Cloudbase logo

Cloudbase

OrganizationPopular
TencentCloudBase
cloudbase

Use when the user builds, deploys, debugs, or troubleshoots anything on 腾讯云开发 CloudBase / 云开发 / TCB / 微信云开发 — Web, 微信小程序, uni-app, 原生 App. Triggers on: 建站, 页面, 表单, 后台, 原型, 登录, 注册, 鉴权, 数据库, 集合, 建表, 云函数, 云托管, 云存储, 静态托管, 上传, 部署, 上线, 域名, 日志, 报错, 巡检, 大模型, AI 对话, 流式输出, 智能体, 小程序. This is an entry skill: it routes the task to the right CloudBase MCP tool and then pulls the detailed recipe from the CloudBase MCP knowledge base. Do NOT use for non-CloudBase stacks or self-hosted backends.

Overview

PublisherTencentCloudBase
RepositoryCloudBase-AI-Toolkit
Skill namecloudbase
Stars
1.2K
Forks
148
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by TencentCloudBase on GitHub. Read the source before you install it.

Installation

Install the Cloudbase AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/TencentCloudBase/CloudBase-AI-Toolkit/tree/main/connectors/cloudbase/qianwen/entry/cloudbase
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-Toolkit.git /tmp/CloudBase-AI-Toolkit
mkdir -p .claude/skills
cp -r /tmp/CloudBase-AI-Toolkit/connectors/cloudbase/qianwen/entry/cloudbase .claude/skills/cloudbase
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cloudbase in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cloudbase on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cloudbase is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

腾讯云 CloudBase(云开发)入口技能

这个技能只做三件事:确认站点、把任务路由到对的工具、告诉你细节去哪取。配方正文不放在包里,连上 CloudBase MCP 后用知识库检索拿(见「细节从哪来」)。

CloudBase 是给开发者的后端云:数据库(NoSQL 文档库 / PostgreSQL)、云函数、云托管(容器)、云存储、静态托管、身份认证、内置大模型,以及把这些串起来的 CLI 与控制台。

第一步:先确认站点,别猜

CloudBase 有两套互不相通的账号体系。站点弄错的表现不是报错,而是「登录了但看不到环境」。能推断就推断(控制台域名、envId、已有报错),推不出来就问一次。

国内站国际站
远程 MCPhttps://tcb-api.cloud.tencent.com/mcp/v1https://tcb-api.tencentcloud.com/mcp/v1
本地 stdio默认即国内TCB_SITE=intl + TCB_REGION=ap-singapore
CLI默认TCB_IS_INTL=true
控制台tcb.cloud.tencent.comtcb.tencentcloud.com
默认地域ap-shanghaiap-singapore
NoSQL 文档库有没有

第二步:接上 CloudBase MCP

技能包里不能携带 MCP 配置。 技能市场把两件事分开:Skill 给「怎么做」,MCP 给「用什么工具」,ZIP 规范里只有 SKILL.md(可带脚本和参考资料),没有声明 MCP 的字段。所以这一步必须显式做,做完再谈调用。

先确认站点(见上表),再按客户端能力选一条:

A. 客户端能执行命令(Claude Code 等)

bash
# 远程,推荐
claude mcp add --transport http cloudbase https://tcb-api.cloud.tencent.com/mcp/v1

国际站把域名换成 tcb-api.tencentcloud.com。

B. 手动加(Cursor、Qoder 这类图形客户端)

Agent 改不了这类客户端的配置,把参数给用户:

  • 远程:设置 → MCP → 新增 → 类型 HTTP / Streamable HTTP → 地址填上面的 /mcp/v1
  • 本地:类型 stdio → 命令 npx → 参数 -y @cloudbase/cloudbase-mcp@latest

C. 客户端不支持 MCP,但有终端(兜底,实测可用)

用 mcporter 当桥,不需要客户端理解 MCP:

bash
# 列工具(42 个)
npx -y mcporter@0.16.1 list --stdio "npx -y @cloudbase/cloudbase-mcp@latest"

# 调工具
npx -y mcporter@0.16.1 call --stdio "npx -y @cloudbase/cloudbase-mcp@latest" auth action=status

注意:mcporter 走远程地址会失败(它先用 SSE GET 探测,CloudBase 的 /mcp/v1 只收 POST,报 SSE error: Non-200 status code (405)),所以这条只走 stdio。

验证连上没有:调一次 queryEnv(或上面的 auth action=status)。能返回环境信息就是通了;提示未登录就按提示在浏览器里授权。

第三步:任务 → 工具

要做的事首选工具
看有哪些环境、环境详情queryEnv / manageEnv
设计数据模型、建集合writeNoSqlDatabaseStructure / manageDataModel
读写文档数据writeNoSqlDatabaseContent / readNoSqlDatabaseContent
PostgreSQL 建表、查询managePgDatabase / queryPgDatabase
创建、更新、部署云函数manageFunctions / queryFunctions
查函数日志、排错queryLogs / manageLogs
静态托管上传、域名manageHosting / queryHosting
云托管(容器)manageCloudRun / queryCloudRun
对象存储manageStorage / queryStorage
登录与权限manageAppAuth / queryAppAuth
从模板起项目downloadTemplate
声明式部署deployPlan → deployBuild → deployApply
查官方文档 / 技能配方searchKnowledgeBase

远程 MCP 缺几个工具:manageStorage 的本地文件读写、downloadTemplate、声明式部署三件套,以及 manageHosting 的上传。需要这些时改用本地 stdio。

细节从哪来(关键)

不要凭记忆写 CloudBase 的配置和命令。先查,再写:

想要什么怎么取
某个技能的完整配方searchKnowledgeBase({ mode: "skill", skillName: "<技能名>" })
官方文档某一段searchKnowledgeBase({ mode: "docs", action: "searchDocs", input: "关键词" }),再用 action: "readDoc" + docPath 取全文
某个 OpenAPI 的参数searchKnowledgeBase({ mode: "openapi", apiName: "<api>" })

可检索的技能(31 个):

  • Web / 小程序 / 原生:web-development、miniprogram-development、http-api-cloudbase、ui-design、minimal-web-baas-demo
  • 数据:postgresql-development-cloudbase、postgresql-best-practices-cloudbase、cloudbase-document-database-web-sdk、cloudbase-document-database-in-wechat-miniprogram、relational-database-mcp-cloudbase、relational-database-web-cloudbase
  • 计算与部署:cloud-functions、cloudrun-development、cloudbase-declarative-deploy、cloudbase-cli、cloud-storage-web
  • 身份:auth-tool-cloudbase、auth-web-cloudbase、auth-nodejs-cloudbase、auth-wechat-miniprogram
  • AI:ai-model-web、ai-model-nodejs、ai-model-wechat、cloudbase-agent
  • 运维与方法:ops-inspector、cloud-api-operations、cloudbase-mcp、cloudbase-code-review、cloudbase-platform、cloudbase-wechat-integration、spec-workflow

没有 MCP 时的兜底:让用户在 WorkBuddy、豆包、Kimi、MiniMax 等客户端里装「腾讯云 CloudBase」连接器(同一套能力),或者直接看 https://cloudbase.net 文档。不要凭空编工具名和配置项。

三条红线

  1. 先定站点再登录、再绑环境。两站的环境、密钥、登录态互不相通。
  2. 新的关系型数据库一律用 PostgreSQL。环境里已经有 MySQL 时才走 MySQL 那条,不要主动建议开通 MySQL。
  3. 删除数据、改安全规则、改权限、改配额之前先说清后果再动手。

常见失败对照

现象多半是
登录成功但环境列表为空站点选错(国内/国际)
工具列表里没有某个工具用的是远程 MCP,缺的工具改本地 stdio
云函数部署后 404触发方式选错(事件型 vs HTTP),或 scf_bootstrap 没配
前端直连数据库读不到安全规则没放行,或没走登录态

Frequently asked questions

What does the Cloudbase AI skill do?

Use when the user builds, deploys, debugs, or troubleshoots anything on 腾讯云开发 CloudBase / 云开发 / TCB / 微信云开发 — Web, 微信小程序, uni-app, 原生 App. Triggers on: 建站, 页面, 表单, 后台, 原型, 登录, 注册, 鉴权, 数据库, 集合, 建表, 云函数, 云托管, 云存储, 静态托管, 上传, 部署, 上线, 域名, 日志, 报错, 巡检, 大模型, AI 对话, 流式输出, 智能体, 小程序. This is an entry skill: it routes the task to the right CloudBase MCP tool and then pulls the detailed recipe from the CloudBase MCP knowledge base. Do NOT use for non-CloudBase stacks or self-hosted backends.

Why use Cloudbase on TypingMind?

Because you install it once and use it with any model. Cloudbase is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cloudbase in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TencentCloudBase/CloudBase-AI-Toolkit/tree/main/connectors/cloudbase/qianwen/entry/cloudbase. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cloudbase?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cloudbase?

As many as you like. As long as a model supports skills, you can use Cloudbase with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cloudbase AI skill free?

Yes. It is published on GitHub by TencentCloudBase under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇