/ 디렉터리 / 플레이그라운드 / claude-shorts
● 커뮤니티 AgriciDaniel ⚡ 바로 사용

claude-shorts

제작: AgriciDaniel · AgriciDaniel/claude-shorts

Turn a long podcast or stream into ready-to-post Shorts — Claude picks the highlights, Remotion animates the captions.

claude-shorts is a longform-to-shortform video pipeline packaged as a Claude Code skill: transcript-driven segment scoring picks candidate clips, audio-aware boundary snapping cleans them up, a Remotion project renders animated captions and cursor overlays, and Claude wires it all together. Output: vertical Shorts you can post without opening a video editor.

왜 쓰나요

핵심 기능

라이브 데모

실제 사용 모습

claude-shorts-skill.replay ▶ 준비됨
0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "claude-shorts-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AgriciDaniel/claude-shorts",
        "~/.claude/skills/claude-shorts"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "claude-shorts-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AgriciDaniel/claude-shorts",
        "~/.claude/skills/claude-shorts"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "claude-shorts-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AgriciDaniel/claude-shorts",
        "~/.claude/skills/claude-shorts"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "claude-shorts-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AgriciDaniel/claude-shorts",
        "~/.claude/skills/claude-shorts"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "claude-shorts-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AgriciDaniel/claude-shorts",
        "~/.claude/skills/claude-shorts"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json
{
  "context_servers": {
    "claude-shorts-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/AgriciDaniel/claude-shorts",
          "~/.claude/skills/claude-shorts"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add claude-shorts-skill -- git clone https://github.com/AgriciDaniel/claude-shorts ~/.claude/skills/claude-shorts

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: claude-shorts

How to turn a 90-minute podcast into 10 Shorts

👤 Podcasters and content creators ⏱ ~90 min advanced

언제 쓸까: You published a long episode and want a week of Shorts from it with minimal effort.

사전 조건
  • Node 20+ for Remotion and FFmpeg installed — nvm install 20; brew install ffmpeg
  • Skill cloned — git clone https://github.com/AgriciDaniel/claude-shorts ~/.claude/skills/claude-shorts
흐름
  1. Transcribe and score
    Process podcast_ep42.mp3 — transcribe and score candidate Short segments.✓ 복사됨
    → Ranked list of 20–30 candidates with timestamps and hooks
  2. Pick and snap
    Pick the top 10 and snap boundaries to clean audio breakpoints.✓ 복사됨
    → 10 segments with cleaned-up start/end
  3. Render Shorts
    Render vertical 9:16 Shorts with animated captions to ./shorts/.✓ 복사됨
    → MP4 files ready to upload

결과: A week's worth of Shorts generated in an afternoon.

함정
  • Captions out of sync — Use word-level timestamps from whisper — skill expects them
  • Same joke across 3 Shorts — Ask Claude to de-dupe by topic cluster before rendering
함께 쓰기: filesystem

Build a highlight reel from a Twitch / YouTube stream

👤 Streamers, educators, conference archivists ⏱ ~60 min intermediate

언제 쓸까: You have a long recording and need a sampler to promote it.

흐름
  1. Score peaks
    Find the 15 most engaging moments based on transcript + audio energy.✓ 복사됨
    → Ranked peaks with timestamps and reasons
  2. Assemble the reel
    Assemble a single 60-second highlight reel with smooth cuts.✓ 복사됨
    → One MP4 with good pacing

결과: A concise reel that represents the best of the session.

함정
  • Reel has no narrative — Ask Claude to order clips for arc, not just score
함께 쓰기: claude-youtube-skill

조합

다른 MCP와 조합해 10배 효율

claude-shorts-skill + claude-youtube-skill

Same pipeline feeds YouTube long-form + Shorts strategy

Pick 10 Shorts from the latest podcast and suggest YouTube Shorts titles and descriptions.✓ 복사됨

Auto-caption each Short for IG/TikTok/Threads

For each rendered Short, generate posting captions for Instagram Reels and TikTok.✓ 복사됨

도구

이 MCP가 노출하는 것

도구입력언제 호출비용
transcribe-and-score audio/video path First step in any pipeline Whisper / scoring compute
boundary-snap segment timestamps + waveform After scoring audio analysis compute
remotion-render segments + captions + style Final step Remotion render time
cursor-overlay screen-capture + cursor events For tutorials or software walkthroughs 0

비용 및 제한

운영 비용

API 쿼터
none beyond whisper/LLM provider
호출당 토큰
~10–30k tokens per long-form source
금액
free at the skill level; rendering uses your CPU/GPU
Score in one pass, then batch-render overnight to avoid UI blocking

보안

권한, 시크릿, 파급범위

자격 증명 저장: none
데이터 외부 송신: none — local rendering

문제 해결

자주 발생하는 오류와 해결

Remotion render fails

Check Node version (20+), ensure the Remotion project compiles: npx remotion render.

확인: npx remotion --version
FFmpeg: codec not found

Install a full FFmpeg build: brew install ffmpeg; confirm libx264.

확인: ffmpeg -codecs | grep 264
Captions off by ~200ms

Re-run transcription with word timestamps enabled.

대안

claude-shorts 다른 것과 비교

대안언제 쓰나단점/장점
claude-youtube-skillYou need YouTube strategy, not automated renderingStrategy vs pipeline

더 보기

리소스

📖 GitHub에서 공식 README 읽기

🐙 열린 이슈 보기

🔍 400+ MCP 서버 및 Skills 전체 보기