Video & Animation

编码 Agent 做视频时的能力地图与工艺手册：列出可调用的画面、3D、生成式模型、合成与音频能力（Remotion、HyperFrames、three.js、Blender、Tripo、生成视频/图像/3D/音频模型、numpy、ffmpeg 等）和真实素材来源（本地素材索引、开放素材库检索与授权），说明各自擅长的表达、边界、代价与验证状态，附历史案例的组合、经验与坑；每个案例收尾时判断有没有值得沉淀的新工具、方法、教训，有才回写进本手册。用户要用代码或 Agent 产出 MG、讲解片、产品宣传片、3D 动画、短片、数据可视化视频，或在规划视频该用哪些工具时使用。纯转写、视频内容分析、单张生图不触发。

Add the voiceover, word-timed captions and sound effects to a faceless reel and produce the finished video. Works with a free AI voice (Malayalam, English, Hindi, Tamil and many more), ElevenLabs, or the user's own recording. Use when someone wants a voiceover, captions or subtitles on an animated reel, sound effects, or to finish, render or export a reel made with viral-animate. Fourth step of the viral pack.

Redesign GitHub README homepages or create project-native pure SVG, hybrid SVG-composed PNG/WebP, and opt-in animated GIF assets. Use when a user asks to beautify, redesign, rebrand, visually upgrade, simplify, or audit a GitHub README; create only a hero, section headers, diagrams, badges, motion graphics, showcase modules, or other README assets; or turn a repository homepage into a cohesive visual story. If whole-README work versus asset-only work is unclear, ask which scope the user wants. For hero-like assets where pure SVG and generated raster material are both viable, explain the tradeoffs and confirm the implementation before creating the asset.

Produces short looping motion social creatives in Codex. Use when creating motion graphics, stop-motion ads, animated social posts, looping MP4/GIF creatives, Reel-style frame sequences, storyboards, frame prompts, and simple video assembly from generated images.

Plan and produce videos from concepts, scripts, supplied footage, animation, effects, narration and music with OpenMontage pipelines, checkpoints, local FFmpeg, Remotion and HyperFrames.

Edits a talking-head clip into a storytelling reel. Three simple image cards run across the top, with a bold black-box title and a small white subtitle under them, all landing together over one continuous take with simple TikTok-style captions (white, black outline, 1 to 3 words). Use when the user runs /storytelling or asks for a story or proof reel, "three images and a title", or a lead-magnet style edit on a 9:16 clip.

Continuous-scene Remotion camera system with mandatory intake, approved-reference review, anti-neon rules, and first-pass QA.

Directs a faceless vertical short from idea to finished, mastered file, and gets better with every run. Picks a format, writes the episode in a writers' room (three premises judged as the buyer), voices it, gates on an animatic, then decides beat by beat how each moment is made: drawn in code in Remotion, a cut-out from a generated still, a generated clip, or one of the engine tracks. Modes: series, writers-room, produce, sound, finish, bakeoff, effects (/effects), improve (the learning loop after every short). Formats so far: character skit with dialogue and synced mouths, photoreal mini documentary with sourced figures. Triggers on "make a short", "next episode", "make a video about X", "faceless video", "reel for this offer". Do NOT trigger for editing an existing video file, for a pure code-drawn explainer with no writers' room (make-short), or for collage (make-vox).

Make a "What If" animated episode from one topic line ("What if you could rewind 10 seconds?"), in the dusk-lit stick-figure style of the What If channels that broke out on YouTube in October 2026. Writes the script on the seven-beat What If formula, voices it with ElevenLabs, lays out a shot list at the genre's pace, renders a storyboard of stills and self-checks it before animating, animates every frame in code (Remotion and SVG, with an original cast on one rig, rooms in perspective and light from lamps and windows), generates and syncs the sound, and masters a finished 15-25 s episode to -14 LUFS. Use when someone asks for a What If episode, animation or cartoon, "make a what if video about X", a stick-figure explainer in this style, or to run the free What If skill.

Create looping outline animations from geometric shapes or supplied SVGs using staggered copies, shape-specific tilt and rotation, pronounced easing, and a subtle halo. Deliver a live adjustable preview and exported video. Use for contour motion graphics, not general interface transitions.

Make cinematic product promo videos of a real web app in Remotion: captures the real pages, picks from ~124-150 shot recipe cards, offers the Ink Press template, beat sync and Freesound sound design. Use for "make a promo/launch video of my site/app", single shot-card effects, or finding/aligning SFX for an existing product video. Always fetches latest.

Rules, Remotion helpers and audio scripts for stop-motion style video cut to music, proposing Remotion by default to make it. A low frame rate is kept on purpose, with one pose per eighth note of the song. Pages start on bar lines, clicks land on kicks and snares, and the skill teaches when to skip a beat. Use when making or reviewing stop-motion, low frame rate, beat-synced or music-synced video. Also use for cutting a video to a song, Remotion launch films cut to a track, compositions timed to a BPM, metronome or click tracks, kinetic type timed to a beat, or scenes played live on a web page in time with a metronome. It covers measuring a song's tempo, bars and drops, and deciding where a cut, a click, a hold or a transition should land.

Spatial Film - the film engine behind talking-explainer. Make a 45-90 s unnarrated spatial 3D product motion graphic (one CSS-3D camera, push-throughs, no hard cuts, last frame loops into the first) with real product UI, platform-faithful third-party canvases (GHL, n8n, Zapier), a native-tempo music bed and SFX, rendered at 1080p60 via HyperFrames. Built by 5 parallel scene workers against one contract (frame.md + seam table + per-scene harness). Use when the user says "spatial film" or "3D motion graphic", hands over a MOTION-PROMPT.md, or asks for a 6+ scene / 3D-camera product video with NO voiceover. A narrated explainer (the user's voice and/or a mascot presenting) is explainer-kit, which runs on this skill's machinery.

One-take motion films (一镜到底动效短片), vertical-first: 9:16 1080×1920 promos, teasers and skill/app films for 小红书 / 抖音 / 视频号, where every beat grows out of the one before and the picture runs on a music grid. Modified from onetake: adds what its protocol cannot give (material worth looking at, a music clock, an arc, change as content, review rounds), lets the reference's measured numbers outrank the genre rules, a verify oracle that judges stillness and quiet against the reference, vertical stills and safe zones, a numpy beat-grid finder, and the nested-portal dive (画中洞天) from the W1-v2 film. Also: make short product / skill motion videos (10–30 s, narrated feature demos up to ~60 s) the way high-end launch clips are made — kinetic type, real UI as the material, a hand that causes every reaction, beats that carry into each other instead of replacing each other, hard cuts only where they mean something — without HyperFrames or Remotion. A single HTML composition where every value is a pure function of time…

Build premium, realistic soundtracks for code-made videos and animations from real licensed recordings - launch films, product and feature videos, UI walkthroughs, logo stings, explainers, trailers and animated shorts made with Remotion, HyperFrames, three.js, GSAP or any renderer. Use this whenever a video or animation needs sound design, SFX, foley, ambience, music, a soundtrack, a score, UI click / whoosh / riser / impact / logo-sting sounds, or a music edit to picture; whenever a synthesized or "random" sounding soundtrack must be replaced with real recordings; or when the user asks to source, license, credit, mix, master, critique or mux audio for a film. It covers cue lists from the picture, sourcing from Freesound / Mixkit / composer libraries with licence checks, a music edit at bar lines, a JSON sound design rendered by a deterministic mixer, measured QA (clicks, masking, harshness, sync, loudness) plus earshot listening, a multi-agent critique, mastering, credits and the mux.

Plan, create, edit, preview, and render polished AI-assisted videos, product promos, explainers, and cinematic multi-shot stories. Combines HyperFrames or Remotion rendering, Shotcraft-style product direction, and fal.ai footage workflows. Use when the user asks to make, script, storyboard, edit, or render a video, reel, promo, launch film, explainer, ad, trailer, demo video, animated intro, or motion graphic, or to generate AI footage or shot prompts, even if they don't name a tool. Skip for still images, slide decks, and questions about video that change nothing.

Turn a project or a live website into a finished 15–25 second vertical promo for Reels, TikTok and Shorts, with music, motion, a cover frame and a share caption. Follows Turkish on-screen copy rules. Use for /vitrin, putting a project in the window, or making a video of a site.

Keeps all text, logos, captions, CTAs and faces inside the safe zone of Instagram Reels, Stories, Feed, TikTok, YouTube Shorts and LinkedIn when making videos, reels, carousels, thumbnails or graphics. Use this skill whenever the user asks for a reel, story, short, TikTok, social video, post graphic, promo video or any 9:16 / 4:5 / 1080x1920 / 1080x1350 design, even if they never say "safe zone". Also use it to check, auto-fix or preview an existing design or video against platform UI overlap (buttons, captions, profile bar, grid crop).

اكتب سكربت فيديو يوتيوب عربي من فكرة خام: خمس افتتاحيات من 21 صيغة، مقاسة بأداة، ثم السكربت المنطوق كاملا مع ما يظهر على الشاشة. استخدمها عند طلب سكربت فيديو، افتتاحية، هوك، أول جملة، وش أقول في الفيديو، اكتب لي فيديو، أو قبل التصوير بدون أول 15 ثانية. Arabic YouTube script writer: "write my video script in Arabic", "Arabic hook", "سكربت يوتيوب".

Produce short promo videos (vertical 9:16 reels, 16:9 web spots) from raw phone/camera footage with Remotion, including proxy generation, contact sheets for choosing clips, brand theming, and the render pitfalls that waste hours (Turkish uppercase, ffmpeg stdin, HEVC output, missing drawtext). Use when the user says "make a promo video", "reel from this footage", "Remotion", "tanıtım videosu", "kısa video render", or needs code-driven text/branding over real footage.

用2ByteASR MCP制作带字幕视频，完成三模型识别、校对、剪辑、5标题、3简介、tags和三比例封面，原片移动归位后按单视频文件夹交付；默认仅本地制作，上传可选。

Fill out, review and strengthen a16z speedrun accelerator applications — every form field within its character limit, founder bios, team section, one-liner, description, traction, deck review, the team video talking points — plus speedrun interview prep and mock interviews, and answer questions about applying to a16z speedrun (deal, cohorts, eligibility). Use whenever someone mentions a16z speedrun, speedrun.a16z.com, an SR cohort (e.g. SR008), or applying to Andreessen Horowitz's accelerator.

Usar y hacer crecer la biblioteca comunitaria de modelos 3D procedurales (Three.js) para explicadores animados — buscar en CATALOGO.md, ver un modelo en vista.html, copiarlo a un proyecto, y al terminar CADA video detectar los modelos nuevos, dejarlos listos (miniatura, catálogo, autor, CC BY 4.0) y preguntar "¿Los subo a la biblioteca? (S/n)" para abrir el PR con gh. Úsala antes de modelar cualquier objeto 3D en un explicador ("¿ya hay un flexómetro, un mosquito, un árbol?"), cuando el usuario pregunte qué modelos hay, o cuando termine un video con modelos nuevos que valga la pena compartir.

Build a short vertical (9:16) reel, Short, TikTok, ad or animated explainer video for free, entirely from code, with word-by-word captions and optional voiceover and music sync. No footage, no stock clips, no paid software, no AI video generation, no browser. Use whenever the user wants a reel, short, Instagram, YouTube or TikTok video or ad, a captions video, a voiceover-synced explainer, or wants an ad script or product description turned into a video, even if they never say "canvas", "ffmpeg" or "JSON". Works in English and Hindi out of the box and other scripts with an added font.