Cloudbase Miniprogram logo

Cloudbase Miniprogram

OrganizationPopular
TencentCloudBase
cloudbase-miniprogram

Use when building a WeChat Mini Program (微信小程序 / 小程序) with a real backend on 腾讯云开发 CloudBase — from an idea to a published release. Triggers on: 小程序, 微信小程序, wx.cloud, 云开发, 云函数, 数据库, 集合, 云存储, 上传图片, 登录, openid, 订阅消息, 支付, 体验版, 预览, 上传代码, 提交审核, 发布, 合法域名, 真机调试, 分包. Covers project scaffolding, project.config.json / appid / miniprogramRoot, the wx.cloud data path, cloud functions, storage, auth, subscription messages, and the preview → upload → review → release chain. Do NOT use for Web/H5 frontends (use a web skill), pure backend services, or mini programs that do not use CloudBase.

Overview

PublisherTencentCloudBase
RepositoryCloudBase-AI-Toolkit
Skill namecloudbase-miniprogram
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 Miniprogram 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-miniprogram
  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-miniprogram .claude/skills/cloudbase-miniprogram
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cloudbase Miniprogram 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 Miniprogram 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 Miniprogram 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.

CloudBase 全栈小程序开发

一个小程序要真正跑起来,缺的从来不是页面,是后端那一半:数据存哪、登录怎么做、图片传到哪、消息怎么发、审核怎么过。这个技能按「从想法到上架」的顺序组织,每一步告诉你调哪个工具、去哪取细节。

配方正文不打包,用 CloudBase MCP 的知识库按需检索(见文末)。这样内容永远跟线上最新版一致。

第 0 步:先问清三件事,别急着写代码

要确认为什么
小程序 appid 与主体类型个人 / 个体工商户 / 企业主体决定能用哪些能力(支付、部分类目)。测试号不支持云开发
后端是否用 云开发(CloudBase)不用云开发就走另一条路,本技能不适用
云开发环境是国内站还是国际站两套账号体系互不相通,选错的表现是「登录了但环境列表空」

还有一个高频坑:DevTools 里「云开发」入口是灰的,或者看不到环境——先诊断,不要当成工具 bug。常见原因就是上表第三条(主体不支持 / 绑定账号不一致 / 站点错)。诊断路径:searchKnowledgeBase({ mode: "skill", skillName: "miniprogram-development" }) 的 Common Pitfalls 一节。

第 1 步:接上 CloudBase MCP

技能包不能携带 MCP 配置,这一步必须显式做。三条路径按客户端能力选:

bash
# A. 能跑命令的客户端
claude mcp add --transport http cloudbase https://tcb-api.cloud.tencent.com/mcp/v1

# B. 本地 stdio(需要 API Key,或要用远程缺的工具)
claude mcp add cloudbase -- npx -y @cloudbase/cloudbase-mcp@latest

# C. 客户端不支持 MCP 但有终端(走 mcporter 桥)
npx -y mcporter@0.16.1 call --stdio "npx -y @cloudbase/cloudbase-mcp@latest" auth action=status

图形客户端(Cursor、Qoder)只能让用户手动加:类型 HTTP / Streamable HTTP,地址填 /mcp/v1。

验证:调 auth action=status,返回 auth_status: READY 且带 current_env_id 就通了。

第 2 步:先跑通一个最小闭环,再谈功能

顺序固定,不要跳:

  1. 建环境并绑定:manageEnv(查/建)→ auth(action="set_env", envId=...) 绑定。
  2. 建一个集合:writeNoSqlDatabaseStructure。
  3. 写一条数据:writeNoSqlDatabaseContent。
  4. 写一个云函数并部署:manageFunctions,创建后在 DevTools 里「上传并部署:云端安装依赖」;用 MCP 的 queryFunctions / queryLogs 验证调用与日志。
  5. 小程序端读这条数据:wx.cloud.init({ env }) → wx.cloud.database().collection(...).get()。

这五步通了,说明环境、权限、网络都对了;后面加页面只是重复。

第 3 步:按任务路由

要做的事首选工具 / 技能
项目脚手架、project.config.json、miniprogramRoot、tabBarsearchKnowledgeBase → miniprogram-development
数据库集合、索引、权限规则writeNoSqlDatabaseStructure / manageDataModel
增删改查(小程序端 / 云函数端)writeNoSqlDatabaseContent / readNoSqlDatabaseContent + skill cloudbase-document-database-in-wechat-miniprogram
云函数(含 scf_bootstrap、定时触发)manageFunctions + skill cloud-functions
图片/文件上传manageStorage + skill cloud-storage-web
登录、openid、用户体系skill auth-wechat-miniprogram(先在控制台配登录方式)
订阅消息 / 客服消息skill miniprogram-development 的消息推送一节
预览、上传代码、提交审核miniprogram-ci,或 DevTools Nightly 的 wechatide CLI
页面长得不好看skill ui-design
上线后出问题queryLogs / skill ops-inspector

第 4 步:发布链

体验版 → 上传代码 → 提交审核 → 发布。三步都有各自的坑:

  • 预览/上传优先用 miniprogram-ci(走密钥,可自动化);想用 wechatide CLI 需要 Nightly 版 DevTools,没装就如实说「这是缺工具,不是环境限制」,等用户决定。
  • 合法域名:小程序端只能请求已备案并配置的域名;走 wx.cloud 不受这个限制——这也是云开发省事的地方。
  • 审核驳回最常见三类:类目与实际功能不符、有诱导分享、收集了不该收集的用户信息。这些只能提前避,工具帮不上。

细节从哪来

不要凭记忆写配置项和小程序 API 参数,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>" })
官方文档段落searchKnowledgeBase({ mode: "docs", action: "searchDocs", input: "订阅消息" }),再 action: "readDoc" + docPath 取全文
某个云 API 的参数searchKnowledgeBase({ mode: "openapi", apiName: "<api>" })

可查的相关技能:miniprogram-development、cloudbase-document-database-in-wechat-miniprogram、auth-wechat-miniprogram、cloud-functions、cloud-storage-web、ui-design、ops-inspector、cloudbase-wechat-integration、spec-workflow。

四条红线

  1. 先确认主体与站点,再动环境。测试号 / 个人主体不支持的能力,硬做只会白费。
  2. 不要把密钥、AppSecret 写进小程序端代码——小程序包是可以被反编译的。
  3. 改数据库权限规则、删集合、删云函数前说清后果。
  4. 审核相关的事(类目、诱导分享、用户信息)先讲规则再动手,别等驳回才改。

常见失败对照

现象多半是
DevTools 里云开发入口是灰的测试号 / 主体不支持,或绑定账号不一致
登录成功但环境列表空站点选错(国内 / 国际)
wx.cloud 调用报环境不存在没 wx.cloud.init,或 envId 写错
云函数本地跑通、线上 500依赖没装(「云端安装依赖」),或 scf_bootstrap 缺
图片上传成功但打不开存储权限规则没放行读

Frequently asked questions

What does the Cloudbase Miniprogram AI skill do?

Use when building a WeChat Mini Program (微信小程序 / 小程序) with a real backend on 腾讯云开发 CloudBase — from an idea to a published release. Triggers on: 小程序, 微信小程序, wx.cloud, 云开发, 云函数, 数据库, 集合, 云存储, 上传图片, 登录, openid, 订阅消息, 支付, 体验版, 预览, 上传代码, 提交审核, 发布, 合法域名, 真机调试, 分包. Covers project scaffolding, project.config.json / appid / miniprogramRoot, the wx.cloud data path, cloud functions, storage, auth, subscription messages, and the preview → upload → review → release chain. Do NOT use for Web/H5 frontends (use a web skill), pure backend services, or mini programs that do not use CloudBase.

Why use Cloudbase Miniprogram on TypingMind?

Because you install it once and use it with any model. Cloudbase Miniprogram 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 Miniprogram 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-miniprogram. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cloudbase Miniprogram?

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 Miniprogram?

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

Is the Cloudbase Miniprogram 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 👇