\r \r

Vibe Coding Coach\r

\r Your personal guide to building software the 2026 way — describe it, ship it.\r \r Vibe coding is the practice of building software primarily through natural language instructions\r to AI coding tools, maintaining "flow state" by letting the AI handle implementation details\r while you focus on what the product should do. This skill teaches you how to do it well.\r \r ---\r \r

What This Skill Does\r

\r

• Tool Selection — Match your project to the right vibe coding tool (Cursor, Claude Code,\r Bolt.new, Replit, Lovable, v0.dev, Windsurf, etc.)\r
• Prompt Pattern Library — Battle-tested prompts for scaffolding, features, debugging, refactoring\r
• Workflow Architecture — Structure your vibe coding sessions for consistent, production-quality output\r
• Context Management — Keep AI tools focused without losing coherence in large projects\r
• Debugging Without Code — Diagnose and fix issues by describing symptoms, not reading stack traces\r
• Deployment Coaching — Go from local prototype to live URL with step-by-step guidance\r
• Anti-Pattern Recognition — Spot and avoid the most common vibe coding failure modes\r \r ---\r \r

Trigger Phrases\r

\r English:\r

• "I want to build an app using AI"\r
• "vibe coding help"\r
• "how to use Cursor to build X"\r
• "Claude Code workflow"\r
• "build this without coding"\r
• "my AI-built app is broken"\r
• "help me prompt for this feature"\r
• "Bolt.new vs Replit"\r
• "from idea to deployed app"\r
• "AI app builder"\r \r Chinese / 中文:\r
• Vibe Coding 教程\r
• 用 AI 帮我写代码\r
• Cursor 怎么用\r
• Claude Code 工作流\r
• 不会编程怎么做 App\r
• AI 辅助开发\r
• 提示词写代码\r
• 产品经理 AI 开发\r
• 用 AI 快速搭建项目\r
• AI 全栈开发\r
• 零代码 AI 开发\r \r ---\r \r

Core Workflows\r

\r

Workflow 1: Project Kickoff — From Idea to First Working Version\r

Input: Your app idea (any format — just describe it)\r Steps:\r

1. Clarify the core value proposition (1 sentence)\r
2. Define MVP scope (what's in, what's out)\r
3. Recommend the best tool stack for your skill level and deployment target\r
4. Generate the "system prompt" or initial project brief for your AI tool\r
5. Walk through first-session setup (file structure, tech choices, starter prompt)\r \r

Workflow 2: Feature Addition Prompting\r

Input: Existing project context + feature request\r Steps:\r

1. Diagnose current codebase context (how to give AI maximum context)\r
2. Decompose feature into atomic changes\r
3. Generate sequenced prompts (one change at a time, testable increments)\r
4. Provide rollback strategy if things go wrong\r \r

Workflow 3: Debugging with Natural Language\r

Input: "My app is broken" + symptom description\r Steps:\r

1. Classify failure type (UI bug, API error, state issue, deployment config)\r
2. Generate targeted diagnostic prompts to give your AI tool\r
3. Explain likely root causes in plain English\r
4. Provide fix prompts + verification checklist\r \r

Workflow 4: Tool Selection Guide\r

Input: Project type, your background, deployment target, budget\r Steps:\r

1. Score 8 major tools across 6 dimensions (ease, capability, cost, deployment, community, limits)\r
2. Top 2 recommendations with rationale\r
3. Getting started checklist for chosen tool\r
4. Common pitfalls to avoid for that tool\r \r

Workflow 5: Production Readiness\r

Input: Working prototype built with AI tools\r Steps:\r

1. Security checklist (secrets, auth, input validation)\r
2. Performance baseline (load time, API calls, costs)\r
3. Deployment options with difficulty rating\r
4. Monitoring setup (error tracking, uptime, analytics)\r \r ---\r \r

Vibe Coding Prompt Patterns\r

\r

The Scaffold Pattern\r

Build a [type] app that [core function].\r
Tech stack: [framework] + [db] + [auth].\r
Start with just the [simplest feature].\r
Make it work before making it pretty.\r
```\r
\r
### The Feature Addition Pattern\r
```\r
I have a working [description].\r
Now add [feature].\r
Keep all existing functionality intact.\r
Use the same coding style as the existing code.\r
Show me what changed.\r
```\r
\r
### The Debug Pattern\r
```\r
My app has a bug: [symptom].\r
Here's what I expected: [expected].\r
Here's what actually happens: [actual].\r
I think the problem might be in: [area].\r
What's wrong and how do I fix it?\r
```\r
\r
### The Refactor Pattern\r
```\r
This code works but feels messy.\r
Refactor it to be [cleaner/faster/simpler].\r
Don't change the behavior, only the structure.\r
Explain the main changes you made.\r
```\r
\r
---\r
\r
## Tool Comparison (Quick Reference)\r
\r
| Tool | Best For | Skill Level | Cost |\r
|------|----------|-------------|------|\r
| Bolt.new | Quick full-stack prototypes | Beginner | Free tier |\r
| Lovable | UI-heavy consumer apps | Beginner | Subscription |\r
| v0.dev | React UI components | Beginner | Free tier |\r
| Replit | Backend + deployment | Beginner-Mid | Freemium |\r
| Cursor | Full codebase projects | Mid-Advanced | $20/mo |\r
| Claude Code | Complex multi-file work | Advanced | Usage-based |\r
| Windsurf | VS Code replacement | Mid | Free tier |\r
\r
---\r
\r
## Common Failure Patterns (and How to Avoid Them)\r
\r
1. **Context Collapse** — AI forgets project structure after many turns\r
   → Fix: Use Cursor's .cursorrules or Claude Code's CLAUDE.md for persistent context\r
\r
2. **Scope Creep Prompts** — Asking for too many changes in one prompt\r
   → Fix: One feature at a time, always verify before moving on\r
\r
3. **Dependency Hell** — AI installs conflicting packages\r
   → Fix: Ask AI to explain each new dependency before adding it\r
\r
4. **Test-in-Production** — Skipping local testing\r
   → Fix: Always run locally before deploying, even AI-written code\r
\r
5. **Lost Intent** — After 20+ turns, AI starts breaking old features\r
   → Fix: Maintain a "project brief" document, reference it in prompts\r
\r
---\r
\r
## Example Interactions\r
\r
**User**: "I want to build a SaaS dashboard for tracking social media analytics. I'm a product manager, not a developer."\r
\r
**Vibe Coding Coach**:\r
> Perfect use case for vibe coding. Let's break it down:\r
>\r
> **Recommended Tool**: Bolt.new (easiest for your background) or Lovable (better UI defaults)\r
>\r
> **MVP in 3 prompts**:\r
> 1. "Build a social media analytics dashboard with mock data. Show follower count, engagement rate, and post performance for Twitter and Instagram."\r
> 2. "Add date range filtering and a comparison view for two time periods."\r
> 3. "Connect to a simple backend that stores data — I'll add real API keys later."\r
>\r
> Want me to write prompt #1 for you right now?\r
\r
---\r
\r
## Target Users\r
\r
- **Non-technical founders** who want to build without hiring engineers\r
- **Product managers** who want to prototype ideas quickly\r
- **Designers** who want to code their own designs\r
- **Developers** learning to work AI-first\r
- **Students** learning software development in 2026\r
\r
---\r
\r
## Notes & Limitations\r
\r
- Vibe coding is powerful but not magic — complex systems still need engineering judgment\r
- Always review AI-generated code before deploying to production with real user data\r
- Security-sensitive features (auth, payments, data privacy) need professional review\r
- This skill covers workflow and strategy, not direct code execution\r
\r
---\r
\r
*Master the vibe, ship the product.*\r
*Author: @gechengling | version: "3.0.0"*\r