做什么
在云端服务器上自我托管 OpenClaw 时使用,将远程 OpenClaw 网关硬化,在SSH地道,Tailscale,或倒置-代理曝光之间选择,或审查Podman,配对,沙箱,sord auth,以及工具-permission中默认的安全个人部署.
技能库 智客分类:运维与云 openclaw-secure-linux-cloud
在云端服务器上自我托管 OpenClaw 时使用,将远程 OpenClaw 网关硬化,在SSH地道,Tailscale,或倒置-代理曝光之间选择,或审查Podman,配对,沙箱,sord auth,以及工具-permission中默认的安全个人部署.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
在云端服务器上自我托管 OpenClaw 时使用,将远程 OpenClaw 网关硬化,在SSH地道,Tailscale,或倒置-代理曝光之间选择,或审查Podman,配对,沙箱,sord auth,以及工具-permission中默认的安全个人部署.
当用户提及以下任何一项时使用此技能 :
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Overview、When To Use、Workflow、1. Classify the request、2. Start from the secure baseline、3. Separate local and server actions。 其中含规范建议的小节:分步指令。
文件分析:除 SKILL.md 外,正文引用了 references/REFERENCE.md,属于带资源的技能包,这些文件按需再读。
Use when self-hosting OpenClaw on a cloud server, hardening a remote OpenClaw gateway, choosing between SSH tunneling, Tailscale, or reverse-proxy exposure, or reviewing Podman, pairing, sandboxing, token auth, and tool-permission defaults for a secure personal deployment.
OverviewWhen To UseWorkflow1. Classify the request2. Start from the secure baseline3. Separate local and server actions4. Ask only for blocking facts5. Use the access escalation ladderOutput ExpectationsCommon MistakesReference Usage
来源分类:skills.sh agent-skill
nameopenclaw-secure-linux-clouddescriptionreferences/REFERENCE.md以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。
具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「openclaw-secure-linux-cloud」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-ffd7f0693900ff89-Openclaw-%E5%AE%89%E5%85%A8-Linux-%E4%BA%91.html 请存为 .cursor/skills/openclaw-secure-linux-cloud/SKILL.md 或 .claude/skills/openclaw-secure-linux-cloud/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。 该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/xixu-me/skills 取完整目录,不要只建一个 SKILL.md。
需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。
npx skills add 'https://github.com/xixu-me/skills' --list
npx skills add 'https://github.com/xixu-me/skills' --skill 'openclaw-secure-linux-cloud'
CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。
Use this skill for the conservative "deploy first, expose later" pattern for OpenClaw on a cloud server.
Default to a private control plane:
127.0.0.1.This skill is for secure Linux cloud hosting. If the user only wants the fastest generic OpenClaw install on a local machine, prefer the official OpenClaw onboarding docs instead of forcing this flow.
Open references/REFERENCE.md when you need the
command matrix, baseline config shape, checklist, or access-path comparison.
Use this skill when the user mentions any of the following:
Do not use this skill for:
Put the task in one of these buckets before giving detailed guidance:
Unless the user clearly asks for something else, recommend this baseline:
Treat these as explicit red flags:
0.0.0.018789 to the public internet~/.openclaw readable by other local usersAlways distinguish between:
Do not blur the two execution contexts together. The user should be able to tell which commands run on their laptop and which run on the Linux host.
Only stop for missing facts that change the safe path, such as:
If a detail is not safety-critical, make the reasonable secure assumption and state it.
Recommend remote access in this order:
If the user asks for Tailscale or reverse proxy, still explain why the loopback binding and private-first model remain the baseline.
For a fresh deployment, provide:
For a hardening review, provide:
For an access-path decision, provide:
Use references/REFERENCE.md when you need:
运维与云
用于容器管理,图像操作,调试的基本道克命令和工作流程.
运维与云
从开放的代理技能生态系统中发现并安装技能. 使用时:(1)用户问"我如何做X",X可能拥有现有技能,(2)用户说"为X找到技能"或"是否为X有技能",(3)用户问"你能否做X",X是专门能力,(4)用户想扩展代理能力,(5)用户想搜索工具,模板,或工作流程,(6)用户提到他们希望…
运维与云
构建,部署,评价,优化,微调,管理微软创始代理,模型,资源最终结束. 用法:铸造、azd ai代理、azd 提供/部署、托管代理脚手架/开发/运行/部署/拖放、即时代理创建、创建代理、更新代理、添加代理工具、援引代理、代理.yaml、评估代理、批量活化、连续活化、持续监测、代理C…
运维与云
执行已有.azure/部署计划.md和基础设施文件的ALREADY-PREPARED应用程序的Azure部署。 当用户向 CREATE 请求新应用程序时, 请不要使用此技能 。 这种技能运行了 azd上行, azd 部署, trarraform 应用, 和 az 部署命令带有内置…