Video & Animation

Use when turning a seminar, webinar or conference recording into an editable slide deck: slides from video frames, annotated links, and transcript excerpts as speaker notes.

Design and deliver subtitle style mockups and animated comparison samples for the MMD/K-pop dance videos — S1–S6 style catalogue (Y2K chrome, minimal kinetic, glitch, mix&match editorial, graphic emphasis, hand-marker), PIL/numpy effect recipes, font list, contact-sheet/comparison video conventions, and the parallel-subagent workflow used for S4 vs S6. Load this when asked 出几个静态帧方案/参考女团PV字幕/做个小样/对比几个风格, or when choosing a visual direction before building a full-length subtitle track.

End-to-end recipe for making subtitles for the MMD dance videos in this workspace (字幕/ project) — probe the source, pick a segment, map LRC cues, choose a style, build ASS, burn, verify, and deliver. Load this when starting or resuming any subtitle task (静态稿/5s小样/30s小样/全片/透明叠加层), when a render "succeeded" but the video has no text, or when you need this project's paths, font list, cue sheet and acceptance criteria.

Character-avoiding subtitle layout for the MMD dance videos — measure the dancer's per-frame bounding box, compute a per-cue union, place text in safe side/top columns, and verify zero overlap on every frame. Load this when asked 字幕不要挡住人物/完全不挡/避让, or when text overlaps wings/body and you need a verified-free layout with measured overlap counts.

Build professional vertical (9:16) YouTube Shorts / Reels / TikTok explainer and tech-news videos fully in Python (no editor needed) - researched script (Hinglish/Hindi/English), ElevenLabs voiceover, word-level sync, multi-font + multi-palette motion graphics, real colour-emoji icons, 8 different transitions, kinetic captions, synthesized music + SFX with voice ducking, and a visual QA gate. Use whenever the user asks for a short video, news video, explainer, reel, or "make a video like the previous one" and wants it to NOT look AI-generated / template-like.

Use when working with The Senate (WoW guild) ranks or promotions on Discord. Covers the class ladder (Imperator, Consul, Senator, Legionnaire/Civis, Plebeian), the formal Plebeian to Civis/Legionnaire vote, the informal promotion to Senator, and Consul appointments. Includes guild, role, and channel IDs plus the Discord MCP workflow.

>- Write the Instagram caption - the line that survives the "... more" cut, the body, the single ask, the search terms and up to five hashtags - and lint it before it goes out. Use when the user says "write the caption", "caption this", "what do I put in the description", has a reel or a carousel ready and needs the text, or asks about hashtags.

Create, revise, or review readable Remotion product demos, app showcases, and UI ads with purposeful choreography, authentic interface content, deterministic animation, and optional sound.

Add auto-generated hard subtitles to a video file or URL and output a subtitled MP4 plus SRT. Use when the user asks to caption or subtitle a video. Do not use for editing existing subtitles only.

Motion graphics, launch videos and explainers as editable code. A director picks the motion language for your product; you point at frames to change them. 动画、发布片、解说视频，指着画面改。

Build, fix or audit motion-graphics videos (promos, explainers, brand films, logo stings, 9:16 cuts) in EffectCraft, the After Effects-style compositor, with voiceover, music and SFX in sync. Use this whenever the user mentions EffectCraft, an .ecproj file, effectcraft-cli, or asks for a motion graphic / promo video / animated explainer for a brand or website on this machine - including fixing or reviewing an existing EffectCraft project made by another agent - even if they don't name the tool.

Analiza transcripts y fichas de vídeos nuevos y actualiza la skill editor-video con la lógica de edición aprendida. Úsala cuando el usuario diga "nutre el editor", "procesa los transcripts nuevos", "aprende de estos vídeos" o añada archivos a transcripts/nuevos/.

Editor de vídeo experto para YouTube con criterio propio. Edita brutos (corte, limpieza de voz, motion graphics, subtítulos de énfasis, efectos de sonido) aplicando la lógica de edición de vídeos que retienen, adaptada al formato del vídeo, a las referencias del creador y a su branding, y entrega un kit por capas listo para CapCut donde solo falta el LUT y la banda sonora. También analiza vídeos de referencia segundo a segundo para extraer la lógica de su edición. Usa esta skill siempre que el usuario quiera editar o montar un vídeo, preparar un vídeo para CapCut, crear motion graphics o subtítulos para un vídeo, colocar efectos de sonido, analizar la edición de otro vídeo o creador, "editar como" alguien, configurar su estilo de edición, o cuando añada archivos a brutos/ o referencias/, aunque no mencione la palabra "skill".

First-run setup conversation for a new creator of the AI Video Factory. Asks exactly five short questions (what to create, where it will be published, language and tone, own brand/product/characters, budget per video), writes studio.json, creates the first project, and explains how to start other formats in new conversations. Use right after installation, when studio.json does not exist, or when the user says "onboarding", "empecemos", "set me up", "configura la fábrica", "what can I make?".

Produces long-form ambient videos (10 minutes to 3 hours) — guided meditation, sleep stories, breathwork, affirmations, yoga nidra, focus/study music, ambient loops — with seamless looping AI scenes, a Suno music bed and an optional ElevenLabs voice-over with long pauses, delivered as 1080p YouTube video plus MP3. Use for "meditación", "meditation video", "sleep story", "música para dormir", "ambient loop", "focus music", "video largo de relajación", "yoga nidra", "affirmations".

Machine-check rendered videos (shorts, long-form, social clips) with ffmpeg instead of eyeballing - frozen/still stretches, dead air, loudness and true peak, duration/size/audio-presence, subtitle format and reading speed, and a "flat opening" visual-density measure. Use when producing videos with an AI/automated pipeline, when you need objective publish gates, or when a video "passes" review but feels like a slideshow. Exit code 3 = could not measure, never a pass.

Voice the narration of an article explainer video - Cartesia TTS with word timestamps (key lookup, voice ids, model), the local Kokoro fallback, pronunciation tips for numbers and symbols, choosing a Spanish voice, and the audio QA thresholds (clipping, garbled lines, -16 LUFS). Use when running or debugging npm run tts / npm run audio-qa, or when the narration sounds wrong.

Turn lecture notes (typed or handwritten PDFs, scans, phone photos, Markdown) into a narrated lecture video (MP4) with clean academic slides, step-by-step animated diagrams, a natural British narrator, and exam-style checkpoint questions that pause with a countdown before revealing the answer. Self-installing and fully automated - one script sets up Python, LaTeX, ffmpeg and offline voices on macOS, Linux or Windows, then renders the video. Use this whenever the user wants a lecture, notes, slides, handout, chapter or problem set turned into a video, a narrated walkthrough, a "lecture recording", an explainer with visuals, or a study video to watch or revise from - even if they just say "make this into a video" or "explain lecture 5 to me as a video".

Build the scenes of an article explainer video in Remotion - write src/timeline.ts from an approved script, pick and configure animation components (Counter, BarCompare, FlowDiagram, KeyQuote, StatGrid), add a bespoke component with a tested frameState, keep to the vertical safe area and check rendered stills by eye. Use when composing, changing or debugging the scenes of a video made with this plugin.

Turn a published blog article into a short narrated, animated vertical explainer video (30-60 s, 1080x1920) in the AGILabs brand, rendered locally with Remotion. Use when asked to make a video, reel, short or explainer from an article or blog post, or to re-render one made with this plugin (a folder with video.config.mjs and src/timeline.ts).

Write the script for a 30-60 s narrated explainer video of a blog article - hook, setup, experiment, finding with its exact number, so-what and closing card - with a visual idea per scene mapped to an animation component, caption reading-speed limits and an optional parallel Spanish version. Use when drafting or revising what an article video says, before any scene is built.

Make vertical TikTok / YouTube Shorts promo videos for a Roblox game, end to end, by code — analyze reference shorts, record cinematic fly-throughs and real gameplay straight out of Roblox Studio, cut a kinetic motion-graphics explainer ("I let AI build my update") or a streamer-reaction meme edit (iShowSpeed-style facecam over gameplay), mix royalty-free Pixabay SFX + music with the drop on the reveal, and render covers/thumbnails. Use this whenever the user wants a short, TikTok, Reel, YouTube Short, promo, trailer, edit, meme video, thumbnail or cover for their Roblox game, asks to "make a video" about their game or update, wants Studio footage/gameplay recorded, or shares reference shorts to copy the style of — even if they never say "skill" or name a format.

Build, fix and promote the Roblox game Emotion Tycoon via Studio MCP and Blender: your house rules, asset IDs, pass IDs, known gotchas and the automated promo-video recipe.

When the user wants social captions or post copy written or reviewed for a specific platform. Also use when the user mentions 'write a caption', 'LinkedIn post', 'Instagram caption', 'TikTok caption', 'tweet', 'post copy', or pastes a caption and asks if it is good, too long, or ready to post.