careful

Analyze commands and prompt before executing destructive operations.

Updated Apr 25, 2026
One-click install
npx skills add https://github.com/uzumaki-inc/uzustack --skill careful-uzumaki-inc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/uzumaki-inc/uzustack/tree/main/careful
Command: npx skills add https://github.com/uzumaki-inc/uzustack --skill careful-uzumaki-inc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides safety guardrails for destructive commands, warning users before execution of dangerous operations such as rm -rf, DROP TABLE, git reset --hard, kubectl delete, and similar actions, helping prevent accidental production impact.

Core Features & Use Cases

  • Pre-execution warnings detect dangerous patterns in user input and prompt for confirmation.
  • Override capability lets informed users proceed with explicit acknowledgment.
  • Configurable modes (safety, production, careful) tailor risk posture in live or shared environments.

Quick Start

Enable safety guardrails and try a dangerous command to see the warning prompt and decide whether to proceed.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent accidental execution of destructive bash commands like rm -rf?

To prevent accidental execution of destructive bash commands like rm -rf, you need a pre-execution safety guardrail. This Skill intercepts dangerous input patterns before execution and prompts you for explicit confirmation.

Can I add a confirmation prompt before running git reset --hard or kubectl delete?

Yes, you can add a confirmation prompt before running git reset --hard or kubectl delete. The PreToolUse hook analyzes your input command and returns an ask prompt whenever it detects an irreversible operation.

What is a pre-tool-use safety guardrail for production environments?

A pre-tool-use safety guardrail for production environments is a mechanism that enforces safety checks before command execution. It detects dangerous patterns like DROP TABLE and prompts you to prevent accidental production impact.

How do I override safety warnings when I intentionally need to run a destructive command?

You can override safety warnings when you intentionally need to run a destructive command by providing explicit acknowledgment. This override capability allows informed users to proceed with dangerous operations after the warning prompt.

Does this safety guardrail work for database operations like DROP TABLE?

Yes, this safety guardrail works for database operations like DROP TABLE. It covers common dangerous actions across bash, git, kubectl, and database commands, warning you before execution of irreversible operations in shared environments.

When should I use careful mode versus production mode for command safety?

You should choose between careful, production, or safety modes based on your risk posture in live or shared environments. These configurable modes tailor how the guardrail handles destructive commands and prompts you for confirmation.