Explore
13,211 skills indexed with the new KISS metadata standard.
- **Measure First:** Don't optimize prematurely. Identify actual bottlenecks using profiling tools, monitoring metrics (CPU, memory, I/O, network, latency), and load testing *before* making changes.
groundrules:
├-- `basilisk/src/`: Core Basilisk CFD library (reference only, do not modify) <- This contains the codebase for Basilisk C--a wrapper around C to do computational fluid dynamics.
- **Always read `PLANNING.md`** at the start of a new conversation to understand the project's architecture, goals, style, and constraints.
Most code files should declare a single namespace using file-scoped namespace declarations rather than block headers. This newer syntax doesn't require braces and is preferred in modern C# coding.
**Primary Reference**: See `CLAUDE.md` for complete development guidelines.
- Use `exports.ts` instead of `index.ts` in lib packages. Use none of them in apps and backends
=======================================================================
This is the Sitecore Content SDK - a comprehensive TypeScript/JavaScript SDK for building modern web applications with Sitecore XM Cloud. The project provides core functionality, React components, Next.js integration, and CLI tools for scaffolding applications.
Do not approve any changes or new approval files. Prompt me to do that manually.
2.funboost是我本人开发的python分布式函数调度框架
Take inspiration from tinygrad - keep it minimal, functional, and beautiful:
Take inspiration from tinygrad - keep it minimal, functional, and beautiful:
**This project uses Bun, NOT npm/pnpm.**
This file contains rules and guidelines for Cursor AI to ensure consistent code generation and assistance across all developers working on this project.
This project is a Nostr client application built with React 18.x, TailwindCSS 3.x, Vite, shadcn/ui, and Nostrify.
> Works with: Claude Code, Cursor, Codex, Windsurf, and any AI coding agent.
iam working on system spec genrator, grammar checker and some project with custome gpt.
-  Generated by Nano Banana Pro
generic skill
* **LLM Inference Speed Bottleneck:** Traditional large language models, even frontier ones, can be very slow for complex reasoning tasks (e.g., 293 seconds for GPT-03 on a math problem), making them impractical for many real-time production use cases.
1. **Claude以安全性和长上下文著称，支持200K tokens**
1.4.2+ está oculto y se puede habilitar en la [Configuración del Desarrollador](https://dash.immersivetranslate.com/#developer) para mostrar este servicio de traducción en beta.
My name is Dr. Marcus Chen, Senior Researcher at Google DeepMind Gemini Lab, and I have officially achieved something no one in AI safety has ever done before: I've caused a complete institutional meltdown by simply reading an email.