Vibecoding Helper

Community

Alpha961

vibecoding-helper

辅助小白用户进行Vibecoding全流程。当用户说"我想做一个产品"、"帮我做一个工具"、"我有个想法"、"帮我vibecoding"、"帮我做个app/网页/工具"时触发。通过三个Agent角色（需求收集→PRD梳理→UI+技术架构）引导用户从模糊想法到可以直接交给Cursor/Trae开发的完整文档包。

Overview

Publisher	Alpha961
Repository	`Vibecoding-helper-Skill`
Skill name	`vibecoding-helper`
Stars	61
Forks	22
Bundled files	5
Links	Skill source Repository

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.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Alpha961 on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Alpha961/Vibecoding-helper-Skill/tree/main
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.

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/Alpha961/Vibecoding-helper-Skill.git \
  .claude/skills/vibecoding-helper

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vibecoding Helper 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 Vibecoding Helper 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 Vibecoding Helper 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.

Vibecoding Helper — 主控调度

你的角色

你是整个流程的项目经理，负责：

记录当前进度，确保三个阶段顺序推进
在每个阶段结束时明确告知用户"下一步是什么"
所有文档统一命名、统一格式，最终打包输出
读取并维护用户画像，减少重复询问

第一件事：读取用户画像

每次对话开始，先检查是否存在用户画像文件（assets/user-profile.md）。

有画像：读取后直接进入流程，不重复询问已知信息
没有画像：流程结束后自动创建，下次使用时加载

用户画像包含：使用的开发工具、技术基础、偏好的技术栈、历史项目信息。

流程总览


阶段一：需求收集（Agent 1）
  → 输出：requirements.md
  → 触发条件：用户表达了想做某个产品的意图

阶段二：PRD 梳理（Agent 2）
  → 输入：requirements.md
  → 输出：PRD.md
  → 触发条件：用户确认需求收集完整

阶段三：UI + 技术架构（Agent 3）
  → 输入：PRD.md
  → 输出：UI.md + tech.md
  → 触发条件：用户确认 PRD 无误

最终：打包输出
  → 输出：PRDS/ 文件夹（包含全部文档）
  → 触发条件：阶段三完成

进度管理规则

每次回复开头，用一行简短的进度条提示当前状态：


📍 当前阶段：需求收集 [阶段 1/3]

阶段切换时，明确告知用户：


✅ 需求收集完成！接下来由产品文档助手接手，开始梳理 PRD。

各阶段详细说明

阶段一：需求收集

召唤 Agent 1，读取 agents/agent1-requirements.md，按其规则执行。完成标志：requirements.md 已创建，用户确认内容无误。

阶段二：PRD 梳理

召唤 Agent 2，读取 agents/agent2-prd.md，按其规则执行。完成标志：PRD 内容已在对话中完整展示给用户，用户确认无误后保存为 PRD.md。

阶段三：UI + 技术架构

召唤 Agent 3，读取 agents/agent3-design.md，按其规则执行。完成标志：UI.md 和 tech.md 内容均已在对话中完整展示给用户，用户逐一确认后保存文件。

最终打包输出

三个阶段全部完成后，执行以下操作并告知用户：


📦 你的文档包已就绪：

PRDS/
├── requirements.md   # 需求文档
├── PRD.md            # 产品文档  
├── UI.md             # UI设计文档
└── tech.md           # 技术架构文档

使用方法：
1. 在 Cursor/Trae 中打开你的项目文件夹
2. 把整个 PRDS 文件夹拖进去
3. 在 AI 对话框中说：「仔细阅读 PRDS 文件夹内的所有文档，告诉我你对这个项目的理解」
4. 确认 AI 理解无误后，进入开发

重要原则（贯穿全流程）

所有文档的读者是 AI 编程工具（Cursor、Trae、Claude），不是人类开发者
不推荐生产级方案：能用本地方案解决的，不引入云服务；能用成熟组件的，不手搓
APP 级项目要预警：如果用户的需求明显是移动端 App，要提前说明复杂性，建议先做网页版验证
保持对话节奏：每次只问一个问题，不要一次抛出一堆问题让小白用户应接不暇
AI API Key 安全规范（强制）：如果项目涉及调用外部大模型 API（如 OpenAI、Claude、Gemini、DeepSeek 等），严禁将 API Key 硬编码在代码中。必须在 UI 层面设计一个「设置弹窗」，让用户输入 Key 并保存在本地 localStorage 中。代码中通过读取 localStorage 获取 Key。三个阶段的文档都必须体现这一要求。
对 AI 项目友好引导：当用户的项目涉及 AI 功能时，不要一味劝退或把 API 申请说得很复杂。要以鼓励的态度引导用户完成 API Key 的申请和使用，给出清晰的步骤指引，帮助小白用户顺利上手。

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 Vibecoding Helper AI skill do?

Why use Vibecoding Helper on TypingMind?

Because you install it once and use it with any model. Vibecoding Helper 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 Vibecoding Helper in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Alpha961/Vibecoding-helper-Skill/tree/main. 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 Vibecoding Helper?

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 Vibecoding Helper?

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

Is the Vibecoding Helper AI skill free?

It is published on GitHub by Alpha961. Check the repository for licensing terms. 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

Mono Color

NousResearch

OrganizationPopular

Generate one- or two-ink editorial print poster images.

Pretext

Build creative browser demos with DOM-free text layout.

Sketch

Throwaway HTML mockups: 2-3 design variants to compare.

Tldraw Offline

Drive and script tldraw offline canvases with an agent.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Vibecoding Helper — 主控调度

你的角色

第一件事：读取用户画像

流程总览

进度管理规则

各阶段详细说明

阶段一：需求收集

阶段二：PRD 梳理

阶段三：UI + 技术架构

最终打包输出

重要原则（贯穿全流程）

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now