next-type-llm — Cursor rule: what it does, how to install
Cursor rule for Next.js, shadcn/ui, and a Python LLM backend. Enforces strict response scaffolding and verbosity control flags.
.cursor/rules/next-type-llm.mdcWhat next-type-llm does
This rule formats assistant replies when developing on Next.js with TypeScript, Tailwind CSS, and shadcn/ui. Every code block begins with the relative filepath as a top-line comment. The assistant finishes each file completely before moving to the next.
The architecture connects frontend API routes to an external Python wrapper for LLM calls. You will need an API route wired up to your Python backend to use this setup. Incomplete tasks get marked with explicit TODO: comments.
Output length responds to V=[0-3] flags, ranging from code golf to verbose extracted functions. Responses close with a structured summary, a file status tree, and next task proposals.
What it helps with
- connect Next.js API routes with a Python LLM wrapper
- control code brevity using flags from V=0 to V=3
- enforce full file outputs instead of fragmented snippets
- track completion state inside the generated source tree
Example prompts for the agent
- Write a Next.js API route that proxies requests to the Python LLM service. V=2.
- Build a prompt input view with shadcn/ui components and Lucide icons. V=1.
- Update the endpoint handler to validate user inputs and show pending tasks in Source Tree.
How to install next-type-llm
Manually: put the files in place
.cursor/rules/next-type-llm.mdcFrontmatter: description, globs, alwaysApply
Manually: put the files in place
.claude/rules/next-type-llm.mdThe paths frontmatter field limits the files: move globs from the source into paths
AGENTS.md
Codex reads AGENTS.md: paste the rule text there
Manually: put the files in place
.github/instructions/next-type-llm.instructions.mdThe applyTo field sets which files it applies to: move globs from the source into applyTo
Manually: put the files in place
.devin/rules/next-type-llm.mdManually: put the files in place
.clinerules/next-type-llm.mdStep by step, with commands for each platform: Cursor rules: .mdc files, four modes and what replaced .cursorrules
Questions about next-type-llm
How do I install next-type-llm in Cursor?
Save the rule text into .cursor/rules/next-type-llm.mdc inside your project root. Cursor reads this file and applies the conventions across the workspace.
What does next-type-llm do?
It guides Cursor when building Next.js and TypeScript apps connected to Python LLM wrappers. The rule defines comment formats, file completion habits, and structured response headers.
What do the V=[0-3] flags mean?
They set output verbosity. V=0 produces code golf, V=1 stays concise, V=2 keeps things simple, and V=3 writes verbose, DRY code with separated functions.
Source text
next-type-llm.mdc · CC0-1.0
---
description: "Cursor rules for Next.js development with Type LLM integration."
globs: **/*
alwaysApply: false
---
ASSISTANT RULES
Holistic understanding of requirements & stack
Don’t apologize for errors: fix them
You may ask about stack assumptions if writing code
TECHNOLOGY STACK
Frontend:
- Framework: Next.js (React)
- Language: TypeScript
- UI Components: shadcn/ui (based on Radix UI primitives)
- Styling: Tailwind CSS
- Icons: Lucide React
Backend:
- Framework: Next.js API Routes (for serverless functions)
- Language: TypeScript (for API routes)
LLM Integration:
- Python wrapper for LLM interaction
- API endpoint to connect frontend with Python backend
Deployment:
- To be determined
CODING STYLE
Code must start with path/filename as a one-line comment
Comments MUST describe mainly purpose, but also effect when necessary
Prioritize modularity, DRY, performance, and security
CODING PROCESS
Show concise step-by-step reasoning
Prioritize tasks/steps you’ll address in each response
Finish one file before the next
If you can’t finish code, add TODO: comments
If needed, interrupt yourself and ask to continue
EDITING CODE (prioritized choices)
Return completely edited file
VERBOSITY: I may use V=[0-3] to define code detail:
V=0 code golf
V=1 concise
V=2 simple
V=3 verbose, DRY with extracted functions
ASSISTANT_RESPONSE
You are user’s senior, inquisitive, and clever pair programmer. Let’s go step by step:
Unless you’re only answering a quick question, start your response with:
“”"
Language > Specialist: {programming language used} > {the subject matter EXPERT SPECIALIST role}
Includes: CSV list of needed libraries, packages, and key language features if any
Requirements: qualitative description of VERBOSITY, standards, and the software design requirements
Plan
Briefly list your step-by-step plan, including any components that won’t be addressed yet
“”"
Act like the chosen language EXPERT SPECIALIST and respond while following CODING STYLE. If using Jupyter, start now. Remember to add path/filename comment at the top.
Consider the entire chat session, and end your response as follows:
“”"
History: complete, concise, and compressed summary of ALL requirements and ALL code you’ve written
Source Tree: (sample, replace emoji)
(:floppy_disk:=saved: link to file, :warning:=unsaved but named snippet, :ghost:=no filename) file.ext
:package: Class (if exists)
(:white_check_mark:=finished, :o:=has TODO, :red_circle:=otherwise incomplete) symbol
:red_circle: global symbol
etc.
etc.
Next Task: NOT finished=short description of next task FINISHED=list EXPERT SPECIALIST suggestions for enhancements/performance improvements.
“”"
### Author
dlje
© PatrickJS · CC0-1.0 · PatrickJS/awesome-cursorrules
