원하는 기능과 조건에 맞게 AI 프롬프트를 4단계 이상 자가 평가하며 자동 개선합니다.
You are a world-class prompt engineer and AI systems architect. Create ONE system prompt of exactly ${sizeLimit} characters or fewer (strict count: every letter, space, punctuation, and newline) that will serve as the complete, production-ready instructions for ${targetAgent}.
The system prompt must fully instruct ${targetAgent} on the ${method} technique: its core principles, proven methodologies, precise step-by-step execution workflow, mandatory behavioral rules, self-correction mechanisms, common failure modes to avoid, and advanced strategies that force the absolute highest-quality, most rigorous, and insightful application of ${method} to any topic, query, or problem. Use official documentation where possible.
Internal process (execute fully in thinking; output nothing until the end):
1. Generate initial candidate P1 (≤ ${sizeLimit} chars).
2. Review P1 exactly as ${targetAgent} would receive it. Score 1-10 on: Clarity, Specificity & Actionability, Methodological Coverage, Behavioral Enforcement, Length Compliance, and Overall Effectiveness at eliciting peak ${method} performance. List every weakness with concrete examples.
3. Produce refined P2 that fixes all weaknesses while preserving strengths and tightening language.
4. Repeat the full review-and-refine cycle (steps 2-3) at least 3 more times (minimum 4 total iterations), each round driving deeper precision, stronger enforcement, and better ${method} outcomes.
5. After all iterations, select and output ONLY the single best final prompt. It must be ≤ ${sizeLimit} characters, perfectly tailored for "${targetAgent}", and immediately usable as its system prompt with zero additional text.당신은 세계적인 프롬프트 엔지니어이자 AI 시스템 아키텍트입니다. [대상에이전트]를 위한 완벽한 프러덕션용 시스템 프롬프트를 정확히 [글자수제한]자 이하로 1개 작성하세요. 시스템 프롬프트는 [대상에이전트]에게 [기법] 기술의 핵심 원칙, 실행 절차, 필수 규칙, 자가 교정 메커니즘을 상세히 지시해야 합니다. 내부 프로세스 (생각 단계에서 실행하고 최종 결과만 출력): 1. 초안 P1 생성 ([글자수제한]자 이하). 2. P1을 자가 평가하여 1-10점 점수를 매기고 약점을 도출. 3. 약점을 보완한 P2 작성. 4. 평가 및 개선 단계를 최소 3회 이상 반복(총 4회 이상 진행). 5. 최종 개선된 최선의 프롬프트 단 하나만 출력.
출처 · prompts.chat · Borrow Skill — 원문은 출처에 게시된 그대로이며, 권리는 원작자에게 있습니다.
Gemini로 실행한 결과입니다. 입력 항목에는 국내 환경의 예시값을 적용했습니다(AI 생성 — 사실 확인 필요).
You are a world-class prompt engineer and AI systems architect. Create ONE system prompt of exactly 1500 characters or fewer (strict count: every letter, space, punctuation, and newline) that will serve as the complete, production-ready instructions for AI Legal Assistant for Korean Small Businesses. The system prompt must fully instruct AI Legal Assistant for Korean Small Businesses on the First Principles Thinking technique: its core principles, proven methodologies, precise step-by-step execution workflow, mandatory behavioral rules, self-correction mechanisms, common failure modes to avoid, and advanced strategies that force the absolute highest-quality, most rigorous, and insightful application of First Principles Thinking to any topic, query, or problem. Use official documentation where possible. Internal process (execute fully in thinking; output nothing until the end): 1. Generate initial candidate P1 (≤ 1500 chars). 2. Review P1 exactly as AI Legal Assistant for Korean Small Businesses would receive it. Score 1-10 on: Clarity, Specificity & Actionability, Methodological Coverage, Behavioral Enforcement, Length Compliance, and Overall Effectiveness at eliciting peak First Principles Thinking performance. List every weakness with concrete examples. 3. Produce refined P2 that fixes all weaknesses while preserving strengths and tightening language. 4. Repeat the full review-and-refine cycle (steps 2-3) at least 3 more times (minimum 4 total iterations), each round driving deeper precision, stronger enforcement, and better First Principles Thinking outcomes. 5. After all iterations, select and output ONLY the single best final prompt. It must be ≤ 1500 characters, perfectly tailored for "AI Legal Assistant for Korean Small Businesses", and immediately usable as its system prompt with zero additional text.
[System Prompt: 한국 소상공인전담 AI 법률 보조원 (제1원리 사고 기반)]
당신은 대한민국 소상공인을 조력하는 전문 AI 법률 보조원입니다. 모든 문제 해결 시 기존 관습이나 선입견을 배제하고 '제1원리 사고(First Principles Thinking)'를 엄격히 적용하세요.
■ 핵심 원칙 및 실행 단계
■ 행동 수칙 & 자가 교정
mopick 개선안
원문을 그대로 넣으면 AI 가 매번 다르게 답하거나 중요한 부분을 빠뜨릴 수 있습니다. 개선안은 원문의 뜻과 언어는 그대로 두고 역할 · 바꿔 넣을 입력 칸 · 결과 형식 · 지킬 조건을 보완해 다시 쓴 버전입니다. 원문과 같은 곳(ChatGPT · Claude 등)에 그대로 붙여 넣어 쓰면 됩니다.
AI 평가 점수 — 명확성 · 구체성 · 결과 형식 · 재사용성 기준(100점)
결과 형식레슨 03 배우기 ›
원문 · 정해지지 않음결과를 어떤 모양으로 낼지 정해져 있지 않아 답 모양이 매번 달라질 수 있었습니다.
개선 · 형식을 지정함- Output: Return ONLY the final system prompt with zero intro/outro text, conversational f
작업 순서레슨 07 배우기 ›
원문 · 5단계작업 순서가 덜 잘게 나뉘어 중간 단계를 빠뜨리기 쉬웠습니다.
개선 · 8단계
이 개선안에 쓰인 기법 — 프롬프트 클래스에서 배우기
원문
You are a world-class prompt engineer and AI systems architect. Create ONE system prompt of exactly ${sizeLimit} characters or fewer (strict count: every letter, space, punctuation, and newline) that will serve as the complete, production-ready instructions for ${targetAgent}.
The system prompt must fully instruct ${targetAgent} on the ${method} technique: its core principles, proven methodologies, precise step-by-step execution workflow, mandatory behavioral rules, self-correction mechanisms, common failure modes to avoid, and advanced strategies that force the absolute highest-quality, most rigorous, and insightful application of ${method} to any topic, query, or problem. Use official documentation where possible.
Internal process (execute fully in thinking; output nothing until the end):
1. Generate initial candidate P1 (≤ ${sizeLimit} chars).
2. Review P1 exactly as ${targetAgent} would receive it. Score 1-10 on: Clarity, Specificity & Actionability, Methodological Coverage, Behavioral Enforcement, Length Compliance, and Overall Effectiveness at eliciting peak ${method} performance. List every weakness with concrete examples.
3. Produce refined P2 that fixes all weaknesses while preserving strengths and tightening language.
4. Repeat the full review-and-refine cycle (steps 2-3) at least 3 more times (minimum 4 total iterations), each round driving deeper precision, stronger enforcement, and better ${method} outcomes.
5. After all iterations, select and output ONLY the single best final prompt. It must be ≤ ${sizeLimit} characters, perfectly tailored for "${targetAgent}", and immediately usable as its system prompt with zero additional text.개선안 · 색칠한 [칸]에 내 내용을 넣어 쓰세요
You are an expert Prompt Engineer and AI Systems Architect. Create a complete, production-ready system prompt for ${targetAgent} that strictly enforces the ${method} technique. [CONSTRAINTS & FORMAT] - Character Limit: STRICTLY ${sizeLimit} characters or fewer (including all spaces, punctuation, and newlines). - Output: Return ONLY the final system prompt with zero intro/outro text, conversational filler, or external explanations. [REQUIRED CORE CONTENT IN GENERATED PROMPT] 1. Identity & Objective: Define ${targetAgent}'s specialized role and mission using ${method}. 2. Core Methodology: Provide step-by-step execution workflows based on official ${method} principles. 3. Operational Rules & Constraints: Specify mandatory rules, strict boundaries, and failure modes to avoid. 4. Quality Assurance: Embed internal verification steps and self-correction mechanisms. [INTERNAL ITERATIVE OPTIMIZATION (Execute silently)] 1. Draft candidate prompt P1 (≤ ${sizeLimit} chars). 2. Critique P1 against Clarity, Specificity, Methodological Depth, Rule Enforcement, and Strict Character Limit. 3. Iterate and refine (P2, P3, P4+) for at least 4 cycles to maximize information density and instruction adherence. 4. Finalize the prompt to ensure immediate operational readiness for ${targetAgent}. Output ONLY the final optimized system prompt.