Video & Animation

从主题或文稿制作中文讲解视频：联网核实并确认文案、声音形式与视觉风格，再用代码制作配乐字幕版或真人演说 API 配音版。适用于资讯、产品与技术讲解；不用于 AI 生成视频镜头。

旁白、视频切片与文字动画混搭的成片：拿一条新闻、一件事、一段八卦、一个产品或人物的故事，从网上与用户的视频库里搜素材、切当事人的原声，配旁白剪成一条画面一直在动的片子，推文、引语、日期、数字做成压在画面上的卡片。题材不限；别的成片里要加一段这样的切片也用它。整段画面由代码画出来的讲解片走 explainer-video，剪已有的口播走 talking-head-cut。

Make a short, verified math / computer-vision / ML explainer video (computed animation + captions, optional translated version, narration script and TTS voice-over) with the animkit library in this repo. Use when the user asks for an explainer video, an animation of a concept / paper / mechanism, a storyboard for one, or a review / revision round of one.

Turn academic papers into learning videos by first producing a Chinese academic-style summary, then narration, visual planning, storyboards, and video review. Render videos when suitable tools are available. Use for paper-to-video learning summaries.

用故事板规划并制作 HyperFrames 视频。适用于识别共享主体、选择连续形变方案、按依赖并行制作镜头、验收关键帧、拼接总时间线，以及处理镜头连续性问题。

>- Generate, export, or convert finished videos (or code-rendered videos) into native, self-contained JianYing Pro (剪映 / CapCut) project drafts, and automatically launch JianYing to open the project immediately with zero missing-media prompts. Use when the user wants to export a video, script, or timeline to JianYing, create a JianYing project from a video, or automate draft generation.

>- Write and lint the title and thumbnail for a YouTube video as one pairing, checking truncation, duplication and vagueness before publish. Use for "title ideas", "what should I call this", "thumbnail text", "my CTR is bad", packaging, or any request to rename or repackage an existing video.

>- Turn a raw recording's transcript into an edit decision list - dead air, filler cues and retakes, with timecodes. Use for "edit this", "cut the dead space", "tighten this video", "I rambled", or any request to shorten footage from a transcript.

>- Write YouTube chapters from a transcript, validated against YouTube's own rules so they actually render. Use for "add chapters", "timestamps", "break this video into sections".

>- Audit a YouTube channel end to end - packaging, consistency, the first fifteen seconds, and what to fix first. Use for "audit my channel", "why isn't my channel growing", "review my videos", or a pasted channel URL.

End-to-end pipeline for editing Hinglish talking-head reels and product-ad reels (1080x1920, Instagram/Shorts) in the ~/video-editing studio — retake removal, tightened pauses, Roman karaoke captions, word-synced motion graphics, layered SFX, music bed, premium grade, -14 LUFS export. Use when the user gives talking-head/speech footage (your channel or any client), says "edit this reel", "new project from inbox", "make a product ad", or asks to re-render/tweak a version of an existing speech reel.

Turn slides, a PDF deck, course notes or a webinar outline into a long-form narrated training/course video (10–60 min, 16:9) — script per slide, ElevenLabs narration with word timings (Prem / Indian-English voices), each slide built up part-by-part on spoken cues with an easing camera, push transitions, progress bar and chapter markers, ducked music bed, light SFX, YouTube chapters and lesson splits. Use when the user says "make a course video", "training video from this PDF/deck", "narrate these slides", "lesson/module video", or gives a deck and wants a long educational video ("normal editing, not heavy motion graphics").

Produce many performance-ad creatives from one shoot or edit for Meta (Facebook/Instagram) and YouTube ads — modular hooks × bodies × CTAs matrix, 9:16 / 4:5 / 1:1 / 16:9 versions with platform safe zones, UGC/talking-head and product-demo styles, burned captions for sound-off, offer/price supers, consistent naming for testing, and a creative test plan. Use when the user says "ad variants", "make 5/10 ad creatives", "hook variations", "test different hooks", "Meta ad creatives from this video", "resize this ad for all placements", or works on paid campaigns for clients.

Use when producing a continuous score-synchronized video and matching covers from MusicXML/MXL, an original score PDF, and a real recording. Also use for alignment corrections, preview review, paused render recovery, or cover revisions within this workflow.

用于把用户指定的视频链接或本地音视频整理成带来源、时间点和关键画面的学习笔记，也可按需提炼工作流。需要依据字幕、完整转录及必要画面核对内容；不凭标题、简介或片段生成全片总结。

Edit raw camera footage into a cinematic, beat-synced vertical reel (Instagram Reels / YouTube Shorts) using FFmpeg — e.g. car delivery, event, product or travel reels. Use when the user asks for a cinematic reel, car delivery reel, beat-sync edit or B-roll montage from their clips.

Build music-only cinematic reels (no speech) from phone clips and photos, cut on the song's beat grid with true slow-mo, bloom/vignette/grain grade, flash+boom on the drop, shutter SFX on photos and bold title cards — e.g. car delivery, wedding, travel, celebration, unboxing reels in ~/video-editing. Use when the user supplies a song plus clips/photos and wants a "cinematic reel", "beat-synced edit", or "delivery/celebration video".

Optional first-run setup for Reelsmith: introduces what it can make, builds the brand kit, notes music and voice preferences, suggests optional keys, and installs the engines and free voice in the background.

Use when the user asks for a video - sizzle reel, promo, launch or teaser, event recap, testimonial, data/stat story, how-to or tutorial, animated slides or kiosk loop, narrated explainer, social clip (Reels, Shorts, TikTok, LinkedIn, X), captions, overlay or GIF. Writes the script, plans and gets approval, builds from parameterized templates with a brand kit, real or synth music on a beat grid, free stock and local voice, captions and platform presets, runs a review gate, then renders 16:9, 9:16 and 1:1 on your own computer. Paid AI is optional and quoted first.

Build and render a film, reel or animation as code. One HTML page draws any frame on demand with window.seek(t), and a headless browser renders every frame at 2x into an MP4 with sound. Use it whenever someone wants a video made with code rather than a video generator, says "make a film / reel / animated explainer / career video", "render this to MP4", "turn this page into a video", or needs the finishing steps (audio cues, loudness, colour-safe encode, phone preview). It is style-agnostic and renders 9:16, 4:5, 1:1 or 16:9. It runs after reel-intake (the brief) and reel-style (the look), builds on template/starter.html or a style pack such as voxel-walk, and passes film-audit before anything is shown to anyone.

The interview before any video is built. It reads what the person already gave (source text, CV, links, brand files), then asks the rest in a few short rounds of numbered questions with a recommended answer marked, always including the format (platform, reel or video, ratio, layout, length, sound). It ends in a one-screen brief that splits "you said" from "I assumed", plus a storyboard, and builds nothing until the person says yes. Use it whenever someone asks for a reel, a video, an explainer, a career film, an animation or a "make a video about X", before film-engine or any style pack, and again when a request changes its purpose, platform or audience mid-way.

An orbiting camera follows an ice logo as it breaks apart, reforms into two text moments, and fades. HyperFrames block, 1920×1080, 22.5s, 216 variables.

Glass shards fly in through fog and tile themselves into the headline. HyperFrames block, 1920×1080, 12.16s, 19 variables.

A chain of bevelled cuboids rides a travelling wave as a content carousel. HyperFrames block, 1920×1080, 6.666666666666667s, 40 variables.