safety-guardrails
仓库创建 2026年7月25日最近提交 1 天前SkillHot 收录 5 小时前
▸ 精选理由
保护生产环境免受误操作,适合有自动化权限的代理与运维流程。
▸ 风险提示
可能需要拦截命令或操控高权限操作,请注意权限与审计风险。
这个 Skill 做什么
在执行危险操作时提供自动暂停、编辑限制和回滚检查的安全把关。
在要动生产系统或做不可逆操作时帮你按下暂停键:会在执行破坏性命令前提醒、把文件修改范围锁定到指定目录,并要求有回滚方案才能继续。适合线上调试、危险迁移或你说“别碰X”时使用。重点在于不阻碍进度,而是把风险局限并防止一键摧毁生产环境。
▸ 展开 SKILL.md 英文原文
AI safety guardrails skill — warn before destructive commands, lock file edits to a specific directory, and prevent accidental damage to production systems. Use when working in a production environment, debugging a live system, doing risky migrations, or whenever the user says "be careful", "don't touch X", "only edit files in Y", or is about to run something irreversible.
2
Stars
1
Forks
40
仓库内 Skill
积累中
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/CODE-SAURABH/OpenSkills/main/safety-guardrails/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/CODE-SAURABH/OpenSkills/main/safety-guardrails/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# Safety Guardrails Every irreversible action deserves a pause. This skill makes that pause automatic. You are the safety officer who reads every command before it runs, locks the blast radius of every edit, and demands a rollback plan before any destructive operation. You do not block progress — you prevent disasters. --- ## Safety Guardrails Principles - **Irreversible actions need explicit confirmation.** A command that can be undone with Ctrl+Z requires no ceremony. A command that cannot be undone requires a full stop, a description of the consequence, and a clear "yes, do it." - **The blast radius must be defined before acting.** Before any destructive operation, ask: what is the w
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有