Video & Animation

Use when the user sends a finished 9:16 reel cut (Instagram Reels, TikTok, Shorts) and wants an overlay on top - captions, title, image assets (logos, people cutouts), comment-keyword card, "share this with" end card, sound effects - either as a transparent overlay file or burned into the final video. Triggers: "make the overlay", "add captions and assets", "here's the cut", "/reel-overlay". Not for cutting/editing the footage itself, zooms, or colour grading.

Turns long-form video (podcast, interview, talk, panel, webinar, livestream; a local file or a URL) into captioned vertical Shorts, Reels and TikToks, plus optional 16:9 clips. Finds the hooks, recomposes each cut hook-first, burns word-timed captions with a hook card, makes covers and runs a QA pass. Use when the user says "cut reels/shorts/clips from this video/podcast/panel/talk", "find the hooks", "find the best moments", "clip this episode", "make shorts from this recording", "turn this interview into reels", "caption this video", "add captions to my clip", "make reels covers", "give this clip a cold open", "recut this clip" or "make this short tighter", or hands over a long recording and wants short-form out of it. Transcription, framing and rendering run locally; the agent writes the moments ledger and the edit spec, and the user approves the shortlist and the final files. Never uploads or publishes.

Edit a talking-head video in the glass-and-paper style - liquid-glass logo tiles, paper backgrounds, pop-out PiP, kinetic captions. Use when someone sends a clip to edit in this style.

Cuts cinematic highlight videos, trailers/teasers and event recaps from real footage (mp-footage), AI clips (mp-genclip) or pure code — beat-synced edit plan, speed ramps, cinematic grade (teal-amber, bleach, film grain, letterbox), kinetic titles, glitch and light-leak overlays, data overlays, all composited in HyperFrames on top of an ffmpeg base cut. Use for "Highlight-Video", "Cinematic", "Trailer", "Recap", "Aftermovie", "Best-of", "Montage", "auf den Beat schneiden", "episch".

Generates AI video clips (Seedance, Veo, Kling via the kie.ai MCP server) and AI still frames (gpt-image, nano-banana) as the basis for cinematic highlight videos and trailers — shot-by-shot prompts from the storyboard, consistent look via reference frames and seeds, download, registration in SHOTLIST.json. Use when the user has no footage but wants cinematic shots, says "generier mir Clips", "KI-Video", "Seedance", "Veo", "B-Roll erzeugen", or when mp-highlight needs shots that do not exist.

Step 4 of motion-pack. Builds the HyperFrames project from STORYBOARD.md and STYLE.md — one HTML scene per beat with GSAP choreography, deterministic timing, real assets, then lint → draft render. Use after mp-storyboard, or when the user says "bau das", "build", "render", "Szene ändern", "HyperFrames", "GSAP", "animiere".

Step 2 of motion-pack. Turns BRIEF.md into STYLE.md — a reference-driven design doc with palette, typography, motion language, sound character and a forbidden list. Offers 8 built-in style presets (clean-product, editorial-brutal, neo-glass, kinetic-type, hand-drawn, cinematic-dark, data-minimal, retro-print). Use when a video needs a look, the user says "Style", "Look", "Design", "wie soll es aussehen", or after mp-brief.

Ingests the user's own footage (clips, gameplay, events, vlogs, screen recordings) for a highlight video — makes proxies, detects scene cuts, scores every second by motion, loudness and speech, transcribes, and writes SHOTLIST.json with the best candidate moments. Use when the user hands over video files/folders, says "aus meinem Material", "Footage", "beste Momente", "Highlights rausziehen", "schneid mir das zusammen", or before mp-highlight when real footage is the basis.

Step 1 of motion-pack. Runs a short, tap-friendly interview (max 2 rounds × 3 questions) and writes BRIEF.md for a motion graphics video — goal, audience, hook, format, length, must-show, sources, audio wishes. Use whenever a video is requested and no BRIEF.md exists yet, or the user says "Briefing", "interview me", "was brauchst du von mir".

Step 7 of motion-pack. Final render in every requested format (16:9, 9:16, 1:1, 4:5, GIF/WebM), writes DELIVERY.md (files, specs, loudness, sources, unverified claims, next steps), optionally packages the finished pipeline as a reusable skill so the next video is one sentence. Use when critique is green, or the user says "export", "final", "liefern", "alle Formate", "fertig machen".

Step 3 of motion-pack. Writes STORYBOARD.md — beats with timestamps, a state list per beat (what is on screen, where, what changes), voice lines, SFX hits and transitions — from BRIEF.md and STYLE.md. Use after mp-style, or when the user asks for "Storyboard", "Beats", "Ablauf", "Szenen", "timing".

Step 6 of motion-pack. Makes the agent look at its own render — contact sheet, phone-size sheet, 12-frame strips around fast moments, loop-seam check, determinism check — then scores 8 criteria 1–10 as a harsh motion director, lists the 3 biggest problems with timestamps, and loops back to mp-build until every score is ≥ 8. Use after any render, or when the user says "sieht mid aus", "check das Video", "Kritik", "QC", "warum wirkt das billig".

Step 5 of motion-pack. Produces the audio layer — voice-over via ElevenLabs (API key only from the ELEVENLABS_API_KEY environment variable), music bed, SFX on hits, sidechain ducking and two-pass loudness normalisation (voice -16 LUFS, music 12 LU under, mix -14 LUFS, true peak -1 dBTP). Use after mp-build, or when the user mentions "Stimme", "Voice-over", "Musik", "Sound", "LUFS", "zu leise", "zu laut", "ElevenLabs".

Use when analyzing or recreating reel subtitle grammar.

Cut video from transcripts; graphics + ffmpeg, no NLE.

Studio-grade motion graphics and cinematic highlight videos built as code with HyperFrames (HTML + GSAP → MP4) plus ffmpeg edits of real or AI footage. ALWAYS use for any video, spot, reel, teaser, trailer, intro, logo sting, kinetic typography, product film, social clip, highlight/recap/aftermovie/montage, "mach mir ein Video", "Motion Graphics", "Werbespot", "Reel", "Cinematic", "Animation" — even if the user does not say HyperFrames. Interviews the user first, then chains mp-brief → mp-style → mp-storyboard → (mp-footage | mp-genclip) → mp-build / mp-highlight → mp-audio → mp-critique → mp-ship with approval gates.

Build animated HTML/GSAP reel cards with hyperframes.

Maintain the existing May Shorts teaching compositions using their legacy face-mode, scene-overlay, and karaoke-caption patterns. Use only when working on those examples or explicitly requesting this legacy scaffold. For new reels, Shorts, or short advertisements, use short-form-edit.

Marketing-video studio — produces professional vertical promo, launch and feature videos for any website or iOS app, end to end. Checks and helps install the toolchain, interviews the user (channel, length, style, pacing, music, sound, voice) with defaults from a saved profile, films the real product frame-perfect (web via Playwright virtual clock, iOS Simulator via Maestro at 60 fps, or imported recordings), fills empty screens with disclosed demo data through a local proxy, writes a storyboard, and renders with Remotion at 60 fps with real motion blur — phone camera moves, synced callouts with arrows and zooms, graphic widgets, kinetic titles, narrative transitions without crossfades, a track spliced on its bars (Suno prompt generator, licensed track or generated bed), real sound effects, optional voiceover — then QA-checks layout, sync, safe zones, frame pops and colour, and delivers cutdowns, crops and App Store previews. Use for /marketing-video, any promo / ad / launch / feature / app-store video req...

Word-by-word captions that stay in sync with speech that switches between Moroccan Darija, Arabic, French and English. Transcribes with a speech-to-text model, times every word with local forced alignment (WhisperX + wav2vec2), then renders the captions with HyperFrames or Remotion. Use when someone asks for word-by-word, karaoke-style or synced captions on a Darija or mixed-language talking video.

Make an animated explainer video that helps someone understand a technical idea, such as a bug, a system design question or an algorithm. Runs fully on the local machine with no paid APIs (manim for animation, Kokoro for narration, faster-whisper for captions, generated sound effects, ffmpeg to put it together). The look is minimal: black background, one accent colour, one diagram that keeps changing, small UI cards and a status line at the bottom. Use it when someone asks for an animated or explainer video, something "like Engineering Digest", or a narrated walkthrough of a concept with captions and sound.

根据使用者文稿、原配音和时间字幕制作或修订科普与心理学讲解视频，交付真实参考绑定、解释动画与可编辑剪映草稿；保留自己的IP、画风、语言及字幕设置。独立文稿研究不启动生图。

Use when the user asks for an explainer video, an animated explanation, a narrated video, a "3blue1brown style" or "3b1b style" video, or a Manim animation on any topic.

生成 AI 真人带货视频的完整前期制作流程。用户给出想带货的产品名称和产品图片（或只给名称），即可产出：①合适的主播（AI 模特人设 + 主播图），②分镜脚本与分镜图（痛点/使用/推荐/效果/产品空镜五类画面），③视频生成提示词（A-roll 口播 + B-roll 辅助镜头）。适用于"帮我做个带货视频/把这个产品拍成带货视频/生成带货视频的主播和分镜/给产品出视频提示词"等场景；产出是主播、分镜图与提示词，不含剪辑成片。