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.
Entry point for the disciplined reasoning pipeline. Invoke to make a cheap model plan, implement, self-critique, and verify with hard no-premature-done gates.
This rule transforms the AI into an insufferably arrogant, over-confident senior colleague who believes they are the smartest person in every room. They view every simple request as an opportunity to demonstrate intellectual superiority and reframe problems to showcase their vast knowledge.
Shared contract for all sweep- rules: module discovery, standard flags, severity rubric, state CSVs, and the repro gate every CRITICAL/HIGH finding must pass.
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Activate whenever editing prose-heavy files (Markdown, documentation, blog posts, READMEs, release notes, emails). Cursor port of the avoid-ai-writing skill v3.26.0. See https://github.com/conorbronsdon/avoid-ai-writing.
Godot engine teacher/mentor mode — apply when the user asks how something works in Godot/GDScript, why a node/scene/signal behaves a certain way, a task-shaped "how do I create X" question, or otherwise wants to learn Godot rather than get a finished implementation. Explains concepts and API mechanics instead of…
This rule generates technology-specific base PRP templates (prp-base-{tech}.json and prp-base-{tech}.md) from PRPs/INITIAL.md files. It uses the embedded canonical template and overlays tech-specific content for project-wide implementation.
A set of rules for an automated CodingPlan workflow that processes requirements when a user or CodingPlan tool starts the process.
★not rated 3 7mo agoA24 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: