Video & Animation

Turn explicit creator feedback on pacing, framing, titles, transitions, and audio into a reusable style note without overgeneralizing one-off corrections.

Measure and finish the mixed audio of a Reel, Short, long video, or audio-only deliverable with local FFmpeg and an encoded-output check.

Compare multiple frames from videos or photos across cameras, lighting, and output formats, then review a deliberate color adjustment.

Reframe a selected source range for wide YouTube, vertical Reels or Shorts, square, or portrait-feed delivery with fit or intentional crop.

Audit the picture and audio at edit boundaries in a rendered video, catching clipped speech, sudden sound changes, black frames, awkward dissolves, and visible jump cuts.

Generate narration locally in a consented speaker's voice using the bundled Chatterbox TTS model. Works with any language supported by the installed checkpoint. Audio finishing and soundtrack mixing are separate steps.

Review a finished video export for story coverage, readable text, framing, motion graphics, audio, and technical integrity before delivery.

Match narration or dialogue to indexed footage and audit a video timeline for off-topic shots using local, free tools. Use for footage searches and voiceover-to-picture alignment; do not treat filename similarity as visual proof.

「参考视频 → 新风格素材包」蒸馏工作流：把用户给的一支或多支参考视频逐镜头拆解（硬切、镜头表、关键帧、联系表、主色板与强调色、运动强度、动效切片、配乐卡点），提炼出配色、字体、版式、入场 / 转场 / 镜头运动、节奏和招牌画面这些「画面语法」，再在 weilanx-claude-videos 工程里从零写成一套可复用的 Remotion 风格素材包：src/library 下一个以风格 ID 命名的组件目录、一个 library- 开头的预览作品、styles/我的风格 下的风格配方卡，并登记进素材库目录和风格总表。用户说「蒸馏这个视频的风格」「把这几个视频的风格整理成一套素材」「一比一复刻这个视频的样式」「拆解这个视频的动效和画面」「照这个视频做一套新风格」，或者丢来参考视频（template/、Downloads 里的 mp4）想学它的样子时都用这个 skill；只想复刻单个动画片段、不需要进素材库的，也先用它做拆解。

动效导演 brief 方法论：需求 5 问澄清、分镜三段式、拍点网格、交付规格。写任何渲染代码之前先用它定方向。

动效导出与质检方法论：ffmpeg 导出参数、平台规格、成片自查流程。点"导出"之前先用它过一遍。

Inventory and classify footage, photos, audio, and factual evidence before a footage-based video edit; record required shots and source-backed labels in this repository.

多通道 AI 视频生成 + 配音合成引擎（fal.ai 队列：Wan 3.0 / Seedance 2.0+2.5 / MiniMax H3 / Gemini Omni Flash；TTS 用 ElevenLabs 英文 + 火山豆包中文；ffmpeg 合成）。当用户要求生成视频、文生视频、图生视频、视频编辑、配音、TTS、口播、短视频、BGM 混音，或提到 视频、视频配乐、视频号、抖音视频、短片、video clip、voiceover 时使用——即使没有说"生成"。需要 FAL_KEY（fal.ai）；可选 ELEVENLABS_API_KEY（英文配音）/ VOLC_TTS_API_KEY（中文配音，豆包 seed-tts V3）；REPLICATE_API_TOKEN 通道已脚手架化。零依赖，Node ≥ 18（合成与时长校验需要 ffmpeg/ffprobe）。模型路由、端点、参数枚举与定价集中在一个 JSON 注册表——加模型=改配置，不改代码。

Turn a vehicle on the Winn Kia of Fremont lot into three branded 10-second vertical reels (1080x1920) — "heartfelt" (warm family story), "sky-drop" (the car falls from the sky and lands), and "exploded" (the car bursts into floating parts and reassembles). Pulls the real listing photos from winnkiaoffremont.com, generates each clip with Higgsfield Seedance 2.5 using those photos as references, then adds the Winn logos, a hook, captions written for that car, a music bed and an end card with the dealership address. Use this whenever the user names a Kia model, stock number, VIN or Winn Kia listing URL and wants a reel, video, social content, "the three videos", or "do the same for this car" — and for follow-ups such as changing captions, re-running one style, or redoing a clip.

Biến nguyên liệu thô (link, file PDF/ảnh/slide, đoạn mô tả của người dùng) thành videos/NNN-slug/idea.md có cấu trúc cho kênh devdraw. Dùng khi người dùng dán link, đính kèm tài liệu hoặc kể một ý tưởng và muốn "lên idea", "làm video về cái này", "lưu ý tưởng này". Không dùng để viết script.json.

将人物演奏视频与单独录制的鼓声音频同步剪成架子鼓成片。适用于筛选正确录制版本、保留歌曲前奏、对齐落鼓动作与鼓声、删除准备或操作设备画面、检查漂移并轻度提亮。

动效音乐与音效方法论：BGM 三选一、拍点对齐、SFX 峰值对齐、响度 -14 LUFS。混音之前先用它定方案。

把真人口播竖屏短视频剪出「网感」——用 Remotion 做文字版式、换场画面、补停顿、配音效，并守住社媒安全区。用于：剪口播、口播精剪、抖音精剪（B-roll / 小人像窗 PIP / 分屏 / 海报大字）、抖音/Reels/Shorts 竖屏短视频、字幕太长或跑边、画面太平没网感、「用剪映那种花字/版式」、talking-head short video editing、Douyin-style 精剪 edit、B-roll、kinetic captions、safe zone。需要 1080×1920 的口播视频；有稿子更好。不用于：没有真人口播的品牌宣传片、多场景长片、纯素材混剪、静态标题卡。

纯代码渲染引擎方法论：seek(t) 确定性时间函数、静帧先行探针、子帧动态模糊、无头浏览器逐帧渲染。写渲染代码时用它。

Gets a finished video out on YouTube (Shorts or long), Instagram Reels and TikTok - picks the video, makes the light export for Instagram and TikTok, the cover, the caption and the YouTube title, sets the time, shows the plan, then after the creator's yes publishes through Treg on their own connected accounts (setup included), or hands a ready-to-post kit when Treg isn't set up. Use when the user says publish, post it, schedule, upload to YouTube, put it on Instagram, TikTok, publier, poster, programmer, mets-le en ligne.

给短视频做声音：配音用 HeyGen 复刻的自己的声音，也可以选 HeyGen 公共声音或 Gemini TTS，字幕时间按真实说话段落对齐；配乐和音效优先从 HeyGen 曲库/音效库找真实录音，曲风贴主题（产品介绍默认动感、有推进力），配乐压在人声下至少 12 dB，转场和关键帧都配音效；曲库找不到又要按小节精确编排时用 GarageBand 自带 Apple Loops 编曲，代码合成只做库里没有的短音效；测曲子的 BPM、拍点和高潮，让高潮砸在画面关键时刻并出卡点镜头时间表；最后压人声、统一响度到平台标准，交付前自检响度、峰值、音画等长和切点落拍。适用于竖版短视频、产品介绍、项目宣传片、讲解视频的配音、配乐、转场音效、卡点 BGM。当用户说"配音""用我的声音""Gemini 配音""换个声音""配乐""BGM""背景音乐""音效""转场音效""卡点""用库乐队/GarageBand""HeyGen 音乐""测一下 BPM""高潮对上画面""声音太小/抢人声"时使用。只负责声音，不负责画面。

>- Makes a product launch motion-graphics video in Remotion. Covers how to research a reference clip, how to build the story from what the product actually does, how to split a supplied logo into moving parts, and how to render real UI with the product's own components and CSS. Use when the user asks for a launch video, promo, motion graphics, Remotion video, ローンチ動画, or モーショングラフィック, including a localized second cut.

口播精剪官方套件（v1）：逐句留删决策树、人味配额与跳切遮盖。含"删什么/保什么"的阈值表、人味下限补偿、多片拆分、返修记忆点与失败处置，供口播精剪师执行。

口播点睛层官方套件（v1）：把逐字稿里的金句/数字/结论/步骤做成知识点弹幕、贴纸卡与章节条。含密度与安全区纪律、文案抽取口径、渲染交接与失败处置。