Video Editor logo

Video Editor

Community
minicoohei
video-editor

TikTok/YouTube向け動画編集スキル。ffmpegでキャプション焼き込み、 Ken Burnsエフェクト、シーン結合、音声合成を行う。 scenes.jsonから自動的に編集指示を読み取り最終動画を出力する。 Remotionコンポーネントも同梱(ローカル環境用)。 「動画編集」「キャプション追加」「テロップ付き動画」等で発動。

Overview

Publisherminicoohei
Repositoryai-agent-camp
Skill namevideo-editor
Stars
346
Forks
13
Bundled files
5
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by minicoohei on GitHub. Read the source before you install it.

Installation

Install the Video Editor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/minicoohei/ai-agent-camp/tree/main/.claude/skills/video-editor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/minicoohei/ai-agent-camp.git /tmp/ai-agent-camp
mkdir -p .claude/skills
cp -r /tmp/ai-agent-camp/.claude/skills/video-editor .claude/skills/video-editor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Video Editor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Video Editor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Video Editor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Video Editor

scenes.json + フレーム画像/動画クリップから最終動画を生成する。

2つの実行モード

🟢 ffmpegモード(サンドボックス対応・推奨)

Chromium不要。サンドボックスでも動作する。

bash
python skills/video-editor/scripts/compose_video.py \
  --storyboard-dir output/storyboard/YYYYMMDD_session \
  --captions \
  --output output/final_tiktok.mp4

🔵 Remotionモード(ローカル環境用)

Chromium + Node.js必要。より高度なアニメーション。

bash
npx remotion render TikTokVideo --output=out/tiktok_video.mp4 --root=remotion-editor/src/Root.tsx

ffmpegパイプライン

1. 素材準備

scenes.json → 各フレームのmotion_type確認
  i2v        → video/{frame}_i2v.mp4 を使用
  ken_burns  → ffmpeg zoompan フィルターで画像→動画
  static     → ffmpeg loop で画像→動画
  motion_graphics → ffmpeg で画像→動画(将来テキストアニメ追加)

2. 正規化

全クリップを統一仕様に:

  • 解像度: 1080×1920 (9:16) or 1920×1080 (16:9)
  • FPS: 30
  • コーデック: h264 / yuv420p
  • 横向きi2V動画 → ぼかし背景付き縦型に変換

3. キャプション焼き込み(drawtext)

bash
ffmpeg -i clip.mp4 -vf "drawtext=text='テキスト':fontfile=/path/to/NotoSansJP-Bold.otf:\
  fontsize=64:fontcolor=white:borderw=3:bordercolor=black:\
  x=(w-text_w)/2:y=h*0.58" output.mp4

キャプション仕様:

項目TikTok推奨
フォントサイズ54-76px (画面幅の5-7%)
文字数/行日本語5-8文字 / 英語2-3語
最大行数2行
フォントNoto Sans JP Bold
色白 + 黒ストローク(3px) + シャドウ
位置Y: 55-65% (TikTokセーフゾーン内)

4. 結合

bash
ffmpeg -f concat -safe 0 -i concat.txt -c:v libx264 -pix_fmt yuv420p final.mp4

5. 音声合成(オプション)

bash
ffmpeg -i video.mp4 -i narration.mp3 -c:v copy -c:a aac -shortest final_with_audio.mp4

TikTokセーフゾーン

┌─────────────────────┐
│  ⚠️ 上15% 避ける     │ ← ユーザー名/フォローボタン
├─────────────────────┤
│   メインコンテンツ    │
│  ┌───────────────┐  │
│  │ キャプション    │  │ ← Y: 55-65%
│  └───────────────┘  │
├─────────────────────┤
│  ⚠️ 下20% 避ける     │ ← いいね/コメント/シェア
└─────────────────────┘

scenes.json フォーマット

json
{
  "title": "動画タイトル",
  "scenes": [
    {
      "frame_number": 1,
      "timestamp": "0:00-0:02",
      "motion_type": "i2v | ken_burns | static | motion_graphics",
      "narration": "ナレーション台本",
      "text_overlay": {
        "main_text": "メインテロップ",
        "sub_text": "サブテロップ",
        "position": "top | center | bottom",
        "style": "bold | subtitle | minimal"
      }
    }
  ]
}

依存

  • ffmpeg (静的バイナリ: .bin/ffmpeg)
  • Python 3.11+ (compose_video.py)
  • Noto Sans JP フォント(キャプション用)

Remotionコンポーネント(ローカル用)

remotion-editor/src/
  components/
    Caption.tsx    # TikTok最適キャプション(日本語改行、pop-inアニメ)
    KenBurns.tsx   # Ken Burns zoom/pan エフェクト
  compositions/
    TikTokVideo.tsx # 9:16 メインコンポジション
  Root.tsx         # エントリポイント

関連スキル

  • storyboard-generator — 入力素材(frames + scenes.json)
  • content-creator — コンテンツ企画
  • post-publisher — 投稿・配信

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Video Editor AI skill do?

TikTok/YouTube向け動画編集スキル。ffmpegでキャプション焼き込み、 Ken Burnsエフェクト、シーン結合、音声合成を行う。 scenes.jsonから自動的に編集指示を読み取り最終動画を出力する。 Remotionコンポーネントも同梱(ローカル環境用)。 「動画編集」「キャプション追加」「テロップ付き動画」等で発動。

Why use Video Editor on TypingMind?

Because you install it once and use it with any model. Video Editor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Video Editor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/minicoohei/ai-agent-camp/tree/main/.claude/skills/video-editor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Video Editor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Video Editor?

As many as you like. As long as a model supports skills, you can use Video Editor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Video Editor AI skill free?

It is published on GitHub by minicoohei. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇