shell

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

Updated May 28, 2023
One-click install
npx skills add https://github.com/steveulrich/ProjectB --skill shell-steveulrich
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: shell
Source: https://github.com/steveulrich/ProjectB/tree/main/.cursor/skills/shell
Command: npx skills add https://github.com/steveulrich/ProjectB --skill shell-steveulrich

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It lets you run an exact shell command through the AI without the model rewriting, explaining, or modifying it first, giving you direct terminal control when you need it. ## Core Features & Use Cases - Literal Command Execution: Treats all text after the /shell invocation as the exact command to run in the terminal. - No Command Rewriting: Runs the command as-is without inspecting the repository or improving the input. - Status Reporting: Reports the exit status and important stdout or stderr after execution. - Use Case: When you know the exact command you want, such as checking git status or listing files, invoke /shell followed by the command to run it verbatim. ## Quick Start Invoke /shell followed by the exact command you want executed, for example asking to run git status in the terminal.

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 through the AI assistant?▼

Invoke /shell followed by the literal command text. The skill passes everything after the invocation directly to the terminal tool without rewriting or explaining the command first.

Will the AI modify or improve my shell command before running it?▼

No. The skill explicitly forbids rewriting, explaining, or improving the command. It executes your text verbatim and only reports the exit status and important output afterward.

What happens if I invoke /shell with no command?▼

If you invoke /shell without any following text, the skill asks you which command to run instead of guessing or executing anything on its own.

Does the shell skill inspect the repository before running commands?▼

No, it does not inspect the repository first unless the command itself requires repository context. The design prioritizes immediate, literal execution of your input.

When should I not use the /shell command?▼

Avoid it when you want the AI to interpret a goal and construct commands for you. It is intended only for cases where you explicitly want your exact text executed directly in the terminal.