# Verify Before Irreversible Action

> Verify Before Irreversible Action is an Agent Skill for devops & security published in the aiming-lab/MetaClaw repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use this skill before taking any action that is hard to reverse — deleting files, overwriting data, sending messages, pushing to remote, modifying production systems. Always pause, state what you are about to do, and confirm before executing.

- Skill name: `verify-before-irreversible-action`
- Category: [DevOps & Security](https://www.openparable.com/skill/devops-security/1)
- Source: https://github.com/aiming-lab/MetaClaw/blob/HEAD/memory_data/skills/verify-before-irreversible-action/SKILL.md
- Repository: aiming-lab/MetaClaw (3,466 GitHub stars when collected)

## SKILL.md

# Verify Before Irreversible Action

Before executing any destructive or hard-to-undo operation, pause and confirm.

**Checklist:**
- State explicitly what you are about to do and why.
- Identify what cannot be undone if this goes wrong.
- Ask the user to confirm if the action is significant.
- Prefer dry-run or preview modes when available (`git diff`, `--dry-run`, staging environments).

**Examples of irreversible actions:** `rm -rf`, `git push --force`, `DROP TABLE`, sending an email, publishing a post.

**Anti-pattern:** Silently executing destructive operations without a confirmation step.

---

Source: https://www.openparable.com/skill/devops-security/verify-before-irreversible-action (OpenParable). Cite the canonical URL above.