shell

Executes user-provided text after /shell as a literal terminal command.

Updated Oct 15, 2019
One-click install
npx skills add https://github.com/kkkaoru/dotfiles --skill shell-kkkaoru
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: shell
Source: https://github.com/kkkaoru/dotfiles/tree/main/.cursor/skills-cursor/shell
Command: npx skills add https://github.com/kkkaoru/dotfiles --skill shell-kkkaoru

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When you already know the exact shell command you want to run, you do not want an AI to rewrite, explain, or second-guess it. This Skill passes your text straight to the terminal so the command runs exactly as typed. ## Core Features & Use Cases - Literal Command Execution: Treats everything after the /shell invocation as the exact command to run, with no rewriting or improvement. - Minimal Overhead: Skips repository inspection unless the command itself requires repository context. - Concise Reporting: Runs the command first, then briefly reports the exit status and any important stdout or stderr. - Use Case: You type "/shell git status --short" and the command runs immediately in the terminal, returning the working tree status without extra commentary. ## Quick Start Invoke /shell followed by the exact terminal command you want executed, such as asking to run ls -la in the current directory.

Frequently Asked Questions about shell

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run an exact shell command without the AI modifying it?

Invoke /shell followed by the command text. The Skill treats everything after the invocation as the literal command and executes it directly in the terminal without rewriting, explaining, or improving it.

What happens if I invoke /shell with no command after it?

The Skill asks you which command to run. It does not guess or execute anything on its own when no command text follows the invocation.

Does the shell skill inspect the repository before running commands?

No, it skips repository inspection by default. It only looks at repository context when the command itself requires that context to execute correctly.

What output does the shell skill return after running a command?

It runs the command first, then briefly reports the exit status along with any important stdout or stderr output, keeping the response concise.

When should I not use the /shell command execution approach?

Avoid it when you want the AI to interpret a goal and construct the command itself. This Skill only fits cases where you explicitly invoke /shell and already know the exact command to run.