跳到正文
TakoAPI
返回技能列表

clips-machine

由 mayank8290 提供

Coding Agents & IDEs
1.6k下载量由 clawskills.sh 提供
6星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Transform long videos into viral short-form clips.

描述

该技能的功能

Clips Machine takes long videos from YouTube, local files, TikTok, Twitter/X, or Twitch and cuts them into short vertical clips ready for TikTok, Reels, or Shorts. It transcribes audio locally with Whisper, scores each moment by virality criteria, and exports captioned 9:16 clips with multiple text style options.

Runs entirely on local tools with no cloud service, so there are no per-clip fees, upload limits, or API keys required.

何时使用

  • Clipping the top 5 moments from a 2-hour podcast
  • Turning a Twitch gaming VOD into meme-captioned TikToks
  • Extracting quotable segments from a conference keynote on YouTube
  • Processing a local interview MP4 into Reels-ready highlights
  • Batch-generating 10 short clips from a long YouTube interview for a client

示例工作流

输入

User asks: Take this podcast and find the 10 best moments: https://youtube.com/watch?v=PODCAST_ID — make them Hormozi-style with bold captions

智能体
  1. 1

    Downloads the video using yt-dlp

  2. 2

    Transcribes the audio locally with Whisper.cpp to produce a timestamped transcript

  3. 3

    Analyzes the transcript and scores moments by virality criteria (hooks, emotional peaks, quotable lines)

  4. 4

    Cuts the top 10 segments using FFmpeg and crops to 9:16 vertical format

  5. 5

    Renders animated Hormozi-style captions onto each clip and saves them to ~/Videos/OpenClaw/

输出

10 captioned vertical MP4 clips with a summary.md listing each clip's virality score and timestamp

前置要求

  • ffmpeg (brew install ffmpeg or apt install ffmpeg)
  • yt-dlp (brew install yt-dlp or pip install yt-dlp)
  • whisper-cpp (brew install whisper-cpp or built from source)

安装

clawhub install mayank8290/clips-machine

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接