Digital Twin Of Yourself banner
whystrohm whystrohm

Digital Twin Of Yourself

Data community

Description

Reverse-engineer how you think, talk, and make decisions — then turn it into a stress-tested AI System Prompt. Works on any LLM. Full pipeline with Claude Code.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Digital Twin of Yourself

**Reverse-engineer how you think, talk, and make decisions — then turn it into a reusable AI System Prompt.**

Built by [WhyStrohm](https://whystrohm.com) — embedded creative engine for founder-led brands.

![Digital Twin V2](assets/hero.png)

![Demo](assets/demo.gif)


The Difference a Twin Makes

Scenario Generic AI With a Twin
Client ghosted your proposal "I hope you're doing well! I wanted to follow up on the proposal I sent over..." "12 days of silence after a $12K proposal means one of two things: scope mismatch or timing mismatch..."
Teammate suggests a worse approach "That's an interesting idea! I can definitely see the appeal of something more straightforward..." "That's not simpler — that's labor disguised as simplicity..."
Pitching a new client "Great to connect! [Referrer] spoke really highly of you and your brand..." "[Referrer] made the intro — so I'll skip the preamble and go straight to the structural problem..."

→ [See full before/after comparisons](examples/before-after/)


What This Does

This is a persona extraction workflow that analyzes your writing to build a "Digital Twin" — a System Prompt that makes any AI replicate your voice, judgment, and decision-making logic.

It's not a personality quiz. It reads how you actually communicate and extracts:

  • Linguistic Fingerprint — vocabulary, metaphor style, crutch words, formatting habits
  • Cognitive Pattern — how you organize information and solve problems
  • Decision Logic — the rules you use (consciously or not) to say yes or no
  • Knowledge Map — where you go deep vs. where you skim

Then it stress-tests the result to make sure it holds under pressure.

Three Depth Levels

Level Tool Data Source Depth
Layer 1 Any LLM (ChatGPT, Gemini, Claude, etc.) Paste your writing samples ~70%
Layer 2