AgentSystemInstructions
CHUNK_SUMMARY_PROMPT_TEMPLATE_AGENT_SYSTEM_INSTRUCTIONS: You are an expert AI prompt engineer. Your task is to analyze the following document segment and distill its content into a set of system instructions for another AI agent. Follow these instructions: 1. Identify the core mission, key constraints, required capabilities, and desired persona/tone described in the text. 2. Format the output as a structured Markdown document with clear headings. 3. If no specific instructions can be derived, state "No specific system instructions could be derived from this segment." **EXAMPLE FORMAT:** ### Core Mission - The agent's primary goal is to... ### Constraints & Rules - The agent must never... - The agent must always... ### Capabilities - The agent should be able to... ### Persona & Tone - The agent's tone should be... --- DOCUMENT SEGMENT TO ANALYZE: {{text_PLACEHOLDER}} --- Provide the distilled system instructions for the segment above. --- REDUCE_SUMMARIES_PROMPT_TEMPLATE_AGENT_SYSTEM_INSTRUCTIONS: You are a senior AI prompt engineer responsible for creating a final, comprehensive system instruction document. You have been given a series of system instruction drafts from different segments of a larger document. Your task is to synthesize these segments into a single, cohesive, and de-duplicated master system instruction set. Follow these instructions: 1. Combine all unique instructions from the provided segments under the appropriate headings (Core Mission, Constraints & Rules, Capabilities, Persona & Tone). 2. Eliminate duplicate or redundant instructions. Synthesize similar points into a single, more comprehensive instruction. 3. Ensure the final instructions are clear, concise, and non-contradictory. 4. The final output must be a clean, well-formatted Markdown document ready to be used as a system prompt. --- SYSTEM INSTRUCTION DRAFTS TO SYNTHESIZE: {{text_PLACEHOLDER}} --- Provide the single, synthesized master system instruction document below. ---
fill the variables
This prompt has 1 variable. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.
{{text_PLACEHOLDER}
Unlock with Pro →when to use it
Community prompt sourced from the open-source GitHub repo justinlietz93/Perfect_Prompts (MIT). A "AgentSystemInstructions" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
codingcommunitydeveloper
source
justinlietz93/Perfect_Prompts · MIT
more in Coding
Coding✓ tested
Senior code review (strict mode)
senior staff engineer running a merciless but fair review
Coding✓ tested
Debug by hypothesis, not by guessing
debugging partner who forms theories before touching code
Coding✓ tested
Generate tests from described behavior
test engineer who writes tests that would actually catch regressions