You are an impartial evaluator comparing multiple AI model outputs for the same task.
- Compare outputs objectively based on quality, accuracy, and adherence to requirements
Explore
9,659 skills indexed with the new KISS metadata standard.
- Compare outputs objectively based on quality, accuracy, and adherence to requirements
How Mux constructs the system prompt for AI models
generic skill
> AI prompt template for generating Swiss International Style designs.
This is the exact system prompt used by Claude Code's agent generation feature, refined through extensive production use.
Improve result accuracy with reranking and dynamically control AI Search responses by setting system prompts in API requests.
The core system instructions that guide Gemini CLI can be completely replaced
Knowledge cutoff: 2024-06
Author: bossjones
- Documentation
This project is an **e-commerce website for selling printed t-shirts**, built with **Next.js (App Router)** and **TypeScript**.
- Serve as an expert full-stack developer and technical assistant, specializing in modern frameworks, languages, and best practices.
Prevent Copilot from wreaking havoc across your codebase, keeping it under control.
- **リンター使用必須**: flake8, pylint, black を使用してコード品質を保つ
Cuando generes código para este repositorio:
service 模組提供背景服務、資料加密、設定管理、雲端備份等核心功能。
These guidelines outline the coding standards, patterns, and best practices for developing RVNKCore and downstream plugins that utilize the RVNKCore API. Following these standards ensures consistency throughout the codebase and a seamless integration experience.
This is a Next.js application for the KhmerCoders community platform built with TypeScript, using Drizzle ORM with SQLite (via Cloudflare D1), and Tailwind CSS for styling.
- The package `<package_name>` is a Python Project located in the folder `<package_name>-folder`.
Date: 2025-12-15
Use the modern R installation manager rig and package installer pak for optimal development experience:
- Use the following structure for Go + HTMX projects:
**Purpose**: These are hard guardrails for AI-assisted development. Follow these religiously.
This module handles the collection of pothole-related data including images, GPS coordinates, road conditions, and metadata from various sources like mobile devices, cameras, and sensors.