careful

Intercept risky shell commands and prompt for confirmation before destructive actions.

1|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/martin-hsu-test/gstack-gemini-slim --skill careful-martin-hsu-test
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/martin-hsu-test/gstack-gemini-slim/tree/main/.gemini/skills/gstack-careful
Command: npx skills add https://github.com/martin-hsu-test/gstack-gemini-slim --skill careful-martin-hsu-test

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails intercept and warn before executing destructive shell commands, helping prevent accidental data loss and system damage.

Core Features & Use Cases

  • Warns before destructive operations like rm -rf, DROP TABLE, git reset --hard, kubectl delete, and similar commands.
  • Allows user override of warnings to proceed when absolutely necessary.
  • Suitable for touching production, debugging live systems, or working in shared environments where mistakes can have serious consequences.

Quick Start

Activate careful mode and proceed with your command; the guard will warn before any destructive operation and require confirmation.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add confirmation prompts for destructive shell commands like rm -rf or DROP TABLE?

To add confirmation prompts for destructive shell commands, you need safety guardrails that intercept risky patterns like rm -rf or DROP TABLE and prompt for user confirmation before proceeding. This prevents accidental data loss in production and staging environments.

Can I override the warning if I need to execute a destructive command intentionally?

Yes, you can override the warning to proceed with destructive commands when absolutely necessary. The guardrails require user confirmation before execution, but allow intentional overrides so you can run required operations after acknowledging the risks.

What types of destructive commands does a shell safety guardrail intercept?

A shell safety guardrail intercepts destructive commands including rm -rf, DROP TABLE, git reset --hard, and kubectl delete. It applies pre-execution checks to identify these risky patterns and prompts for confirmation before allowing them to run in shared environments.

When do I need safety guardrails for my shell environment?

You need safety guardrails when touching production, debugging live systems, or working in shared environments where destructive actions could cause data loss. They are essential for preventing mistakes that have serious consequences in staging or production infrastructure.

Does this work with git reset --hard and kubectl delete operations?

Yes, this works with git reset --hard and kubectl delete operations. The guardrails apply pre-execution checks to these destructive patterns, warning you before execution and requiring confirmation to prevent accidental data loss or system damage.

What is the best way to prevent accidental data loss from risky shell commands?

The best way to prevent accidental data loss from risky shell commands is implementing pre-execution checks that warn before destructive operations. Activating careful mode intercepts commands and requires confirmation, safeguarding production and shared environments from mistakes.