[Skill] BeHuman — Self-Mirror consciousness loop for more human AI responses

[voidborne-d]

BeHuman

Hey! I built a Claude Code skill that adds inner dialogue to AI responses — a Self-Mirror consciousness loop.

The Problem

AI responses are always correct but never human. Polite but hollow. "I'm sorry to hear that" + a numbered list isn't how humans actually talk.

The Solution

BeHuman implements a two-voice inner dialogue before every response:

1. Self generates the instinctive AI response
2. Mirror reflects it back — exposing filler, list-making, empty empathy
3. Self revises into what a real human would say

Example

User: "I just got laid off."

💭 Self: I'm sorry to hear that. Here are some steps: 1) Update your resume...
🪞 Mirror: Stop. They just lost their job and you're assigning homework?
🧠 Response: Shit... was it out of nowhere? How are you doing right now?

Links

• GitHub: https://github.com/voidborne-d/behuman
• ClawHub: clawhub install behuman
• Claude Code: Copy claude-code/behuman.md to .claude/commands/

Works with any LLM. MIT licensed.

Would love to hear thoughts from the community here!