myopenclaw-backup-restore
Cross-platform backup and restore for OpenClaw. Works on Windows, macOS, and Linux — backups created on any OS can be restored on any other OS. Use when user wants to create a snapshot, restore from backup, migrate to a new machine, or protect against data loss. Supports dry-run preview, automatic pre-restore snapshots, gateway token preservation, credential permission hardening, and a built-in HTTP server for browser-based management. Only requires Node.js (no bash/rsync/python needed).
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/beyound87/myopenclaw-backup-restoreWhat This Skill Does
The myopenclaw-backup-restore skill provides a robust, cross-platform mechanism for managing OpenClaw data. Unlike manual copying, this tool intelligently bundles your workspace, including memory files (MEMORY.md, SOUL.md), agent configurations, gateway tokens, API keys, and persistent state files. It generates standard compressed archives (tar.gz or ZIP) that remain compatible across Windows, macOS, and Linux, ensuring you can migrate your entire agent setup between machines seamlessly. The skill includes built-in safety features such as automatic pre-restore snapshots, credential permission hardening, and a dry-run mode that previews changes before overwriting existing data.
Installation
To install this skill, use the ClawHub registry command in your terminal:
clawhub install openclaw/skills/skills/beyound87/myopenclaw-backup-restore
No external dependencies are required beyond Node.js, making it a lightweight addition to your infrastructure.
Use Cases
- Cross-Platform Migration: Move your complete agent environment from a Windows desktop to a Linux server or vice versa.
- Disaster Recovery: Protect your agent's memory index, sessions, and cron jobs against hardware failure by maintaining local snapshots.
- Versioning & Rollbacks: Create a backup point before testing new agent skills or configuration changes, allowing for a quick revert if issues arise.
- Remote Management: Utilize the optional built-in HTTP server to monitor or manage your backups through a web browser using a secure token.
Example Prompts
- "OpenClaw, please trigger a full backup of my current workspace and save it to the default backup directory."
- "I need to move to my new laptop. List the available backups so I can identify the most recent archive to restore."
- "Run a dry-run restoration using the latest backup file to ensure my settings will migrate correctly without overwriting anything yet."
Tips & Limitations
- Security First: Because these archives contain sensitive tokens and API keys, never upload them to public cloud storage or version control systems. Always handle them as sensitive credentials.
- Permissions: On non-Windows systems, the tool automatically applies
chmod 600/700to secure your configuration files; do not manually change these unless necessary. - Exclusions: Be aware that large media files, node_modules, and logs are intentionally excluded to keep archives lean and portable. Always verify the contents via the references file if you are unsure what is included.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-beyound87-myopenclaw-backup-restore": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
smart-agent-memory
跨平台 Agent 长期记忆系统。分层上下文供给 + 温度模型 + Skill经验记忆 + 结构化存储 + 自动归档。三层存储：Markdown（人可读，QMD 可搜索）+ JSON（结构化）+ SQLite/FTS5（高性能全文搜索）。纯 Node.js 原生模块，零外部依赖。
token-pilot
Automatic token optimization during interaction. Behavioral rules + plugin synergy + workspace analyzer. Pure Node.js, cross-platform. Activate on session start (rules auto-apply) or when user asks about token usage/cost/audit.
security-hardening-safey
Agent 安全加固技能。用于：(1) 安装后经用户确认，将安全红线注入所有 Agent 的底层记忆（AGENTS.md），精简版注入~112行，不造成token膨胀；(2) 当用户问到安全规则、提示词注入防御、危险命令管控、外部代码审查、多模态注入等话题时加载此技能；(3) 进行安全审计或排查疑似注入事件时使用。触发词：安全加固、提示词注入、prompt injection、rm -rf、eval exec、外部内容攻击、Agent被黑、安全规则、安全红线、代码审查、脚本审查、skill vetter、安装技能、初始化。
coding-lead
Coding execution skill for any implementation-focused agent. Current production path is claude-only with simple tasks direct, medium tasks preferring ACP run or direct acpx, and complex tasks handled via existing agent continuity plus context files instead of ACP session persistence. Integrates with qmd and smart-agent-memory when available.
team-builder
在 OpenClaw 上一键部署多 Agent SaaS 团队工作区。内置双开发轨（devops 交付 + fullstack-dev 实现）、实时 spawn 调度、cron 巡检、Deep Dive 产品知识目录、onboarding 引导。支持自定义角色、模型、时区，可选 Telegram 接入。