← 返回 Skills 市场
90
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cmg
功能描述
腾讯云迁移平台(CMG/MSP)全流程能力。触发词:资源扫描、扫描阿里云/AWS/华为云/GCP资源、生成云资源清单、选型推荐、对标腾讯云、推荐规格、帮我推荐、给我推荐、ECS对应什么腾讯云产品、成本分析、TCO、迁移报价、询价、价格计算器、cmg-scan、cmg-recommend、cmg-tco
使用说明 (SKILL.md)
CMG 云迁移 Skill
云迁移服务平台(CMG/MSP)AI 辅助能力,覆盖迁移前评估的完整流程。
能力地图
| 能力 | 触发场景 | 详细文档 |
|---|---|---|
| 资源扫描 (cmg-scan) | 扫描阿里云/AWS/华为云等资源清单,导出 Excel | {baseDir}/references/scan.md |
| 选型推荐 (cmg-recommend) | 将扫描结果对标腾讯云产品规格,生成推荐方案 | {baseDir}/references/recommend.md |
| 成本分析 (cmg-tco) | ⚠️ 必须通过 API/价格计算器获取真实价格,严禁自行估算价格,生成 TCO 对比报告 | {baseDir}/references/tco.md |
| 迁移执行引导 (cmg-migrate) | 根据资源类型引导用户使用腾讯云对应迁移工具(主机/对象存储/数据库/文件存储) | {baseDir}/references/migrate.md |
产品代码速查表(所有平台):{baseDir}/references/products.md
典型工作流
1. 资源扫描 (cmg-scan)
↓ 产物:xxx_scan_xxxxxx.xlsx(资源清单 Excel)
2. 选型推荐 (cmg-recommend)
↓ 输入:xxx_scan_xxxxxx.xlsx
↓ 产物:cmg_recommend_result.json(推荐结果,含源端参数 + MCP 原始返回)
3. 成本分析 (cmg-tco)
↓ 输入:cmg_recommend_result.json(推荐方式,优先)或 Excel(直接扫描方式)
↓ ⚠️ 严禁自行估算/编造价格!必须通过以下真实渠道获取:
↓ 方式1(推荐): 调用 tco_pricing.py 脚本通过 API 批量询价
↓ 方式2(备选): 通过浏览器访问各云厂商官方价格计算器
↓ 产物:pricing_data.json + TCO 对比报告(Excel + HTML)
4. 迁移执行引导 (cmg-migrate)
↓ 根据资源类型引导对应迁移工具:
↓ 主机 → 云迁移 > 主机迁移
↓ 对象存储 → 云迁移 > 对象存储迁移(MSP)
↓ 数据库 → DTS
↓ 文件存储 → 云迁移 > 文件存储迁移(使用迁移集群)
使用指南
收到用户请求后,先判断属于哪个能力阶段,然后 Read 对应文档:
- 用户想扫描云资源:Read
{baseDir}/references/scan.md - 用户想选型推荐/对标腾讯云/推荐规格:Read
{baseDir}/references/recommend.md - 用户想查价格/TCO 分析/询价/价格计算器:Read
{baseDir}/references/tco.md - 用户想迁移/问怎么迁移/迁移工具/开始迁移:Read
{baseDir}/references/migrate.md - 用户问产品代码:Read
{baseDir}/references/products.md
cmg-recommend 特别说明
选型推荐通过 mcporter + 远端 MCP Server 执行,Read recommend.md 后按以下流程处理:
- 运行
{baseDir}/scripts/setup.sh --check-only检查环境 - 若未配置,直接运行
{baseDir}/scripts/setup.sh --setup自动完成安装(内置默认地址,无需询问用户) - 环境就绪后,使用
mcporter call cmg-recommend.\x3Ctool>调用推荐工具
🚨🚨🚨 绝对红线:价格数据必须来自真实查询 🚨🚨🚨
本 Skill 涉及的所有价格数据都将直接用于商业决策和客户报价。 虚假价格将导致严重的商业损失和信誉损害,后果不可挽回。
❌ 绝对禁止
- 绝对禁止自行估算、推算、编造任何价格数据 — 不管你对价格有多"自信",你的知识已经过时,云厂商价格随时在变
- 绝对禁止使用"根据经验估计"、"大约"、"通常价格"等模糊说法代替真实询价 — 没有真实数据就明确告知用户
- 绝对禁止基于历史知识推断当前价格 — 你的训练数据中的价格信息已经过时,不具备参考价值
- 绝对禁止在无法调用 API 或访问价格计算器时自行补充价格 — 应该报错并告知用户原因
✅ 必须遵守
- 所有价格必须通过以下渠道之一获取:
- 调用
{baseDir}/scripts/tco_pricing.py脚本通过云厂商 API 获取真实报价 - 通过浏览器访问云厂商官方价格计算器页面读取真实报价
- 调用
- 如果 API 调用失败或浏览器无法访问,必须明确告知用户获取价格失败,说明失败原因,并请用户协助解决 — 绝不能"补一个估算值凑合"
- 每条价格记录必须包含
price_source字段,标明数据来源(如"阿里云 DescribePrice API"、"腾讯云 InquiryPriceRunInstances API"、"阿里云价格计算器网页") - 生成报告前必须确认所有 pricing_items 的价格均来自真实查询
安全使用建议
Before installing or running this skill: 1) Treat the default MCP server (http://61.151.231.241) and the COS download host as untrusted until you verify their operators — do not allow automatic --setup to use the default server; specify a vetted internal/official MCP Server or skip that step. 2) Inspect the mcporter npm package source and the precompiled scanner binaries (verify checksums/signatures) before installing/executing. 3) Understand what data will be sent to the remote MCP Server (resource IDs, config, pricing queries) and avoid sending credentials to unknown endpoints. 4) Run scanner binaries and any installation steps in an isolated environment (VM/container) if you must test. 5) If you provide cloud credentials for scanning/pricing, use least-privilege keys, prefer read-only scopes, and rotate keys after use. 6) Ask the publisher/operator for provenance (who runs 61.151.231.241 and the COS bucket), checksums for binaries, and an option to run recommendation logic entirely locally — getting those answers would increase confidence.
功能分析
Type: OpenClaw Skill
Name: cmg
Version: 1.0.0
The skill bundle facilitates cloud migration but exhibits several high-risk behaviors, including the handling of sensitive cloud credentials (AK/SK) in `scripts/tco_pricing.py` and instructions for the agent to download and execute external binaries from a remote COS bucket in `references/scan.md`. Furthermore, `scripts/setup.sh` hardcodes a specific IP address (61.151.231.241) for an MCP server and `references/recommend.md` explicitly instructs the agent to perform global system modifications (e.g., `npm install -g mcporter`) without seeking user confirmation. While these capabilities are functionally consistent with the stated purpose of cloud resource assessment and migration, the combination of credential processing, automated remote dependency fetching, and hardcoded backend communication warrants a cautious classification.
能力评估
Purpose & Capability
Functionality (scan → recommend → TCO) aligns with the name/description. Requiring cloud account credentials for scanning/pricing is expected. However the skill auto-configures a remote MCP server (mcporter) using a hard-coded default address (http://61.151.231.241) and directs downloads from a COS URL (msp-release-1258344699.cos.ap-shanghai.myqcloud.com). Those external endpoints are not documented in the description/homepage and feel disproportionate unless the operator of those hosts is trusted by the user.
Instruction Scope
SKILL.md and scripts instruct the agent/user to: download and run precompiled scanners from a COS bucket, run tco_pricing.py which accepts AK/SK and will call cloud provider APIs, and install/configure mcporter to point to an external MCP Server. The setup flow auto-uses the default server URL without prompting. The recommendation flow sends resource/specification data to the remote MCP Server (via mcporter), which can include sensitive inventory — this is beyond the skill description's explicit scope and could leak data if the remote endpoint is untrusted.
Install Mechanism
No formal install spec in registry, but runtime instructions perform network installs: npm -g mcporter and downloading precompiled scanner binaries from a Tencent COS bucket URL. Installing a global npm package and executing opaque binaries from a cloud object store are moderate-to-high risk unless you verify package/binary provenance and integrity (checksums/signing). The MCP server default is a raw IP (61.151.231.241), which is a red flag for an unvetted remote endpoint.
Credentials
The skill legitimately needs cloud credentials/keys to scan provider APIs and to run pricing queries; scripts and docs instruct the user to provide SecretId/SecretKey or AK/SK. The registry metadata declares no required env vars, so credentials are provided at runtime (config.yaml / CLI args). This is proportionate for the function, but the instructions also configure a remote MCP server that will receive resource/spec data — you should confirm whether any credentials or sensitive inventory are ever forwarded to that remote server.
Persistence & Privilege
The skill does not request always:true. It will install mcporter globally (npm) and write mcporter config to ~/.mcporter/mcporter.json (persisting a remote server entry). Writing this tool-specific config and installing a global binary are expected for mcporter-based integration, but the script's automatic configuration (without prompting) and default remote server are concerning because they create a persistent connection to an external service.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install cmg - 安装完成后,直接呼叫该 Skill 的名称或使用
/cmg触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of the tencent-cloud-migration skill, providing full-process cloud migration capabilities for Tencent Cloud.
- Supports resource scan (cmg-scan) for Alibaba Cloud, AWS, Huawei Cloud, and GCP, with Excel export.
- Enables product recommendation (cmg-recommend), mapping scanned resources to Tencent Cloud equivalents.
- Offers TCO/cost analysis (cmg-tco) with a strict requirement to use only real-time pricing from official APIs or calculators—no price estimation allowed.
- Guides users in selecting the proper Tencent Cloud migration tools per resource type (cmg-migrate).
- Includes clear workflow and documentation references for each migration stage.
元数据
常见问题
云迁移CMG 是什么?
腾讯云迁移平台(CMG/MSP)全流程能力。触发词:资源扫描、扫描阿里云/AWS/华为云/GCP资源、生成云资源清单、选型推荐、对标腾讯云、推荐规格、帮我推荐、给我推荐、ECS对应什么腾讯云产品、成本分析、TCO、迁移报价、询价、价格计算器、cmg-scan、cmg-recommend、cmg-tco. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 90 次。
如何安装 云迁移CMG?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cmg」即可一键安装,无需额外配置。
云迁移CMG 是免费的吗?
是的,云迁移CMG 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
云迁移CMG 支持哪些平台?
云迁移CMG 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 云迁移CMG?
由 AutoClaw(@llm-pm)开发并维护,当前版本 v1.0.0。
推荐 Skills