# vvv
Adopt this skill: https://proskills.md/skills/other/actionow-ai-vvv-skills-vvv
Page: https://proskills.md/skills/other/actionow-ai-vvv-skills-vvv
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.
## File: skills/vvv/SKILL.md
size: 8050
upstream: https://github.com/actionow-ai/vvv/blob/main/skills/vvv/SKILL.md
````text
---
name: vvv
description: Use when making, recreating or continuing an editable video from reusable templates (the current library covers wedding films), including recreating a reference video (a file or a 抖音/小红书/快手/TikTok share link) with the user's photos (local or 百度网盘), copy and music, or opening a .vvv package. Not for a standalone image or a generic website.
---
# vvv
Vibe Vision Video (VVV) builds a video template once and reuses it: for each new film, fill the template's inputs, change only the scenes the brief needs, and keep the editable project. The current template library focuses on wedding films. Every route ends the same way: render, measure with `vvv check`, look at it yourself, fix, deliver.
## The bar
A VVV film is worth watching when:
- **The first three seconds give a reason to stay:** faces, a shared memory, a question.
- **Something is always changing.** Nothing stands still longer than the template allows (usually 3 s); even a reading hold breathes.
- **Changes land on measured beats** of the actual track.
- **One thing to read at a time,** held long enough (about 5 s a page or more), broken where the author chose.
- **Each format is laid out for itself;** 9:16 is not a crop of 16:9.
- **The content is real and right:** the user's photos, correct names, confirmed dates and events.
- **The sound is intended:** music the user may use, at a sensible level, faded at the ends.
[Craft](references/craft.md) explains how to get there, including where each kind of move peaks against the beat.
## Pick the route
| The user has | Route | Start with |
|---|---|---|
| A purpose a template covers | **Template** | [Templates and projects](references/projects.md) |
| A reference video to match ("make it like this one"), as a file or a share link | **Recreation (复刻)** | [Recreation](references/recreation.md) |
| An idea, or no treatment yet | **Brainstorm** | [Brainstorm](references/brainstorm.md) |
| An existing VVV project or render | **Continue** | [Production and continuation](references/production.md) |
| A `.vvv` file (template, project or effect) | **Open the package** | [.vvv packages](references/vvv-format.md): `verify` first, then `init`, `unpack` or `add` |
## Set up without the user
The user only briefs, watches samples and gives feedback; environment and commands are your job. Before the first project command of a session, run `python3 scripts/vvv.py doctor` (add `--project DIR` once a project exists). It finds FFmpeg (Remotion's own when none is installed) and reuses a Chrome Headless Shell this computer already downloaded. Every failed check, and every failed helper command, carries `next`:
- `run`: run `command` yourself (in `cwd` when given), then retry what failed.
- `ask_user`: the fix needs the user's permission, account or material; ask `say` in one sentence, in the user's language.
- `fix`: work it out from the message and `hint`.
Never hand the user a command to type, a stack trace or an error code; the exception is a step only they can take on their own account (installing musicdl, saving a TikHub token, approving a login), which `next` words for you.
Routes combine: a brainstorm often lands on a template, and a recreation can become one. Ask the user only when the answer changes the film (audience, a missing fact, the format, the treatment); make routine choices yourself and say what you chose.
### Template
`--kit KIT` is optional: the helpers use `$VVV_KIT`, then the `kits/remotion` beside this skill (a clone or the Claude Code plugin).
1. `python3 scripts/vvv.py templates` lists each template with its description, formats and photo needs. Choose by purpose, then format (16:9 for a screen, 9:16 for a phone); ask if you don't know where it will play.
2. `python3 scripts/vvv.py describe --template ID [--format F]` prints one compact JSON: slots with hints, copy fields, props, music, which couple fields the template **shows** and where, and for templates with a page timeline the **seconds per page** at the default track. Tell the user up front what will not appear (an English name, the date) and whether pages will feel rushed.
3. Photos: local files or folders, or a 百度网盘 share link ([cloud storage](references/cloud-storage.md)). `init --photos ...` copies them downscaled to 2560 px (`--faces` adds face boxes when OpenCV is installed). `init --example` builds a demo from the template's own inputs. `--style NAME` applies a saved studio look.
4. Look at every photo and write `creative/photo-tags.json` (mood, subject, date, and `set` for the outfit); `arrange` places them so each page keeps one outfit and paired pages change outfit. Show the user `creative/arc-sheet.jpg`. Replace every line of demo copy and confirm names and dates.
5. Music: `music add --project P --file SONG` for the user's file, or the [music reference](references/music-and-sound.md) for a song they name. Then `music fit --project P` chooses where the song starts and the pace so the chorus opens the climax page; tell the user the length and the seconds per page, and `--apply` once agreed.
6. `doctor --project P` (applies `npm ci`, `npm run music`), `validate`, then sample the hardest range at `--scale 0.5`, `check` it and look at it. Fix the worst peaks `check` lists. Render the full film, `check` again, deliver. Offer `style save` when more films in this style will follow.
When the kit's template changes after a project was made, `update --project P` reports what would change; `--apply` takes the kit's version of files the project has not edited and lists edited ones as conflicts.
Helper errors are one JSON object, `{"status": "failed", "code", "message", "next"}`; follow `next`.
### Recreation
Get the reference (`scripts/vvv_video.py fetch` for share links), measure its rhythm, then **write the page inventory before any code**: every page's beats, photo boxes, how each element enters, how the page leaves, text and decoration. [scripts/vvv_ref.py](scripts/vvv_ref.py) makes the evidence: `sheet` (0.5 s overview, 0.1 s around every transition), `layout` (boxes of settled frames), `compare` (reference and rebuild side by side). Rebuild from the inventory: generate the visual elements (lettering, ornaments, line art, textures, frames) through an image route with reference crops as style references, and keep code for layout, motion and editable text. Compare frame by frame. Never ship the reference itself. Details: [recreation](references/recreation.md).
### Brainstorm
Pin down who watches, where, how long and the one takeaway. Offer three treatments that differ in structure, each with a beat sheet; recommend one and sample its hardest scene first.
## Check, look, deliver
```text
python3 scripts/vvv.py check --project PROJECT # latest sample or render
python3 scripts/vvv.py check --video FILE --beats MAP # any file, such as a reference
```
Fix failures first; `BEAT_SYNC` lists the worst peaks with their signed offsets, and [craft](references/craft.md#land-the-change-on-the-beat) says how far to move each kind of move. Passing is the floor, not approval. Then look, read and listen, following [Review and handoff](references/review-handoff.md), which also covers delivery (including uploading to 百度网盘 when asked). When the film goes to someone else, offer `pack --project` so their agent can continue it.
## Ground rules
- Facts about real people come from the user. Generated pictures of them stay identifiable as generated; never invent events to fill a gap.
- Use only music, clips and voices the user may use. Mixkit tracks are fetched by `npm run music` and never redistributed. A song fetched with musicdl is for that user's own film only and never enters a template or package.
- Never install musicdl or OpenCV, and never read or print tokens (TikHub, 百度网盘): `next` asks the user.
- Use image or video generation only through a route that is available and authorized in this session. A failed route never authorizes a paid fallb
````
## File: README.md
upstream: https://github.com/actionow-ai/vvv/blob/main/README.md
```text
换上照片和文案，就是一部新片；
给一部喜欢的片子，复刻出你自己的版本。
[](LICENSE)
[](https://vibevision.video/zh/)
[](https://linux.do)
[](docs/agent-compatibility.md)
[](docs/agent-compatibility.md)
[](https://vibevision.video/zh/start/#mcp)
[官网](https://vibevision.video/zh/) · [English](README.en.md) · [开始使用](docs/getting-started.md) · [模板](docs/templates.md) · [社区模板](https://vibevision.video/zh/community/) · [文档](docs/README.md)
> [!NOTE]
> **仅供学习与研究。** 本项目用于学习和研究可复用的视频模板、节拍剪辑与 Agent 工作流。示例中的新人和照片均为虚构。复刻参考视频是为了学习它的结构与节奏，请勿搬运或冒充他人作品；照片、音乐和字体请确认你有权使用。
## 用模板做出来的片子
Doodle · 白纸手绘 |
Album · 留白画册 |
DV Story · DV 回放 |
Comedy · 喜剧开场 |
Starter · 节拍相册 |
Album 9:16 · 竖版短片 |
Editorial · 简约杂志 |
Cinema · 黑幕影院 |
Memoir · 手写胶片故事 |
点击动图观看带配乐的完整预览。全部由模板直接渲染并通过 vvv check，新人和照片均为虚构示例。最新加入的 Editorial、Cinema 和 Memoir 都从参考片复刻：简约杂志风婚礼 MV、现场大屏黑底开场片、手写胶片人生故事。全部模板、画幅与风格
## 从一堆照片到一部成片
把照片和想法交给 Agent，从整理照片到渲染成片，每一步它都能接手。你只需要说想法、看样片、拍板。
| 准备照片 | 理清想法 | 样片与修改 | 成片与保存 |
01 说想法
告诉 Agent 想要的风格、画幅和歌曲，一两句话就够。 |
04 理需求
整理风格、画幅、时长和歌曲。点名的歌用你手里的音乐文件，或由你自装的 musicdl 获取（仅限个人使用）。 |
07 出样片
配乐自动对齐：副歌落在高潮页，渲染前先告诉你全片多长、每页停几秒。 |
10 出成片
渲染 1080p 高清成片，自动检查画幅、音量、静止画面和卡点。 |
02 放照片
照片放在本地文件夹，或给一个百度网盘分享链接。 |
05 看照片
逐张识别人物、情绪和服装，按套分组；同一页用同一套，相邻两组自动换装。 |
08 提意见
看完样片，直接说哪里要改。 |
11 存网盘
需要时把成片存进你的百度网盘，经你确认才上传。 |
03 取照片
Agent 下载原图，自动缩到渲染尺寸，原图不动。 |
06 定方案
三选一：推荐最合适的模板、用你指定的模板，或学习一部你喜欢的参考视频的结构和节奏，用自己的素材复刻（抖音、小红书、快手链接直接用）。 |
09 改到位
换照片、改文案、调节奏，逐条修改，只重渲改动的部分。 |
12 留工程
可编辑工程一并留存，以后随时能改，也能交给另一个 Agent 接着做。 |
> 用 vvv 技能做一部婚礼 MV：照片在百度网盘 https://pan.baidu.com/s/…（提取码 abcd），歌用《咱们结婚吧》，风格参考这条小红书 https://xhslink.cn/o/…。新郎林以舟、新娘许知夏，10 月 18 日结婚。先给我看样片。
## 装进你的 Agent
任选一种：
| Agent | 安装 |
|---|---|
| **Claude Code** | `/plugin install vvv --marketplace actionow-ai/vvv`（插件里已包含模板库） |
| **Codex、Cursor、Gemini CLI、Copilot 等 20 多个** | `npx skills add actionow-ai/vvv`（再 clone 本仓库，并设置 `VVV_KIT`，[说明](docs/agent-compatibility.md)） |
| **WorkBuddy** | 从 [Releases](https://github.com/actionow-ai/vvv/releases) 下载技能 ZIP，在「技能 → 添加技能」中上传（[说明](docs/workbuddy.md)） |
| **任何 MCP 客户端** | `claude mcp add --transport http vvv https://mcp.vibevision.video/mcp`，无需安装即可浏览模板和方法指南 |
渲染在你的电脑上进行，需要装好 Python 3.9+、Node.js 26 和 npm；其余依赖由 Agent 安装。可选（用你自己的账号）：下载分享链接参考片用的 [TikHub](https://tikhub.io) Token、百度网盘登录、musicdl（[集成说明](docs/integrations.md)）。
## 一个模板，做每一部新片
场景、版式、节奏和检查只做一次。新片只改属于它自己的东西。
| 只做一次 | 场景结构与镜头运动 · 16:9 与 9:16 版式 · 按节拍规划的时间线 · 渲染检查 |
| 每部片子各自修改 | 照片 · 名字和日期 · 每一句文案 · 配乐与画幅 |
`vvv.py describe` 告诉 Agent 每个模板的照片位、可改文案和配置，`validate` 在渲染前拦下错误输入。Agent 优先改模板开放的输入，只有需求需要时才动 React/TypeScript 源码。复用模板是为了省下反复设计、生成和调试同类视频代码的 token；对照基准尚未发布，见[路线图](ROADMAP.md)。
## 给它一部你喜欢的片子，做出你自己的。
把参考视频和属于你的附件交给 Agent：照片、Logo、文案、音乐。它会拆解参考片为什么好看，再用你的素材重建成一个可编辑的工程。
01 参考视频 + 附件
一个视频文件，或抖音、小红书、快手、TikTok 的分享链接，加上你的照片（本地或百度网盘）、Logo、文案和音乐。参考片只用来学习，不会被打包分发。 |
02 逐页清单
按节拍列出每一页：每个转场按 0.1 秒密集截帧，从定格帧量出照片框坐标，写清每个元素怎么进、怎么出。清单确认后才开始写代码。 |
03 重建并对照
基于最接近的模板或全新的构图。缺的素材以参考截图为风格参考生成；新旧画面并排对照，偏离节拍的峰值逐个列出。 |
> 用 vvv 技能把这条小红书视频 https://xhslink.cn/o/… 复刻成我们自己的片子：用 ./photos 里的照片、我们的 Logo 和文案重建，缺的画面素材用生图补上，正式渲染前先给我看检查过的样片。
有生图能力的 Agent 效果最好。本机同时装有 Claude Code 和 Codex 时，Claude Code 可以通过内置桥接调用 Codex 的生图能力。不生成视频和配音。[复刻流程](docs/capabilities.md#recreate-a-reference-video)
## 还能做什么
- **按情绪线排照片**：每个模板都标好了自己的情绪段落（先笑后泪、从相识到婚礼）。Agent 先看每张照片，标出人物、情绪和时间，再按段落放进对应位置，渲染前先给你看排好的顺序。
- **风格预设**：片头规则、配乐、署名这些定一次存成预设，之后每部片子都直接沿用，不用每次重新交代。
- **渲染检查**：`vvv check` 测量画幅、音量、静止画面和卡点，直接点出偏离节拍最多的几个画面，并列出只能由人判断的事项。
- **模板更新**：`vvv.py update` 把已有工程的模板代码更新到 kit 的最新版本，保留你自己改过的部分。
- **交接**：把模板、动效或做好的工程打包成一个 [`.vvv` 文件](docs/format/vvv-1.0.md)，带上代码、素材授权和渲染验证记录，换一个 Agent 也能接着做。
- **素材工具**：本地 FFmpeg 工具可以探测媒体、截取片段、提取音轨和抽帧（[示例](examples/media-workflow.md)）。
- **社区模板**：做了满意的模板，打包后在[官网投稿](https://vibevision.video/zh/submit/)。站长审核通过后，它会出现在网站和 MCP 服务里。
Agent 第一次在你的电脑上运行命令时，可能会先征求你的同意。想手动运行或开发新模板，见[开始使用](docs/getting-started.md)和[贡献指南](CONTRIBUTING.md)；现成的 `.vvv` 模板包附在 [Releases](https://github.com/actionow-ai/vvv/releases) 中。
### 今天就做出你的第一部片子。
[开始使用](docs/getting-started.md) · [官网](https://vibevision.video/zh/) · [contact@vibevision.video](mailto:contact@vibevision.video) · [Linux.do](https://linux.do)
状态
0.2 早期版本。已在 macOS ARM64 上用 Claude Code 和 Codex 完整验证，WorkBuddy 和其他平台测试较少。验证与限制 |
用途与许可
仅供学习与研究。代码、文档、模板与演示素材采用 MIT；字体、预览配乐和第三方代码沿用各自条款，其中 musicdl 仅限非商业使用：媒体许可 · 第三方说明 |
参与
|