c-clipboard
关于
This Claude Skill enables clipboard operations via macOS's built-in `pbcopy` and `pbpaste` commands for copying, pasting, and transforming content between the terminal and system clipboard. It allows you to easily pipe command outputs to the clipboard, read clipboard contents into files or other commands, and apply transformations like sorting or case conversion. Use it for quick terminal-based clipboard management without needing external tools on macOS.
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-clipboard在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Clipboard — Copy & Paste
Read from and write to the system clipboard. Built into macOS, no install needed.
Commands
# Read clipboard contents
pbpaste
# Copy text to clipboard
echo "hello world" | pbcopy
# Copy file contents to clipboard
pbcopy < /path/to/file.txt
# Save clipboard to file
pbpaste > /path/to/output.txt
# Copy command output to clipboard
ls -la | pbcopy
date | pbcopy
# Transform clipboard content
pbpaste | tr '[:lower:]' '[:upper:]' | pbcopy # uppercase
pbpaste | sort | pbcopy # sort lines
pbpaste | wc -w # word count
# Copy with no trailing newline
printf "%s" "exact text" | pbcopy
Linux Equivalents
# If on Linux, use xclip or xsel
xclip -selection clipboard # copy (pipe into)
xclip -selection clipboard -o # paste
Guidelines
- When the user says "copy this" or "put this in my clipboard", use
pbcopy - When the user says "what's in my clipboard?" or "paste", use
pbpaste - For transformations, pipe
pbpastethrough the transform and back topbcopy - Always confirm what was copied with a brief summary
- Never display clipboard contents unless asked — they may contain sensitive data
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。
