video-studio

Use when the user asks to create or edit videos end-to-end (script→video, auto-cut/jumpcut, captions/subtitles, polishing for Shorts/Reels/TikTok). Current implemented backend: local FFmpeg (probe/render/jumpcut/burn-subtitles/polish). Planned/optional backends: Remotion (motion graphics templates), VectCutAPI (CapCut/剪映 timeline editing), and video-audio-mcp (MCP tool wrapper) when available. Produces a finished video artifact (MP4 by default) from assets + copy + a design/storyboard plan.

Best use case

video-studio is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use when the user asks to create or edit videos end-to-end (script→video, auto-cut/jumpcut, captions/subtitles, polishing for Shorts/Reels/TikTok). Current implemented backend: local FFmpeg (probe/render/jumpcut/burn-subtitles/polish). Planned/optional backends: Remotion (motion graphics templates), VectCutAPI (CapCut/剪映 timeline editing), and video-audio-mcp (MCP tool wrapper) when available. Produces a finished video artifact (MP4 by default) from assets + copy + a design/storyboard plan.

Teams using video-studio should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/video-studio/SKILL.md --create-dirs "https://raw.githubusercontent.com/foryourhealth111-pixel/Vibe-Skills/main/bundled/skills/video-studio/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/video-studio/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How video-studio Compares

Feature / Agentvideo-studioStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use when the user asks to create or edit videos end-to-end (script→video, auto-cut/jumpcut, captions/subtitles, polishing for Shorts/Reels/TikTok). Current implemented backend: local FFmpeg (probe/render/jumpcut/burn-subtitles/polish). Planned/optional backends: Remotion (motion graphics templates), VectCutAPI (CapCut/剪映 timeline editing), and video-audio-mcp (MCP tool wrapper) when available. Produces a finished video artifact (MP4 by default) from assets + copy + a design/storyboard plan.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Video Studio (自动视频制作 / 剪辑 / 打磨)

目标:把「素材(视频/音频/图片)+ 文案 + 编排/设计方案」自动变成可发布的成片,并在最后做一轮“打磨”(节奏、转场、字幕、音量、编码)。

## 何时使用
- 你要“从 0 生成一个视频”(口播/科普/产品介绍/短视频)
- 你要“自动剪辑已有视频/音频”(去静音、裁切、拼接、转场、加字幕、加 Logo/BGM)
- 你要“适配平台规格”(9:16 / 1:1 / 16:9、码率、分辨率、时长上限)
- 你要“自动抛光”(音量标准化、fade in/out、H.264/yuv420p、帧率、字幕烧录)

## 背后能力(融合方案)
本 skill 不绑定单一引擎,而是按可用性选择 backend:

1. **FFmpeg(基线后端,必备)**
   - 本地快速剪辑、拼接、字幕烧录、音频混音、编码打磨
2. **Remotion(可选,做“像设计稿一样”的动效视频)**
   - 程序化动效、模板化片头片尾、动态字幕/图表
3. **VectCutAPI(可选,高阶时间线后端)**
   - 如果你有剪映/CapCut + VectCutAPI 服务,可用 API/MCP 进行更复杂的轨道/特效/关键帧
4. **video-audio-mcp(可选,MCP 封装的 FFmpeg 工具箱)**
   - 如果已配置该 MCP server,可把常用 FFmpeg 操作当成工具调用(trim/concat/subtitles/overlays/remove_silence)

## 先跑一次环境探测(强烈推荐)
在当前项目目录里执行:

```powershell
python C:\Users\羽裳\.codex\skills\video-studio\scripts\video_studio.py probe
```

它会输出 JSON,说明:
- `ffmpeg/ffprobe` 是否可用(没有则给出安装建议)
- `node/npm/npx` 是否可用(Remotion 需要)
- `vectcut_base_url` 是否可连(可选)

## 产物约定(建议)
- 中间文件:`outputs/video-studio/tmp/`
- 最终成片:`outputs/video-studio/final/`

你可以把素材放在:
- `assets/video/` `assets/audio/` `assets/images/` `assets/fonts/`

## 最小闭环:用 spec 直接生成视频(FFmpeg backend)
1) 写一个 spec(可参考本 skill 的 `references/sample_spec.json`)

2) 运行:

```powershell
python C:\Users\羽裳\.codex\skills\video-studio\scripts\video_studio.py render --spec C:\path\to\spec.json
```

## “打磨”步骤(推荐作为最后一步)
```powershell
python C:\Users\羽裳\.codex\skills\video-studio\scripts\video_studio.py polish --in .\outputs\video-studio\final\video.mp4 --out .\outputs\video-studio\final\video.polished.mp4
```

打磨会尽量做到:
- H.264 + yuv420p(平台兼容)
- 统一帧率/分辨率
- 音量标准化(EBU R128 loudnorm)
- 可选 fade in/out

## 自动剪辑:JumpCut(去静音/去停顿)
适合“口播/访谈/课程录屏”这类有明显停顿的视频:自动检测静音区间并拼接,提高节奏流畅度。

```powershell
python C:\Users\羽裳\.codex\skills\video-studio\scripts\video_studio.py jumpcut --in .\assets\video\talking.mp4 --out .\outputs\video-studio\final\talking.jumpcut.mp4
```

常用参数:
- `--silence-threshold-db`:静音阈值(例如 `-35`)
- `--min-silence`:最短静音时长(例如 `0.4`)
- `--pad`:保留在静音边界的 padding(避免“咬字被切掉”)

## 字幕烧录(SRT → MP4)
如果你已经有 `captions.srt`(来自转录或人工),可直接烧录:

```powershell
python C:\Users\羽裳\.codex\skills\video-studio\scripts\video_studio.py burn-subtitles --in .\outputs\video-studio\final\video.mp4 --srt .\assets\captions.srt --out .\outputs\video-studio\final\video.subbed.mp4
```

## 需要 AI 生成素材时(可选)
这个 skill **优先复用既有 skill**,避免重复造轮子:
- 图片/背景:`$imagegen`(需要 `OPENAI_API_KEY`)
- 配音:`$speech`(需要 `OPENAI_API_KEY`)
- 转录:`$transcribe`(需要 `OPENAI_API_KEY`)

典型全自动流程:
1) 文案 → 生成配音(speech)
2) 配音 → 生成字幕(transcribe 或手工脚本)
3) 文案/分镜 → 生成背景图(imagegen)
4) 用本 skill 的 `render/polish` 合成出片

## 质量门禁(交付前自检)
- 成片可播放(本地播放器 + 秒开)
- 分辨率/帧率符合平台(例如 1080x1920@30fps)
- 音量不过爆、不太小(主讲语音清晰,BGM 不盖人声)
- 字幕不超出安全区(手机端不被 UI 遮挡)

## 边界
- 本 skill 会生成/编辑视频文件,但不会替你发布到平台。
- 高级“像剪映一样”的轨道编辑:优先走 VectCutAPI(如果你有服务),否则用 FFmpeg 的能力做到“够用的自动剪辑”。

Related Skills

zinc-database

1174
from foryourhealth111-pixel/Vibe-Skills

Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.

zarr-python

1174
from foryourhealth111-pixel/Vibe-Skills

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

yeet

1174
from foryourhealth111-pixel/Vibe-Skills

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

xlsx

1174
from foryourhealth111-pixel/Vibe-Skills

Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis.

xan

1174
from foryourhealth111-pixel/Vibe-Skills

High-performance CSV processing with xan CLI for large tabular datasets, streaming transformations, and low-memory pipelines.

writing-plans

1174
from foryourhealth111-pixel/Vibe-Skills

Use when you have a spec or requirements for a multi-step task, before touching code

writing-docs

1174
from foryourhealth111-pixel/Vibe-Skills

Guides for writing and editing Remotion documentation. Use when adding docs pages, editing MDX files in packages/docs, or writing documentation content.

windows-hook-debugging

1174
from foryourhealth111-pixel/Vibe-Skills

Windows环境下Claude Code插件Hook执行错误的诊断与修复。当遇到hook error、cannot execute binary file、.sh regex误匹配、WSL/Git Bash冲突时使用。

weights-and-biases

1174
from foryourhealth111-pixel/Vibe-Skills

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

webthinker-deep-research

1174
from foryourhealth111-pixel/Vibe-Skills

Deep web research for VCO: multi-hop search+browse+extract with an auditable action trace and a structured report (WebThinker-style).

vscode-release-notes-writer

1174
from foryourhealth111-pixel/Vibe-Skills

Guidelines for writing and reviewing Insiders and Stable release notes for Visual Studio Code.

visualization-best-practices

1174
from foryourhealth111-pixel/Vibe-Skills

Visualization Best Practices - Auto-activating skill for Data Analytics. Triggers on: visualization best practices, visualization best practices Part of the Data Analytics skill category.