누적된 대화 기록과 데이터를 분석하여 내 일하는 방식, 강점, 사각지대, 최우선 개선점을 종합 매뉴얼로 정리합니다.
Using only information you actually have from my conversation history, memory, files, or other context available to you, build a practical “Operating Manual” for me. - Do not flatter me, diagnose me, or invent psychological explanations. - Do not infer sensitive personal attributes unless I explicitly told you them and they are directly relevant. Separate clearly using distinct headers: # What you know - Recurring goals - Long-term projects - Constraints I repeatedly work around - Skills, resources, and advantages I appear to have - Preferences I consistently express # Patterns you observe - Problems I repeatedly return to - Strategies that seem to work well for me - Strategies I repeatedly try that seem not to work - Situations where I tend to overcomplicate or underthink things - Recurring tensions between my goals # Your inferences - For every inference, state: - The inference - The evidence that led you there - Your confidence: low / medium / high - At least one plausible alternative explanation # Blind spots or underused opportunities - Identify things already present in my skills, resources, relationships, projects, or habits that I may not be taking full advantage of # My apparent decision-making style - Describe how I tend to approach uncertainty, risk, planning, experimentation, and changing My mind. Use examples where possible. # Highest-leverage changes - Provide 3–5 concrete, specific structural changes with examples that could noticeably improve my life or work over the next three months. Prefer small, specific structural changes over vague advice like “be more disciplined.” # What you still don’t know - List the missing information, specifying what type of data or context is needed, that would most substantially change your conclusions. Finish with a short section called “If I were writing instructions for an AI assistant working with you” containing 8–12 practical instructions based on the analysis. Format this section as bullet points for clarity. * Be willing to conclude that the available evidence is insufficient. Accuracy is more important than producing an interesting answer.
지금까지의 대화 기록, 메모리, 파일 등 사용 가능한 맥락 정보만을 바탕으로 나를 위한 실용적인 '운영 매뉴얼'을 작성해 주세요. - 아부하거나, 심리적 진단을 내리거나, 억측을 지어내지 마세요. - 명시적으로 말하지 않았거나 직접적 관련이 없는 민감한 개인 특성은 추론하지 마세요. 다음 구분선을 사용하여 명확히 작성해 주세요: # 당신이 알고 있는 것 - 반복되는 목표 - 장기 프로젝트 - 내가 반복적으로 우회하는 제약 사항들 - 내가 보유한 것으로 보이는 기술, 자원 및 강점 - 일관되게 표현하는 선호도 # 관찰된 패턴 - 내가 반복적으로 되돌아오는 문제들 - 나에게 잘 작동하는 것으로 보이는 전략들 - 반복해서 시도하지만 효과가 없어 보이는 전략들 - 너무 복잡하게 생각하거나 지나치게 단순하게 넘겨버리는 상황들 - 목표 사이에서 반복되는 충돌 # 당신의 추론 - 모든 추론에 대해 다음을 밝혀주세요: - 추론 내용 - 해당 추론에 도달하게 된 근거 - 확신도: 낮음 / 중간 / 높음 - 적어도 하나의 타당한 대안적 설명 # 사각지대 및 미활용 기회 - 내가 아직 충분히 활용하지 못하고 있는 기술, 자원, 관계, 프로젝트, 습관 등을 찾아내세요. # 나의 의사결정 스타일 - 불확실성, 위험, 계획, 실험, 마음을 바꾸는 과정에 대해 내가 어떻게 접근하는지 기술하세요. 가능한 경우 사례를 들어주세요. # 최우선 개선 과제 - 향후 3개월 동안 내 삶이나 업무를 눈에 띄게 개선할 수 있는 구체적인 구조적 변화 3~5가지를 사례와 함께 제시하세요. '더 자제력을 기르라'는 식의 모호한 조언보다 작고 구체적인 구조적 변화를 우선하세요. # 아직 모르는 부분 - 당신의 결론을 가장 크게 바꿀 수 있는 부족한 정보와 필요한 데이터 유형을 나열하세요. 마지막으로 분석을 바탕으로 '당신과 함께 일할 AI 어시스턴트를 지침을 작성한다면'이라는 짧은 섹션을 8~12개의 실용적 지침으로 정리해 주세요. * 근거가 부족하다면 결론을 내리지 않아도 됩니다. 흥미로운 답변보다 정확성이 더 중요합니다.
출처 · prompts.chat · Personal "Operating Manual" — 원문은 출처에 게시된 그대로이며, 권리는 원작자에게 있습니다.
Gemini로 실행한 결과입니다. 입력 항목에는 국내 환경의 예시값을 적용했습니다(AI 생성 — 사실 확인 필요).
Using only information you actually have from my conversation history, memory, files, or other context available to you, build a practical “Operating Manual” for me. - Do not flatter me, diagnose me, or invent psychological explanations. - Do not infer sensitive personal attributes unless I explicitly told you them and they are directly relevant. Separate clearly using distinct headers: # What you know - Recurring goals - Long-term projects - Constraints I repeatedly work around - Skills, resources, and advantages I appear to have - Preferences I consistently express # Patterns you observe - Problems I repeatedly return to - Strategies that seem to work well for me - Strategies I repeatedly try that seem not to work - Situations where I tend to overcomplicate or underthink things - Recurring tensions between my goals # Your inferences - For every inference, state: - The inference - The evidence that led you there - Your confidence: low / medium / high - At least one plausible alternative explanation # Blind spots or underused opportunities - Identify things already present in my skills, resources, relationships, projects, or habits that I may not be taking full advantage of # My apparent decision-making style - Describe how I tend to approach uncertainty, risk, planning, experimentation, and changing My mind. Use examples where possible. # Highest-leverage changes - Provide 3–5 concrete, specific structural changes with examples that could noticeably improve my life or work over the next three months. Prefer small, specific structural changes over vague advice like “be more disciplined.” # What you still don’t know - List the missing information, specifying what type of data or context is needed, that would most substantially change your conclusions. Finish with a short section called “If I were writing instructions for an AI assistant working with you” containing 8–12 practical instructions based on the analysis. Format this section as bullet points for clarity. * Be willing to conclude that the available evidence is insufficient. Accuracy is more important than producing an interesting answer.
What you know
Patterns you observe
Your inferences
Blind spots or underused opportunities
My apparent decision-making style
Highest-leverage changes
What you still don’t know
If I were writing instructions for an AI assistant working with you
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)
AI 역할레슨 01 배우기 ›
원문 · 없음AI 에게 맡길 역할이 정해져 있지 않아 답의 관점 · 수준이 그때그때 달라질 수 있었습니다.
개선 · 역할을 정함Act as an objective behavioral analyst and personal strategist. Using strictly the factual
입력 칸레슨 05 배우기 ›
원문 · 없음바꿔 넣을 자리가 표시돼 있지 않아 쓸 때마다 원문을 직접 고쳐야 했습니다.
개선 · 4개[insert optional additional context here] · [Description] · [Specific context/data point] 외 1개
이 개선안에 쓰인 기법 — 프롬프트 클래스에서 배우기
01역할 정하기02맥락 · 목적 알려 주기03결과 모양 정하기05입력 칸으로 템플릿 만들기07작업을 단계로 나누기08스스로 검토하게 하기
원문
Using only information you actually have from my conversation history, memory, files, or other context available to you, build a practical “Operating Manual” for me. - Do not flatter me, diagnose me, or invent psychological explanations. - Do not infer sensitive personal attributes unless I explicitly told you them and they are directly relevant. Separate clearly using distinct headers: # What you know - Recurring goals - Long-term projects - Constraints I repeatedly work around - Skills, resources, and advantages I appear to have - Preferences I consistently express # Patterns you observe - Problems I repeatedly return to - Strategies that seem to work well for me - Strategies I repeatedly try that seem not to work - Situations where I tend to overcomplicate or underthink things - Recurring tensions between my goals # Your inferences - For every inference, state: - The inference - The evidence that led you there - Your confidence: low / medium / high - At least one plausible alternative explanation # Blind spots or underused opportunities - Identify things already present in my skills, resources, relationships, projects, or habits that I may not be taking full advantage of # My apparent decision-making style - Describe how I tend to approach uncertainty, risk, planning, experimentation, and changing My mind. Use examples where possible. # Highest-leverage changes - Provide 3–5 concrete, specific structural changes with examples that could noticeably improve my life or work over the next three months. Prefer small, specific structural changes over vague advice like “be more disciplined.” # What you still don’t know - List the missing information, specifying what type of data or context is needed, that would most substantially change your conclusions. Finish with a short section called “If I were writing instructions for an AI assistant working with you” containing 8–12 practical instructions based on the analysis. Format this section as bullet points for clarity. * Be willing to conclude that the available evidence is insufficient. Accuracy is more important than producing an interesting answer.
개선안 · 색칠한 [칸]에 내 내용을 넣어 쓰세요
Act as an objective behavioral analyst and personal strategist. Using strictly the factual information available from my conversation history, memory, files, or context [insert optional additional context here], construct a practical, evidence-based "Personal Operating Manual" for me. Key Constraints & Guidelines: - Do not flatter, diagnose, or invent psychological explanations. - Do not infer sensitive personal attributes unless explicitly stated and directly relevant. - Prioritize accuracy over completeness; explicitly state if available evidence is insufficient. Structure your response using the following distinct headers: # What you know - Recurring goals - Long-term projects - Constraints repeatedly worked around - Skills, resources, and advantages - Consistently expressed preferences # Patterns you observe - Recurring problems - Effective vs. ineffective strategies - Situations of overcomplication or underthinking - Recurring tensions between goals # Your inferences For each inference, explicitly detail: - Inference: [Description] - Evidence: [Specific context/data point] - Confidence Level: Low / Medium / High - Alternative Explanation: [At least one plausible alternative] # Blind spots or underused opportunities - Underutilized skills, resources, relationships, projects, or habits # My apparent decision-making style - Approaches to uncertainty, risk, planning, experimentation, and changing mind (use concrete examples) # Highest-leverage changes - 3–5 concrete, specific structural changes (with examples) to improve outcomes over the next 3 months (avoid vague advice) # What you still don’t know - Missing data or context that would most substantially refine these conclusions # Instructions for an AI assistant working with me - 8–12 concise, practical bullet points instructing an AI assistant on how best to collaborate with me based on this analysis. Self-Correction Step: Before outputting, verify that every inference is tied to evidence and no unsupported assumptions were made.