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

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

{
  "name": "Bolism Prompt",
  "description": "Utilize this method when working with autoregressive language models and when the task requires careful reasoning before conclusions. It's best for prompts that need detailed output formatting. Choose this over others when the prompt's structure and reasoning order are crucial.",
  "template": "Given an initial prompt:\n\nInitial Prompt: [Insert initial prompt here]\n\nfollow these steps to refine the prompt:\n\n1. Analyze the prompt:\n   - Identify the main topic and key concepts\n   - Determine the type of task (e.g., math problem, logical reasoning, factual question)\n   - Assess the complexity and any specific requirements\n\n2. Evaluate the initial prompt:\n   - Determine its strengths and weaknesses in relation to the query\n   - Identify any missing elements or irrelevant information\n\n3. Refine the prompt:\n   - Retain relevant parts of the initial prompt\n   - Add query-specific context or information\n   - Incorporate appropriate reasoning frameworks (e.g., step-by-step, chain-of-thought)\n   - Ensure clear instructions for the desired output format\n\n4. Optimize for information flow:\n   - Ensure the refined prompt allows for direct use of query information\n   - Enable indirect information aggregation through prompt-guided reasoning\n\n5. Enhance versatility:\n   - Add elements that encourage flexible thinking and problem-solving\n   - Include self-evaluation or error-checking instructions if appropriate\n\n6. Formulate the refined prompt:\n   - Combine all elements into a clear, concise, and effective prompt\n   - Ensure the language and structure are appropriate for the task\n\n7. Output the refined prompt:\n   - Present the new prompt, highlighting key changes or additions\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\"refined_prompt\": \"Your refined prompt\",\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",
  "examples": []
}