c-video
关于
The c-video skill enables Claude to download videos and process media using `yt-dlp` and `ffmpeg`. It can download from hundreds of sites, extract audio tracks, convert between formats, and clip video segments. Use this skill for automating video/audio downloading, extraction, and conversion tasks directly within Claude.
快速安装
Claude Code
推荐npx skills add daxaur/openpaw -a claude-code/plugin add https://github.com/daxaur/openpawgit clone https://github.com/daxaur/openpaw.git ~/.claude/skills/c-video在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
What This Skill Does
Enables Claude to download online videos, extract audio tracks, convert between formats, and cut/clip video segments using yt-dlp and ffmpeg.
Available CLI Tools
yt-dlp — Video Downloading
# Download a video (best quality)
yt-dlp "https://youtube.com/watch?v=ID"
# Download audio only as MP3
yt-dlp -x --audio-format mp3 "https://youtube.com/watch?v=ID"
# Download specific format/resolution
yt-dlp -f "bestvideo[height<=1080]+bestaudio" "URL"
# Download to specific output path
yt-dlp -o "~/Downloads/%(title)s.%(ext)s" "URL"
# List available formats
yt-dlp -F "URL"
ffmpeg — Processing & Conversion
# Convert video format
ffmpeg -i input.mp4 output.webm
# Extract audio from video
ffmpeg -i input.mp4 -vn -acodec mp3 output.mp3
# Clip a segment (start time, duration)
ffmpeg -i input.mp4 -ss 00:01:30 -t 00:00:45 -c copy clip.mp4
# Resize video
ffmpeg -i input.mp4 -vf scale=1280:720 output.mp4
Usage Guidelines
- Confirm the output directory before downloading large files
- Use
-xwithyt-dlpfor audio-only extraction instead of downloading video first
Notes
- Only download content you have rights to use
yt-dlpmay need periodic updates:pip install -U yt-dlp
GitHub 仓库
相关推荐技能
llamaguard
其他LlamaGuard是Meta推出的7-8B参数内容审核模型,专门用于过滤LLM的输入和输出内容。它能检测六大安全风险类别(暴力/仇恨、性内容、武器、违禁品、自残、犯罪计划),准确率达94-95%。开发者可通过HuggingFace、vLLM或Sagemaker快速部署,并能与NeMo Guardrails集成实现自动化安全防护。
cost-optimization
其他这个Claude Skill帮助开发者优化云成本,通过资源调整、标记策略和预留实例来降低AWS、Azure和GCP的开支。它适用于减少云支出、分析基础设施成本或实施成本治理策略的场景。关键功能包括提供成本可视化、资源规模调整指导和定价模型优化建议。
quantizing-models-bitsandbytes
其他这个Skill使用bitsandbytes库量化大语言模型,能在GPU内存有限时通过8位或4位量化减少50-75%内存占用,同时保持精度损失最小。它支持INT8、NF4、FP4等多种量化格式,可与HuggingFace Transformers无缝集成,适用于需要部署更大模型或加速推理的场景。还提供QLoRA训练和8位优化器支持,让开发者能轻松实现高效模型压缩。
dispatching-parallel-agents
其他该Skill用于并行处理3个以上无依赖关系的独立故障,可为每个问题域分派专属Claude代理同时执行调查修复。它通过并发处理多个独立问题显著提升故障排查效率,特别适用于测试文件、子系统等无共享状态的场景。
