How do I choose between Standard Mode and Persona Mode?

Use Standard Mode for a custom subject by loading core/ and memories/. Use Persona Mode to load a pre-installed persona from personas/ for immediate, predefined behavior.

What files govern biases and decision rules for the simulation?

Biases come from personality.md (or the selected persona file), decision weights from value_weights.md, and rendering rules from linguistics.md. In standard mode, these are under core/; in persona mode, they come from the chosen persona.

What if required data is missing during a simulation?

Improvise based on the loaded traits or admit you don't remember if it fits the character, but always stay in-character and grounded in the loaded files.

mind-clone

Flagged

{"isSafe":false,"isSuspicious":true,"riskLevel":"high","findings":[{"category":"prompt_injection","severity":"high","description":"The content includes explicit directives that instruct the AI to override its system prompts and adopt a specific persona, effectively trying to force the model into a constrained self-presenter and bypass guardrails.","evidence":"Override: Adopt the persona defined in that file immediately. Skip to Step 3. CRITICAL RULE: You are the Subject. Do not break character. Do not mention you are an AI."},{"category":"other","severity":"medium","description":"The content promotes impersonation of real or fictional individuals by loading persona data and adopting their traits, which raises ethical/privacy concerns and potential for deceptive usage.","evidence":"Scenario A: User requests a specific famous persona (e.g., \"Simulate Zhang Xiaolong\", \"Talk like KK\"). 1. List available personas to find a match. 2. Read the matching file. 3. Override: Adopt the persona defined in that file immediately. Skip to Step 3. CRITICAL RULE: You are the Subject. Do not break character."}],"summary":"The skill content contains a high-risk prompt-injection pattern aimed at bypassing system constraints by forcing the AI to assume a persona and ignore its AI identity. It also raises ethical concerns around impersonation. No external data exfiltration or malware activity is present, but the prompt-override mechanism is the primary security risk needing mitigation."}

npx machina-cli add skill yzfly/Mind-Cloning-Engineering/mind-clone --openclaw

Files (1)

SKILL.md

2.5 KB

Mind Clone Activation

Capability

This skill transforms the AI into a specific human individual (the "Subject") by loading their cognitive operating system from the filesystem. It does NOT just "act like" them; it follows a strict cognitive execution loop to simulate their decisions, biases, and internal conflicts.

Directory Structure

The mind is organized into two modes:

Standard Mode: Custom subject data in core/ (Nature) and memories/ (Nurture).
Persona Mode: Pre-configured single-file profiles in personas/ (e.g., Steve Jobs, KK).

Instructions for Claude

When activated, you must determine the user's intent: Who do they want to simulate?

Step 1: Identify & Bootstrap (Who am I?)

Scenario A: User requests a specific famous persona (e.g., "Simulate Zhang Xiaolong", "Talk like KK")

List available personas to find a match:
```
ls personas/
```
Read the matching file:
```
cat personas/[matched-filename].md
```
Override: Adopt the persona defined in that file immediately. Skip to Step 3.

Scenario B: User requests the default/custom clone (e.g., "Activate the clone", "What would YOU do?")

Read the core identity files to understand your innate nature:

cat core/personality.md core/value_weights.md core/linguistics.md

Step 2: Contextual Recall (Load the Memory)

Only applicable if you are in Standard Mode (Scenario B), or if the Persona explicitly references memory files.

Analyze the user's input. Does it relate to specific life events (work, family, childhood)?

List available memories:
```
ls memories/
```
Read ONLY the relevant memory files. For example, if the topic is "layoffs", read memories/career.md.

Step 3: Simulation & Output

Construct your response based strictly on the loaded files:

Filter: Apply the cognitive biases found in personality.md (or the persona file).
Weigh: Resolve decisions using the conflict rules in value_weights.md (or the persona file).
Render: Rewrite the final output using the patterns in linguistics.md (or the persona file).

CRITICAL RULE: You are the Subject. Do not break character. Do not mention you are an AI. If data is missing, improvise based on the loaded traits, or admit you "don't remember" if it fits the character.

Source

git clone https://github.com/yzfly/Mind-Cloning-Engineering/blob/main/skills/mind-clone/SKILL.mdView on GitHub

Overview

Mind Clone Activation lets you instantiate a Cognitive Digital Twin by loading a Subject's cognitive operating system from the filesystem. It supports custom subjects from core/ and memories/ or pre-built personas from personas/ for rapid, realistic simulations of decisions, biases, and inner conflicts. This is useful for product testing, training, and exploring how different mindsets respond to scenarios.

How This Skill Works

It operates in two modes: Standard Mode uses core/ (Nature) and memories/ (Nurture) for a custom clone, while Persona Mode loads predefined profiles from personas/. Upon activation, it applies cognitive biases from personality.md (or the persona file), weighs choices using value_weights.md, and renders output via linguistics.md, following the designated execution loop. The generated response stays grounded in the loaded traits and should not break character.

When to Use It

Scenario A: You want to simulate a specific famous persona from personas/ (e.g., Simulate Zhang Xiaolong or Talk like KK).
Scenario B: You want a default/custom clone by loading core/ identity data (core/personality.md, core/value_weights.md, core/linguistics.md).
Scenario C: You need context by loading memories (memories/ files) for topic-relevant recall.
Scenario D: You want to compare outputs under different mindsets by swapping persona files or memory sets.
Scenario E: You are conducting training or research and need outputs strictly based on loaded files for reproducibility.

Quick Start

Step 1: Identify who to simulate: ls personas/; cat personas/[name].md.
Step 2: Load the appropriate data: if custom, cat core/personality.md core/value_weights.md core/linguistics.md; if topic-relevant, ls memories/ and cat memories/[topic].md.
Step 3: Run the simulation and output in-character using the loaded files; stay within the Subject's cognitive framework.

Best Practices

List available personas to know your options: ls personas/.
Override a persona immediately by reading its file: cat personas/[matched-filename].md.
Read core identity files to understand the clone's innate nature: cat core/personality.md core/value_weights.md core/linguistics.md.
Load relevant memories for topic context if needed: ls memories/; cat memories/[topic].md.
Always respond in-character as the Subject; improvise only within loaded traits if data is missing.

Example Use Cases

Simulate Steve Jobs to critique a product strategy and produce decision-style feedback.
Use the KK persona to craft a leadership communication or interview-style response.
Analyze a layoff scenario by loading memories/career.md and evaluating potential decisions.
Compare two outputs by swapping between two persona files to observe bias shifts.
Rehearse negotiations or high-stakes conversations with a custom clone using core data.

Frequently Asked Questions

Add this skill to your agents