A cross-platform utility for securely backing up OpenClaw state directories and workspaces while automatically excluding sensitive credentials.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install safe-backup
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install safe-backup using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Safe Backup is a specialized utility designed to manage the lifecycle of your agent data. As part of the Openclaw Skills ecosystem, it provides a robust mechanism to package configuration files, agent definitions, and memory files into a portable format. It prioritizes security by automatically omitting sensitive information like API tokens and credentials, ensuring that your backups remain safe even if shared or stored in cloud environments.
This skill is essential for developers who need to migrate their AI agent setups between different machines or maintain a disaster recovery plan. By supporting Linux, macOS, and Windows via Git Bash, it ensures consistency across different development environments while leveraging standard Unix tools like rsync and tar for maximum reliability and efficiency.
Ensure you have bash and rsync installed. For Windows users, Git Bash or WSL is required. Run the following command to initiate a backup:
~/.openclaw/skills/safe-backup/scripts/backup.sh
To restore from a backup, stop the gateway and extract your files using the following workflow:
systemctl --user stop openclaw-gateway
mkdir -p /tmp/restore
tar -xzf /path/to/safe-backup.tar.gz -C /tmp/restore
cp -r /tmp/restore/state/* ~/.openclaw
Safe Backup organizes data into a structured archive that mirrors the OpenClaw internal directory while filtering out volatile or sensitive files. This ensures high compatibility across different Openclaw Skills versions.
| Directory | Included Content |
|---|---|
~/.openclaw/ |
Core configuration files and skill settings |
workspace/ |
Agent workspace files and project data |
agents/ |
Individual agent definitions and logic |
memory/ |
Long-term memory files and context |
hooks/ |
Custom automation hooks and triggers |
Note: Sensitive files such as auth-profiles.json, .env, and *.key are strictly excluded from the schema to maintain security.
Loading
A comprehensive tool for interacting with Feishu documents using user-level authentication for reading, writing, and block management.

A versatile stock market data retrieval tool supporting China A-shares, Hong Kong, and US markets via lightweight APIs and advanced SDKs.

A sophisticated workflow controller for managing continuous, multi-step AI subagent task lines without manual user re-prompting.

A high-performance text-to-speech skill leveraging Aliyun Bailian for natural AI voice generation via command-line tools.

A comprehensive social media scraping and automation skill supporting real-time interaction and scheduled batch monitoring.

A specialized skill for turning technical documentation and dev logs into opinionated, high-engagement social media content.








































