安装方式
手动下载安装
下载 ZIP 后解压到技能目录即可安装。若在桌面客户端 WebView中直接下载出现异常,本站会改为提示页 + 原始链接,请按页内说明操作。
下载 ZIP (shub-quick-backup-restore-v1.0.0.zip)触发指令
/quick-backup-restore
跨平台安装指引
该技能声明兼容以下 1 个平台,将 ZIP 解压到对应目录即可被识别。
unzip shub-quick-backup-restore-v1.0.0.zip -d ~/.claude/skills/
mkdir -p 创建;启用 Skill 后请重启对应 Agent 让配置生效。
使用指南
快速备份与恢复
围绕 快速备份与恢复:小数据集或配置的快速快照与回滚;不适合替代完整灾备方案。 无需在每次任务前把零散英文说明手工拼进上下文,也 减少 与客户端默认行为脱节的试错;具体命令、钩子与 JSON 参数仍以 ZIP 包内 SKILL.md 为权威。下文结构与站内 MCP CLI 类专题稿相同:何时用、前置、流程、速查与故障。
何时使用
- 小数据集或配置的快速快照与回滚
- 不适合替代完整灾备方案
- 已获取本技能 ZIP,并准备在 Claude Code / OpenClaw 中按 SKILL.md 挂载。
- 希望用中文专题稿快速判断「该不该启用」,再深入英文 SKILL 查参数与边界。
- 需要与团队对齐同一套触发方式、目录约定或回调格式时。
前置条件
- 通用:可运行 Claude Code 或文档要求的客户端;有可读写的项目工作区(或 SKILL.md 指定的沙箱目录)。
- 权威细节:API Key / OAuth、钩子路径、环境变量以 ZIP 内 SKILL.md 为准。
典型流程
- 从 ClawHub / 站内分发获取技能 ZIP,校验版本与校验和(若提供)。
- 阅读 SKILL.md 的安装段落:目录落点、客户端类型(Claude Code / OpenClaw / 脚本)。
- 用文档中的最小示例完成第一次调用(单文件修改、单次查询或单次委派)。
- 确认工作目录、权限边界与输出路径后,再处理多文件或长耗时任务。
- 需要回调 / Webhook / 通知时,按 SKILL.md 配置端点并在测试环境先验通。
与 ZIP / SKILL.md 的关系
站内专题稿与 MCP CLI 类 oss 稿同样:概括何时用、怎么接、怎么排错;命令模板、钩子名、JSON 字段、版本矩阵一律以 ZIP 内 SKILL.md 与 ClawHub 上游为准。
命令示例(摘自包内 SKILL.md)
以下为从上游 SKILL.md(或入库正文)自动抽取的终端/脚本片段;路径、环境变量与参数以当前 ZIP 与官方说明为准。
ClawHub slug:quick-backup-restore(安装命令以 SKILL.md / claw CLI 为准)。
sudo bash {baseDir}/bin/backup.sh
tail -5 /var/log/quick-backup-restore.log
tail -20 /var/log/quick-backup-restore.log
restic -r /var/backups/quick-backup-restore --password-file /etc/quick-backup-restore.pass snapshots
SNAPS=$(restic -r /var/backups/quick-backup-restore --password-file /etc/quick-backup-restore.pass snapshots --json | jq -r '.[-2:][].id')
restic -r /var/backups/quick-backup-restore --password-file /etc/quick-backup-restore.pass diff $SNAPS
sudo bash {baseDir}/bin/restore.sh
sudo bash {baseDir}/bin/restore.sh latest --file /root/.openclaw/workspace/MEMORY.md --target /tmp/tc-restore
# Preview the result, then move manually:
# cp /tmp/tc-restore/root/.openclaw/workspace/MEMORY.md /root/.openclaw/workspace/MEMORY.md
sudo bash {baseDir}/bin/restore.sh <snapshot_id>
restic -r /var/backups/quick-backup-restore --password-file /etc/quick-backup-restore.pass check
sudo bash {baseDir}/bin/setup.sh
站内入库时的触发命令(完整语义见 ZIP):
# 使用本技能时可在对话中引用或执行上述指令;完整参数与示例见下载包内 SKILL.md。
/quick-backup-restore
最佳实践
- 先 SKILL.md 再猜参数;站内专题稿不替代 schema 与必填字段说明。
- 委派任务时写清验收标准(命令、文件路径、测试命令),减少来回追问。
- 长任务用文档推荐的回调 / 日志落盘代替高频轮询,省 Token 也省机器负载。
- 多技能同时启用时,注意钩子加载顺序与重复工具调用(以 SKILL.md 冲突说明为准)。
调试与排错
- 打开 stderr 与客户端日志;PTY/tmux 场景同时看面板最后几十行输出。
- 参数错误时对照 SKILL.md 中的 JSON/CLI 示例(引号、转义、工作目录)。
- 网络类失败:查代理、防火墙、MCP 传输方式(stdio / HTTP / SSE)。
速查
| 动作 | 说明 |
|------|------|
| 获取技能包 | ClawHub / 站内 ZIP,核对版本 |
| 权威步骤 | 优先阅读 ZIP 内 SKILL.md |
| 首次试跑 | 使用 SKILL.md 最小示例 |
| 验收 | 对照路径、测试命令或回调负载 |
常见故障
- 无输出或立即退出 → 工作目录错误、依赖未装、或 Claude Code 未登录;按 SKILL.md 自检清单执行。
- 权限被拒绝 → 检查沙箱路径、
--permission-mode与工具白名单。 - 与简介不符 → 以英文 SKILL 与上游仓库为准,站内稿仅作结构化导读。
# ⏱🦞 Quick Backup and Restore (time machine)
Your OpenClaw agent builds memory, preferences, and context over time — and agents make mistakes. They overwrite things. They corrupt their own context. When that happens, you want to go back to *exactly* 2 hours ago, not yesterday's backup, not a full system restore.
This skill gives your agent hourly snapshots of its own brain. Restic-powered, encrypted, silent on success — and it pings you on Telegram only when something breaks.
## Overview
Quick Backup and Restore protects OpenClaw's runtime context (memory, sessions, credentials, config) with hourly snapshots. It runs automatically via cron. You can also trigger it manually or restore any point in the last 72 hours.
**Repository:** `{baseDir}/../../../var/backups/quick-backup-restore` (or as configured in `{baseDir}/config.yaml`)
**Log:** `/var/log/quick-backup-restore.log`
**Password file:** `/etc/quick-backup-restore.pass`
---
## When the user asks to set up or install Quick Backup and Restore (time machine)
1. Check if already set up:
```bash
restic -r /var/backups/quick-backup-restore --password-file /etc/quick-backup-restore.pass snapshots 2>/dev/null && echo "Already initialized"
```
2. If not initialized, ask the user to fill in `{baseDir}/config.yaml` with their Telegram `bot_token` and `chat_id`, then run:
```bash
sudo bash {baseDir}/bin/setup.sh
```
3. Confirm setup succeeded by tailing the log:
```bash
tail -5 /var/log/quick-backup-restore.log
```
---
## When the user asks to run a manual backup
```bash
sudo bash {baseDir}/bin/backup.sh
```
Then confirm with:
```bash
tail -5 /var/log/quick-backup-restore.log
```
---
## When the user asks to check backup status or history
Show the last 10 log lines:
```bash
tail -20 /var/log/quick-backup-restore.log
```
List all snapshots (most recent first):
```bash
restic -r /var/backups/quick-backup-restore --password-file /etc/quick-backup-restore.pass snapshots
```
Show what changed between the two most recent snapshots:
```bash
SNAPS=$(restic -r /var/backups/quick-backup-restore --password-file /etc/quick-backup-restore.pass snapshots --json | jq -r '.[-2:][].id')
restic -r /var/backups/quick-backup-restore --password-file /etc/quick-backup-restore.pass diff $SNAPS
```
---
## When the user asks to restore or roll back
**Interactive restore (recommended — always dry-runs first):**
```bash
sudo bash {baseDir}/bin/restore.sh
```
**Restore a specific file from the latest snapshot:**
```bash
sudo bash {baseDir}/bin/restore.sh latest --file /root/.openclaw/workspace/MEMORY.md --target /tmp/tc-restore
# Preview the result, then move manually:
# cp /tmp/tc-restore/root/.openclaw/workspace/MEMORY.md /root/.openclaw/workspace/MEMORY.md
```
**Restore a specific snapshot by ID:**
```bash
sudo bash {baseDir}/bin/restore.sh <snapshot_id>
```
Always confirm with the user before executing a full restore to `/`.
---
## When the user asks to check repo integrity
```bash
restic -r /var/backups/quick-backup-restore --password-file /etc/quick-backup-restore.pass check
```
---
## When the user asks to change configuration
Edit `{baseDir}/config.yaml` with the requested changes (schedule, retention, paths, Telegram credentials), then re-run setup to apply:
```bash
sudo bash {baseDir}/bin/setup.sh
```
---
## Important notes
- **Silent by design:** cron runs every hour at :05 and logs to `/var/log/quick-backup-restore.log`. No output unless there is a failure.
- **Telegram fires only on failure.** If the user has not configured `bot_token` and `chat_id`, failures are logged only.
- **This is the time machine layer.** It protects against "the agent broke something in the last 3 days." It is NOT a disaster recovery backup — that should be handled by an off-VM backup (e.g. restic to a remote server).
- **Password:** The restic repository is AES-256 encrypted. The password is at `/etc/quick-backup-restore.pass` (chmod 600). Losing it means losing access to all snapshots.
- **Never commit `secrets.env` or `.pass` files to git.** They are excluded via `.gitignore`.