtitles", "make captions", "caption styles", "add a hook", or invokes /caption-video.

Adnaan's house reel style. Turns a raw talking-head take (plus an optional script, links, screen recordings or screenshots) into a finished vertical reel where EVERY beat is a full-screen animated scene in the v7 "MINT" look (house default since 2026-10-17) — TALK beats with him full-screen and our heavy kinetic grotesk captions (Inter Tight 900 + Inter; charcoal with a soft glow, one mint hero word) instead of subtitles, sometimes with objects sliding out from BEHIND him (depth via his background-removed matte); VISUAL beats on a grey paper board with a strong vignette where white Phosphor glyphs sit in mint/charcoal icon discs, a disc CHAIN maps the list, the camera travels across a world bigger than the frame, and props are clean flat vector illustrations; the SIGNATURE SHRINK (his full-screen footage shrinks into the current chain disc or a small left-side card, and grows back for the payoff); an optional frame-0 text hook; the real pages/posts/repos he mentions as big READABLE cards with a mint highli...

Long-form YouTube editing (16:9, 5–15 min explainers, talks and walkthroughs) in a company's brand — Stripe by default. Turns a camera take (plus any screen recordings, or a Cap project) into a finished video: the adnaan-reel v7 design system on a 16:9 board, re-coloured from ONE brand file (brand/stripe.json: blurple accent, slate discs and ink, cool paper, the official wordmark) — a gridded paper board with a strong vignette most of the time, the speaker's plain camera in a fixed rounded card with an accent ring, full-frame talk as punctuation with full-coverage kinetic captions, disc-chain maps the camera travels along, flat white cards, real pages with a highlighter, data in one data colour, screen recordings in a window card with click-planned zooms, before/after inserts that carry their own sound, sparse structural SFX and a ducked ElevenLabs music bed ~5 dB under the voice. Cuts every pause, retake and look-down; builds only the designed moments as HyperFrames scenes in parallel, composites the rest...

Make a polished vertical promo video for an iOS app with Apple's real 3D iPhone model, real app UI captured from the simulator, motion graphics and generated music and sound, in Remotion. Use when someone wants a promo video, launch video, ad, App Store preview-style clip or "brag video" for their app, or says /app-promo.

Transcribe audio locally, preserve word timestamps through edits, style readable captions, and prepare editable subtitle sidecars.

Generate local or optional OpenAI narration, prepare music and sound effects, and mix audio for technical videos.

Write Minara video scripts before any animation work — launch / promo films, single-scene supplements, use case tutorials. Turns a brief, product screenshots, frontend code, Figma frames or a feature note into an English-only script doc built around a keyframe sheet; each keyframe has a still image (rendered from UI code, exported from Figma, or AIGC-generated from screenshots), a picture description, the voiceover line, on-screen text (花字) with style, timing and duration, and the BGM style / sound cues. Also covers what each scene must land, user flow + UI copy, voiceover word budget and open questions, in a calm, neutral, natural voice. Then hands off to minara-video, minara-usecase-video and minara-music. Use for /minara-videoscript, "写视频脚本", "视频脚本", "分镜脚本", "关键帧", "关键帧脚本", "花字", "补充脚本", "旁白稿", "video script", "voiceover script", "keyframes".