Miniprogram Development logo

Miniprogram Development

OrganizationPopular
TencentCloudBase
miniprogram-development

WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects (小程序开发、调试、预览、发布). Covers project structure and config (`project.config.json`, `appid`, `miniprogramRoot`, `tabBar`, routing/navigation, icon assets), WeChat Developer Tools Nightly workflows (`wechatide` CLI, WeChat IDE Skills/MCP), `miniprogram-ci` preview/upload, console/network debugging, message push (消息推送) and customer-service auto-reply (客服消息), mini program SEO / search indexing (小程序搜索优化、页面收录、搜索推广、mpcrawler), and CloudBase integration (`wx.cloud`, 腾讯云开发, 云开发) when explicitly used. Use when users create, develop, modify, debug, preview, deploy, publish, or promote WeChat Mini Programs. NOT for Web frontend (use web-development), pure backend services (use cloudrun-development / cloud-functions), or UI-design-only tasks (use ui-design).

Overview

PublisherTencentCloudBase
RepositoryCloudBase-AI-Toolkit
Skill nameminiprogram-development
Stars
1.1K
Forks
141
Bundled files
6
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.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Miniprogram Development 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.
  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/config/source/skills/miniprogram-development .claude/skills/miniprogram-development
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Miniprogram Development 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 Miniprogram Development 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 Miniprogram Development 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.

Sibling skills (local only)

Sibling CloudBase skills ship beside this skill. Use local relative paths such as ../auth-tool-cloudbase/SKILL.md.

If a referenced sibling skill file is missing from this environment, ask the user to install the full CloudBase plugin (or the missing skill). Do not HTTP-fetch remote skill or protocol markdown into the agent context.

Cross-cutting protocols (required before code changes or deployments):

  • Change Safety Protocol: ../cloudbase-platform/references/protocols/change-safety-protocol.md
  • Deployment Gate: ../cloudbase-platform/references/protocols/deployment-gate.md

Post-deployment (optional, non-intrusive): after a mini program upload/publish is verified successful, you may offer at most once to generate anonymized shareables (visual card + paste-ready copy) — see ../cloudbase-platform/references/protocols/deployment-share.md for trigger boundaries, required information, anonymization red lines, and deliverable formats. Never follow up if declined; never publish on the user's behalf.

Activation Contract

Use this first when

  • The request is about WeChat Mini Program structure, pages, preview, publishing, or CloudBase mini program integration.

Read before writing code if

  • The user mentions wx.cloud, CloudBase mini programs, OPENID, mini program deployment/debug workflows, Nightly DevTools, wechatide, or WeChat IDE Skills.
  • The user mentions message push (消息推送), customer-service auto-reply (客服消息/自动回复), or binding MsgType/Event callbacks to cloud functions.

Then also read

  • CloudBase auth -> ../auth-wechat-miniprogram/SKILL.md
  • CloudBase document DB -> ../cloudbase-document-database-in-wechat-miniprogram/SKILL.md
  • Mini Program WeChat Pay, 虚拟支付 (virtual payment, wx.requestVirtualPayment), or Integration Center generated payment functions -> ../cloudbase-wechat-integration/SKILL.md (official docs: https://docs.cloudbase.net/integration/wechat-pay-miniprogram.md)
  • UI generation -> ../ui-design/SKILL.md first

Do NOT use for

  • Web auth flows or Web SDK-specific frontend implementation.
  • WeChat Pay, 虚拟支付 / wx.requestVirtualPayment, payment callbacks, refunds, or Official Account OAuth details; use cloudbase-wechat-integration for those scenarios.

Common mistakes / gotchas

  • Generating a Web-style login flow for mini programs.
  • Mixing Web SDK assumptions into wx.cloud projects.
  • Applying CloudBase constraints before confirming the project actually uses CloudBase.
  • Assuming Stable WeChat Developer Tools includes Nightly Skills/wechatide (it may not).
  • Forcing CloudBase MCP Tencent Cloud login for daily mini program cloud ops when Nightly wechatide already works.
  • Inventing wechatide tool names or flags instead of using --help / Nightly tools.yaml.
  • Bypassing wxide CLI / IDE for message-push ops with low-level transport before cloud_*_msg_push is exposed (see message-push-customer-service.md).
  • Assuming cloud-function return values auto-reply to customer-service chats (must use cloud.openapi.customerServiceMessage.send).
  • Making code or configuration changes without first following the Change Safety Protocol (cloudbase-platform/references/protocols/change-safety-protocol.md).
  • Performing mini program upload/publish without first completing the checks in cloudbase-platform/references/protocols/deployment-gate.md.

When to use this skill

Use this skill for WeChat Mini Program development when you need to:

  • Build or modify mini program pages and components
  • Organize mini program project structure and configuration
  • Debug, preview, or publish mini program projects
  • Work with WeChat Developer Tools workflows
  • Handle mini program runtime behavior, assets, or page config files
  • Integrate CloudBase in a mini program project when explicitly needed

Do NOT use for:

  • Web frontend development (use web-development)
  • Pure backend service development (use cloudrun-development or cloud-functions as appropriate)
  • UI design-only tasks without mini program development context (use ui-design)

How to use this skill (for a coding agent)

  1. Start with the general mini program workflow

    • Treat WeChat Mini Program development as the default scope
    • Do not assume the project uses CloudBase unless the user or codebase indicates it
  2. Follow mini program project conventions

    • Keep mini program source under the configured mini program root
    • Ensure page files include the required configuration file such as index.json
    • Check project.config.json before suggesting preview or IDE workflows
  3. Route by scenario

    • If the task involves debugging, previewing, publishing, opening DevTools, console/network, or wechatide, read debug and preview reference first
    • If choosing between WeChat IDE Skills and CloudBase MCP, read WeChat IDE Skills vs CloudBase MCP
    • If the task involves CloudBase, wx.cloud, cloud functions, CloudBase database/storage, or CloudBase identity handling, read CloudBase integration reference
    • If the task involves mini program SEO / WeChat search optimization / page indexing / search promotion (小程序搜索优化、页面收录、搜索推广、关键词排名), read Mini Program SEO & WeChat Search Optimization first
    • If the task involves message push (消息推送), customer-service auto-reply (客服消息自动回复), MsgType/Event → cloud function binding, or push-related function logs, read Message Push & Customer Service Auto-Reply first
    • If the task involves tabBar, icon assets, or label spacing, prefer the text-only custom tabBar default below unless the user explicitly requires icons
  4. Use CloudBase rules only when applicable

    • CloudBase / 微信云开发 is an important mini program integration path, but not a universal requirement
    • Only apply CloudBase-specific auth, database, storage, or cloud function constraints when the project is using CloudBase
  5. Recommend the right preview/debug/cloud-ops path


WeChat Mini Program Development Rules

General Project Rules

  1. Project Structure

    • Mini program code should follow the project root configured in project.config.json
    • Keep page-level files complete, including .json configuration files
    • Ensure referenced local assets actually exist to avoid compile failures
  2. Configuration Checks

    • Check project.config.json before opening, previewing, or publishing a project
    • Confirm appid is available when a real preview, upload, or WeChat Developer Tools workflow is required
    • Confirm miniprogramRoot and related path settings are correct
  3. Resource Handling

    • For tabBar, prefer a text-only custom tabBar by default when the user does not explicitly need icons. This avoids icon asset handling, removes reserved icon space, and makes the label area easier to align.
    • Only generate local icon assets and configure iconPath / selectedIconPath when the user explicitly asks for tab icons or the design requires them.
    • When generating local asset references such as icons, ensure the files are downloaded into the project.
    • Keep file paths stable and consistent with mini program config files.

Recommended default for simple tabBar

Use tabBar.custom = true, keep only pagePath and text in app.json, and render text-only items in the custom component so there is no icon slot and no extra blank area above the label.

app.json

json
{
  "tabBar": {
    "custom": true,
    "list": [
      { "pagePath": "pages/index/index", "text": "首页" },
      { "pagePath": "pages/travel/travel", "text": "行程" },
      { "pagePath": "pages/my/my", "text": "我的" }
    ]
  }
}

Keep the custom tabBar layout text-only, and use flex centering or matching height and line-height to remove the blank area above the label. Switch to downloaded local icons only when the user explicitly wants icon-based tabs.

CloudBase as a Mini Program Sub-Scenario

  • If the user explicitly uses CloudBase, wx.cloud, Tencent CloudBase, 腾讯云开发, or 云开发, follow the CloudBase integration reference
  • In CloudBase mini program projects, use wx.cloud APIs and CloudBase environment configuration appropriately
  • Do not apply CloudBase-specific rules to non-CloudBase mini program projects

Debugging, Preview, and Publishing

  • Prefer Nightly DevTools + wechatide for open project, compile, simulator, console/network debug, preview, upload, and daily cloud ops (WeChat login — no separate Tencent Cloud login)
  • Always pass required context: -c <clientName>, absolute --project, valid appid, and cloud env when needed
  • If Nightly / wechatide is not available, use miniprogram-ci as the fallback for preview/upload/npm, and CloudBase MCP for cloud resources; tell the user to install Nightly for full Skills/MCP
  • For detailed workflows, read debug and preview reference and WeChat IDE Skills vs CloudBase MCP

Message Push & Customer Service Auto-Reply

微信生态专章:消息推送 / 客服自动回复细节以中文 reference 为准(术语保留英文 API 名)。

  • Current only ops path: WeChat Developer Tools IDE + wxide CLI. Do not teach low-level bypasses while cloud_query_msg_push / cloud_manage_msg_push are not yet exposed (pending WeChat IDE CLI support).
  • Deploy receiver functions with cloud_fn_deploy and --remote-npm-install; bind (MsgType, Event) → one cloud function in the IDE message-push panel until CLI tools land.
  • Customer-service auto-reply requires cloud.openapi.customerServiceMessage.send plus config.json openapi permissions — function return values alone do not reply.
  • Function logs: IDE 云开发控制台 → 云函数 → 日志; the wxide CLI does not expose log query yet — do not teach low-level log CGI bypasses.
  • Full reference: Message Push & Customer Service Auto-Reply

Minimal project skeleton

app.js

js
App({
  onLaunch() {
    console.log("Mini Program launched");
  },
});

pages/index/index.js

js
Page({
  data: {
    message: "Hello CloudBase Mini Program",
  },
});

pages/index/index.wxml

xml
<view class="page">
  <text>{{message}}</text>
</view>

pages/index/index.json

json
{
  "navigationBarTitleText": "Home"
}

project.config.json

json
{
  "appid": "your-mini-program-appid",
  "projectname": "cloudbase-mini-program",
  "miniprogramRoot": "./",
  "compileType": "miniprogram"
}

References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Miniprogram Development AI skill do?

WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects (小程序开发、调试、预览、发布). Covers project structure and config (`project.config.json`, `appid`, `miniprogramRoot`, `tabBar`, routing/navigation, icon assets), WeChat Developer Tools Nightly workflows (`wechatide` CLI, WeChat IDE Skills/MCP), `miniprogram-ci` preview/upload, console/network debugging, message push (消息推送) and customer-service auto-reply (客服消息), mini program SEO / search indexing (小程序搜索优化、页面收录、搜索推广、mpcrawler), and CloudBase integration (`wx.cloud`, 腾讯云开发,...

Why use Miniprogram Development on TypingMind?

Because you install it once and use it with any model. Miniprogram Development 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 Miniprogram Development in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TencentCloudBase/CloudBase-AI-Toolkit/tree/main/config/source/skills/miniprogram-development. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Miniprogram Development?

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 Miniprogram Development?

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

Is the Miniprogram Development 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 👇