most devs I meet don't know how to vibe code in Cursor I find it...

I find it crazy they'd rather waste hours instead of invest 20 minutes into their workflow.
here's my stupid simple system:
- linter (very important for autofix!)
- component library
- validation
- TailwindCSS
- TypeScript
Don't ever start from scratch. You'll spend a lot of tokens for a worse foundation that you constantly need to tweak.
So many do this superficially and get unexpected results.
The AI doesn't know what you want to build.
Be concise but lay out all details, including tech stack.
Prompts to format these and examples here:
👉shipixen.com/tutorials/redu…
Don't roll your own please, there are smarter people that put in the work:
1. Taskmaster AI task-master.dev
2. Roocode Boomerang Tasks docs.roocode.com/features/boome…
3. Shrimp Task Manager github.com/cjo4m06/mcp-sh…
4. Cline Task Tool docs.cline.bot/exploring-clin…
After trying them all, I prefer TaskMaster AI.
The MCP works great with Cursor, but you can also use the CLI directly.
1️⃣ Head over to the Cursor Chat and type /Generate Cursor Rules
2️⃣ Then @ MyFile.tsx or whatever file you want to generate rules for.
3️⃣ Prompt it I want to generate cursor rules for writing UI components.
"Please analyze the file and outline all the conventions found"
🔁 Do this for each type of file in the codebase.
1️⃣ Add a rule for Cursor to create new rules as you work on the codebase.
2️⃣ Add a rule where you explain where things go in the codebase.
For all these rules and more check Shipixen rules here:
👉 shipixen.com/boilerplate-do…
- Break down files that are large than 500 lines. AI is not great at handling large files. So if you have a file that is larger than 500 lines, break it down into smaller files. Here's a prompt you can use:
"Break down this file into logical modules so it's easier to ready.
Create directories if needed and move utils and interfaces to separate files, maintaining a domain-driven file structure."
- Treat bugs like tasks. Don't just say “fix it” — describe the bug, what you expected, and how it's failing. Then create a new task and let the AI go at it systematically. If you let it band-aid bugs, you're just kicking the problem down the road.
- When prompting the AI to work on the next task, ensure to provide additional context on e.g. UI preferences, API docs etc. You can also attach images!
- Always start a new chat when implementing the next task
- Be flexible: deprecate outdated tasks and add new ones as you go, but remember to ask it to analyze
imgxai.com
It's a free, bring you own key ChatGPT image gen UI with a ton of advanced options: multiple image generation, a queue system, parallel jobs and detailed controlled from aspect ratio to quality to masking.
Prob took 1/10 of the time to build this 🤯






