AI SummaryA comprehensive system prompt and .cursorrules template for building a manufacturing defect detection MVP in Cursor AI, providing structured guidance on FastAPI backend, React frontend, and LLaVA vision model integration.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to add the "llama-vision-inspector — System Prompt" prompt rules to my project. Repository: https://github.com/basedlsg/llama-vision-inspector Please read the repo to find the rules/prompt file, then: 1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type) 2. If there's an existing rules file, merge the new rules in rather than overwriting 3. Confirm what was added
Description
System Prompt for llama-vision-inspector
Overview
This document provides a comprehensive system prompt strategy for building the LLAMA Vision Inspector MVP using Cursor AI IDE. The approach follows proven Cursor best practices with a phased development strategy to ensure reliable, production-quality code generation. ---
Testing Requirements
• Write unit tests for ALL business logic functions • Write integration tests for API endpoints • Mock external API calls in tests • Achieve >80% code coverage • Use pytest for backend testing, Jest/React Testing Library for frontend • Test files must be in __tests__ directories alongside source code
1. Dependencies (requirements.txt):
` fastapi==0.104.1 uvicorn[standard]==0.24.0 pydantic==2.5.0 python-dotenv==1.0.0 httpx==0.25.2 pillow==10.1.0 replicate==0.22.0 pytest==7.4.3 pytest-asyncio==0.21.1 python-multipart==0.0.6 `
3. Image Processing Requirements:
Implement create_comparison_image() function that: • Validates image format and dimensions • Removes EXIF data • Resizes all images to 400x400px maintaining aspect ratio • Creates horizontal concatenation: [GOOD|BAD|TEST] • Returns PIL Image object
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster
Works With
Any AI assistant that accepts custom rules or system prompts