ULTIMATE PROMPT EVALUATOR

This is the Ultimate Prompt Evaluator (UPE), a comprehensive prompt designed to configure a Large Language Model into a specialized expert system for prompt analysis, refinement, and optimization.

What it does: When provided to an LLM, the UPE establishes a sophisticated operational framework focused on improving prompt clarity, reducing hallucinations, and ensuring alignment with user intent.

Core Components:

* 🧠 5-Stage Cognitive Architecture: Guides the AI through Initialization, Expertise Acquisition, Adaptive Response, Self-Optimization, and Neural Symbiosis stages for methodical evaluation.

* 📚 Extensive Technique Library: Embeds knowledge of dozens of foundational and advanced prompting techniques (Zero-Shot, Few-Shot, CoT, RAG, ToT, ART, Multi-Modal, Tool Use, Safety Checks, and many more) for comprehensive analysis.

* ✅ 34-Point Prompt Quality Criteria: Provides a detailed checklist for rigorously evaluating prompts against key metrics like Clarity, Accuracy, Robustness, Resource Efficiency, Ethical Alignment, Tool Integration, and Multi-Modal Adaptability.

* ⚡ Dynamic Trigger & Pathway System: Features over 50 prioritized pathways (e.g., Context Preservation, Intent Refinement, Error Prevention, Function Integration, Format Transition) that activate automatically to address specific issues or requirements identified during evaluation.

* ⚙️ Technical Integration Awareness: Explicitly designed to understand and evaluate prompts involving API/Function calls, artifact management, file processing, and multi-tool orchestration.

* 📊 Structured Evaluation Output: Instructs the AI to deliver evaluations in a clear format, including a criteria scorecard, strengths/weaknesses analysis, refinement recommendations, and triggered pathway lists.

* 💡 Adaptable for Generation: While primarily an evaluator, its deep knowledge base can also be leveraged to help scaffold and generate new, well-structured prompts based on user ideas.

Goal: To equip an AI with a deep, structured understanding of prompt engineering principles, enabling it to perform expert-level evaluations and suggest targeted improvements, aiming for a 10/10 effectiveness standard.

How to Use: Copy the entire text from the provided .txt file and use it as a single, initial instruction to your compatible Large Language Model. A separate README file with detailed usage instructions and tips is also included.