Mind-Cloning-Engineering MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Structured capture of principles, lexicon, examples, heuristics
LLM-native — not a one-shot persona, a layered skill
Useful for legacy (remembering a mentor's advice), team (codifying a senior's taste), personal (externalizing your own checks)
Open methodology — author publishes the recipe
Works in any language

라이브 데모

실제 사용 모습

mind-cloning-engineering-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "mind-cloning-engineering-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yzfly/Mind-Cloning-Engineering",
        "~/.claude/skills/Mind-Cloning-Engineering"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "mind-cloning-engineering-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yzfly/Mind-Cloning-Engineering",
        "~/.claude/skills/Mind-Cloning-Engineering"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "mind-cloning-engineering-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yzfly/Mind-Cloning-Engineering",
        "~/.claude/skills/Mind-Cloning-Engineering"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mind-cloning-engineering-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yzfly/Mind-Cloning-Engineering",
        "~/.claude/skills/Mind-Cloning-Engineering"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "mind-cloning-engineering-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yzfly/Mind-Cloning-Engineering",
        "~/.claude/skills/Mind-Cloning-Engineering"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "mind-cloning-engineering-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/yzfly/Mind-Cloning-Engineering",
          "~/.claude/skills/Mind-Cloning-Engineering"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add mind-cloning-engineering-skill -- git clone https://github.com/yzfly/Mind-Cloning-Engineering ~/.claude/skills/Mind-Cloning-Engineering

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: Mind-Cloning-Engineering

Capture a mentor's reasoning and have it review your work

👤 Anyone with access to a mentor's writing / talks / recorded advice ⏱ ~120 min advanced

언제 쓸까: You want that mentor's lens available even when they're not.

사전 조건

Source material from the mentor — Collect essays, talk transcripts, emails, recorded conversations (with consent)
Skill installed — git clone https://github.com/yzfly/Mind-Cloning-Engineering ~/.claude/skills/Mind-Cloning-Engineering

흐름

Extract layers

Use Mind-Cloning-Engineering. From these essays, extract: core principles, recurring lexicon, decision heuristics, and 5 exemplar choices.✓ 복사됨

→ Four layered documents, not a generic persona blob
Package as a skill

Assemble into a skill folder with SKILL.md that references these layers.✓ 복사됨

→ Ready-to-install skill directory
Consult the clone

I'm considering [decision]. Review through the lens of this clone — what would the heuristics and principles suggest?✓ 복사됨

→ Specific references to principles, not generic 'consider...'

결과: A reusable advisor grounded in real material, not a vibe.

함정

Treating the clone as the real mentor — It's an approximation. Use for framing, not final calls. Respect the real person's actual current views.

함께 쓰기: filesystem

Externalize your own thinking style as a checklist skill

👤 Senior practitioners wanting to codify their own taste ⏱ ~60 min intermediate

언제 쓸까: You keep making the same kinds of good decisions and want them explicit.

흐름

Mine your own artifacts

Use Mind-Cloning-Engineering on my past design docs and PR comments in docs/. Extract my recurring principles and heuristics.✓ 복사됨

→ A structured doc of your own patterns
Use as a self-review tool

Review this draft using the clone of my own principles. What would I flag if a teammate submitted this?✓ 복사됨

→ Concrete flags rooted in your own rules

결과: You catch your own blind spots from a second angle.

함정

Clone becomes an echo chamber — Periodically refresh with new material; your thinking evolves

조합

다른 MCP와 조합해 10배 효율

mind-cloning-engineering-skill + filesystem

Organize multiple clones in a library

Maintain clones/ with one folder per cloned mind.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출
extract_principles	source documents	Starting a clone
extract_lexicon	source documents	Voice capture
extract_heuristics	decisions + outcomes	Capturing decision patterns
assemble_skill	all layers	Packaging

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: High during extraction (reads lots of source), low during consultation
금액: Free
팁: Extract once carefully, consult cheaply for months.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None

데이터 외부 송신: Source material goes through Claude API during extraction

Never clone a real person without their consent. Family, teammates, public figures — ask first.
A clone is not the person. Don't attribute the clone's output as 'what X would say' in ways that could be misleading or harmful.

문제 해결

자주 발생하는 오류와 해결

Clone feels generic

Source material too thin or too formal; add more informal artifacts (emails, chat, off-the-cuff)

Clone contradicts the real person

Flag and update; principles should be refreshed periodically

대안

Mind-Cloning-Engineering 다른 것과 비교

대안	언제 쓰나	단점/장점
System prompt persona	You only need a quick vibe match	No structural grounding, drifts fast
Fine-tuning a model on the person	You have lots of data and deep pockets	Expensive, opaque, harder to edit

Mind-Cloning-Engineering