Runs shell commands directly from Claude conversations and captures the output back into the chat. You'd reach for this when you need Claude to actually execute something on your system rather than just suggest commands, like running build scripts, checking file contents, or automating deployment steps. The obvious caveat is security: you're giving an AI direct terminal access, so this makes sense in controlled environments or when you're comfortable reviewing what gets executed. Think of it as turning Claude from a coding assistant into one that can actually touch your filesystem and run your tools.
npx skills add https://github.com/alirezarezvani/claude-skills --skill execute