c-speakers
关于
This Claude skill enables developers to control Sonos speakers via the `sonos` CLI for audio playback management. It handles play/pause, volume adjustment, room grouping, and favorite selection across speaker zones. Use it when building smart home integrations or automating multi-room audio workflows.
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-speakers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 control Sonos speakers — playback, volume, grouping, and favorites — via the sonos CLI.
Available CLI Tool: sonos
Common Commands
# List all Sonos rooms/players
sonos rooms
# Play and pause
sonos play --room "Living Room"
sonos pause --room "Living Room"
# Skip tracks
sonos next --room "Living Room"
sonos previous --room "Living Room"
# Set volume (0-100)
sonos volume 50 --room "Living Room"
# Adjust volume relative
sonos volume +10 --room "Kitchen"
sonos volume -5 --room "Kitchen"
# Play a favorite (from Sonos app favorites)
sonos favorite "Morning Jazz" --room "Bedroom"
# List favorites
sonos favorites
# Group rooms together
sonos group "Kitchen" --with "Living Room"
# Ungroup a room
sonos ungroup "Kitchen"
# Show now playing info
sonos status --room "Living Room"
Usage Guidelines
- Always specify
--roomto target the correct speaker - Use
sonos roomsto discover available rooms if unsure of names - Grouping joins a room into the specified room's group
Notes
- Requires
sonosCLI (sonoscli) installed and Sonos system on local network - Favorites must be pre-configured in the Sonos app
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。
