video-processing
关于
This skill automates video processing tasks using FFmpeg, enabling developers to compress, resize, clip, and merge videos or extract audio through Claude. It's ideal for preparing content for social media, optimizing uploads, and batch processing. The tool handles the FFmpeg operations while you specify the parameters and use cases.
快速安装
Claude Code
推荐npx skills add guia-matthieu/clawfu-skills -a claude-code/plugin add https://github.com/guia-matthieu/clawfu-skillsgit clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/video-processing在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Video Processing
Automate repetitive video editing tasks using FFmpeg - the industry-standard tool powering YouTube, Netflix, and most video platforms.
When to Use This Skill
- Social media optimization - Resize videos for Instagram (9:16), TikTok, LinkedIn
- Upload preparation - Compress large videos to meet platform limits
- Audio extraction - Pull audio from webinars, interviews for podcasts
- Content clipping - Extract highlights, quotes, or segments
- Batch processing - Apply same operations to multiple videos
What Claude Does vs What You Decide
| Claude Does | You Decide |
|---|---|
| Structures production workflow | Final creative direction |
| Suggests technical approaches | Equipment and tool choices |
| Creates templates and checklists | Quality standards |
| Identifies best practices | Brand/voice decisions |
| Generates script outlines | Final script approval |
Dependencies
pip install ffmpeg-python moviepy click
# Also requires ffmpeg installed on system
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg
Commands
Compress Video
python scripts/main.py compress video.mp4 --target-mb 10
python scripts/main.py compress video.mp4 --crf 28 --output compressed.mp4
Extract Audio
python scripts/main.py extract-audio video.mp4 --format mp3
python scripts/main.py extract-audio video.mp4 --format wav --output audio.wav
Resize for Social
python scripts/main.py resize video.mp4 --format instagram # 1080x1920 (9:16)
python scripts/main.py resize video.mp4 --format youtube # 1920x1080 (16:9)
python scripts/main.py resize video.mp4 --format square # 1080x1080 (1:1)
python scripts/main.py resize video.mp4 --width 1280 --height 720
Clip Segment
python scripts/main.py clip video.mp4 --start 00:30 --end 01:45
python scripts/main.py clip video.mp4 --start 00:30 --duration 60
Merge Videos
python scripts/main.py concat video1.mp4 video2.mp4 --output merged.mp4
python scripts/main.py concat ./clips/ --output compilation.mp4
Generate Thumbnail
python scripts/main.py thumbnail video.mp4 --time 00:30
python scripts/main.py thumbnail video.mp4 --best # Auto-select best frame
Examples
Example 1: Prepare Video for Instagram Reels
# Original: 4K horizontal video, 500MB
python scripts/main.py resize long-video.mp4 --format instagram
python scripts/main.py compress long-video_instagram.mp4 --target-mb 50
# Output: long-video_instagram_compressed.mp4 (1080x1920, <50MB)
Example 2: Extract Podcast from Webinar
# Extract audio track
python scripts/main.py extract-audio webinar-recording.mp4 --format mp3 --bitrate 192k
# Output: webinar-recording.mp3 (ready for podcast hosting)
Example 3: Create Highlight Reel
# Extract multiple clips
python scripts/main.py clip interview.mp4 --start 05:30 --end 06:15 --output clip1.mp4
python scripts/main.py clip interview.mp4 --start 12:00 --end 12:45 --output clip2.mp4
python scripts/main.py clip interview.mp4 --start 28:30 --end 29:00 --output clip3.mp4
# Merge into highlight reel
python scripts/main.py concat clip1.mp4 clip2.mp4 clip3.mp4 --output highlights.mp4
Social Media Format Reference
| Platform | Format | Resolution | Max Size | Max Duration |
|---|---|---|---|---|
| Instagram Reels | 9:16 | 1080x1920 | 4GB | 90s |
| Instagram Feed | 1:1 | 1080x1080 | 4GB | 60s |
| TikTok | 9:16 | 1080x1920 | 287MB | 10min |
| YouTube Shorts | 9:16 | 1080x1920 | - | 60s |
| YouTube | 16:9 | 1920x1080 | 256GB | 12h |
| 1:1/16:9 | 1920x1080 | 5GB | 10min | |
| Twitter/X | 16:9 | 1920x1080 | 512MB | 2:20 |
Performance Tips
- GPU acceleration - FFmpeg uses hardware encoding when available (NVENC, VideoToolbox)
- CRF values - Lower = better quality, larger file. 18-28 typical range
- Preset selection -
ultrafastfor drafts,slowfor final exports - Two-pass encoding - Better quality for target bitrate
Skill Boundaries
What This Skill Does Well
- Structuring audio production workflows
- Providing technical guidance
- Creating quality checklists
- Suggesting creative approaches
What This Skill Cannot Do
- Replace audio engineering expertise
- Make subjective creative decisions
- Access or edit audio files directly
- Guarantee commercial success
Related Skills
- whisper-transcription - Transcribe video audio
- youtube-downloader - Download videos to process
- image-batch - Process video thumbnails
Skill Metadata
- Mode: cyborg
category: automation
subcategory: video-processing
dependencies: [ffmpeg-python, moviepy]
difficulty: beginner
time_saved: 5+ hours/week
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
polymarket
元这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
creating-opencode-plugins
元该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
