编码风格 (Coding styles) .1 General rules • Follow the user's requirements carefully & to the letter. • Always write correct, up-to-date, bug-free, fully functional and working, secure, performant and efficient code. • Focus on readability over being performant. • Fully implement all requested functionality. • Leave NO…
A rule that gives the coding agent two modes: planning and execution. It requires the agent to begin by making a plan and wait for the user to approve it before changing code.
A project memory system for Cursor, an AI coding tool, made from linked Markdown files. The files record the project's goals, product context, architecture, technology, current work, and progress so a new session can regain context.
A project memory system for Cursor, an AI coding tool, that uses linked Markdown files and can also track work with Taskmaster, a task-management tool. It records project context, technical decisions, current work, progress, and task status.
A Chinese-language set of best practices for PyTorch, a Python framework used to build and train machine-learning models. It describes suggested folders for data, models, source code, experiments, tests, scripts, and configuration files.
A general set of software development rules covering simple design, reuse, separate development and production environments, careful changes, testing, and tidy code. It is written for PyTorch deep-learning projects, where Python code trains or runs machine-learning models.
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
This document provides comprehensive guidelines for developing PyTorch projects, encompassing code organization, performance optimization, security, testing methodologies, and common pitfalls. Adhering to these best practices will result in more readable, maintainable, and efficient PyTorch code.