openclaw/config-rollback
2233admin/config-rollback/SKILL.md
自动回滚保护。修改配置前先备份+设5分钟系统定时任务，改坏自动还原。当用户说"自动回滚"或需要改配置时使用此 Skill。
$ install --global
skillsauthnpx skillsauth add openclaw/skills config-rollbackInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 3, 2026, 5:58 AM299.0s1 file scanned
SKILL.md
Config Rollback - 自动回滚保护
口令
用户说"自动回滚"时触发
执行流程
- 备份当前配置
cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.bak
- 设系统级定时任务（5分钟后）
echo "cp ~/.openclaw/openclaw.json.bak ~/.openclaw/openclaw.json && systemctl restart openclaw-gateway" | at now + 5 minutes
-
返回 job ID
-
用户确认正常后
atrm <job-id>
适用场景
- 修改 channel 配置
- 修改代理路由
- 更新插件
- 修改模型配置
- 任何需要重启 gateway 的操作
核心原则
- 必须是系统级定时任务（at/crontab）
- 不能依赖 OpenClaw 本身
- 双重保护：git commit + 自动回滚
Related Skills
openclaw/mcdonalds-skill
tools
VerifiedTrustedCommunity
Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.
3,962SKILL.mdUpdated Apr 10, 2026
openclaw/scrapebadger
development
VerifiedTrustedCommunity
Web scraping platform — Twitter/X data, Vinted marketplace, and general web scraping API
3,962SKILL.mdUpdated Apr 10, 2026
openclaw/slowmist-security-cc
development
VerifiedTrustedCommunity
SlowMist AI Agent Security Review — comprehensive security framework for skills, repositories, URLs, on-chain addresses, and products (Claude Code version)
3,962SKILL.mdUpdated Apr 10, 2026
openclaw/humanizer-cn
data-ai
VerifiedTrustedCommunity
去除中文文本中的 AI 写作痕迹，使其读起来自然。基于维基百科 AI 写作特征指南，检测 24 种 AI 模式。触发词：humanizer-cn、去除 AI 痕迹、去除 AI 写作痕迹、中文文本人性化。
3,962SKILL.mdUpdated Apr 10, 2026