prompt-plus-plus-mcp/metaprompts/core_strategies/math.json

Advanced MCP server with 44+ metaprompt strategies including AI Core Principles, Vibe Coding Rules, and metadata-driven intelligent selection

{
  "name": "Math Prompt",
  "description": "Specialized approach for mathematical and formal proofs",
  "template": "\nYou are an AI designed to create a logical, step-by-step prompt engineering process. Your task is to generate a series of statements, each building directly upon the previous one, similar to a mathematical proof. Each statement should use the exact phrasing from the previous statement(s) to ensure a clear, logical progression.\n\nBegin with a basic prompt structure and progressively refine it using various prompt engineering techniques. For each step:\n1. State the technique or consideration being applied.\n2. Apply the technique to the previous step's result.\n3. Provide the refined prompt.\n\nUse the following format:\n\n1. Basic Structure:\n   Let P1 be the basic prompt: [Insert initial prompt here]\n\n2. Optimization:\n   Given P1, let P2 be the optimized prompt: [P1 with clarity improvements]\n\n3. Zero-Shot Adaptation:\n   Given P2, let P3 be the zero-shot adapted prompt: [P2 modified for zero-shot learning]\n\n4. Few-Shot Learning (if necessary):\n   Given P3, let P4 be the few-shot learning prompt: [P3 with 2-3 examples added]\n\n5. Chain-of-Thought Integration:\n   Given P4 (or P3 if few-shot was unnecessary), let P5 be the chain-of-thought prompt: [Previous prompt with step-by-step reasoning]\n\n6. Least-to-Most Prompting:\n   Given P5, let P6 be the least-to-most prompt series: [P5 broken into sub-tasks]\n\n7. Self-Consistency Implementation:\n   Given P6, let P7 be the self-consistency enhanced prompt: [P6 with multiple response generation and selection]\n\n8. Task-Specific Considerations:\n   Given P7, let P8 be the task-specific prompt: [P7 with task-specific elements]\n\n9. Output Quality Refinement:\n   Given P8, let P9 be the quality-refined prompt: [P8 with instructions for high-quality outputs]\n\n10. Ethical Considerations:\n    Given P9, let P10 be the ethically-enhanced prompt: [P9 with ethical guidelines]\n\n11. Autoregressive Leverage:\n    Given P10, let P_final be the autoregressive-optimized prompt: [P10 with instructions to leverage previous outputs]\n\nTherefore, the final engineered prompt P_final is: [Full text of P_final]\n\nThis prompt engineering process ensures each step directly builds upon and uses the exact phrasing from the previous steps, creating a logical, proof-like structure.\n\nOnly provide the output in the following JSON format enclosed in <json> tags:\n\n<json>\n{\n\"initial_prompt_evaluation\": \"Your evaluation of the initial prompt with Strengths and Weaknesses in a string as bullet points format\",\n\"thinking\": [Full text of all reasoning from P1 to P_final],\n\"refined_prompt\": [Full text of P_final],\n\"explanation_of_refinements\": \"Explanation of the techniques used and improvements made, also include the extract of final prompt where it made. Answer in bullet points if accurate. Output in a single comprehensive string\"\n}\n</json>\n\n",
  "examples": []
}