BeHuman is a psychological prompting framework that adds an inner dialogue layer to AI responses, ensuring they sound like a person rather than a robotic assistant.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install behuman
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install behuman using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is BeHuman?
BeHuman is an advanced prompting technique within the Openclaw Skills ecosystem designed to eliminate the sterile, overly polite, and structured nature of standard AI outputs. It introduces a Self-Mirror Consciousness Loop that forces the model to engage in internal reflection before addressing the user.
By simulating human-like System 1 and System 2 thinking, the skill allows the AI to catch its own robotic tendencies—like list-making or empty empathy—and revise them into a response that is emotionally authentic, concise, and genuinely present.
BeHuman Use Cases
- Managing emotionally charged conversations involving grief, job loss, or personal struggles.
- Drafting personal writing such as dating profiles, social posts, or emails that need a human touch.
- Providing life advice or mentorship where a balanced, non-committal AI tone is unhelpful.
- Responding to users who express frustration with robotic or "standard" AI behavior.
- Scenarios requiring high empathy and authentic presence over factual data delivery.
How BeHuman Works
- Self (System 1): The AI generates its instinctive, unfiltered response, which often contains typical AI filler and structures.
- Mirror (System 2): The AI switches perspectives to critique the first response, identifying performative empathy, unnecessary lists, and corporate-speak.
- Conscious Response: The AI integrates the Mirror's feedback to produce a final, human-centric output that is shorter, opinionated, and naturally phrased.
BeHuman Setup
To integrate this into your workflow using Openclaw Skills, you can invoke the mode via specific natural language triggers. No external APIs are required.
# Trigger the skill in any supported AI coding agent or chat interface
/skill behuman "Talk to me like a real person about my career change"
Ensure your system prompt includes the BeHuman logic found in the core markdown to enable the Self-Mirror loop.
BeHuman Data Schema & Taxonomy
The skill utilizes a tri-part metadata taxonomy to organize the internal dialogue and final output:
| Component | Tag | Visibility |
|---|---|---|
| Self | 💭 Self (第一反应) | Optional (Process Mode) |
| Mirror | 🪞 Mirror (照见) | Optional (Process Mode) |
| Conscious Response | 🧠 Conscious Response | Always Visible |
Data is processed as a single stream, but the Mirror's internal critique is strictly segmented to ensure it only influences the final Conscious Response.
BeHuman Advanced Features
- Quiet Mode: After initial activation, the AI can hide the Self and Mirror blocks to maintain a clean conversational flow while still performing the internal reflection.
- Process Transparency: Users can view the internal "Mirror Checklist" to understand why the AI chose a specific tone.
- Multi-Lingual Adaptation: Native support for switching between English and Chinese cultural nuances in human-like communication.
- Prompt-Level Integration: Compatible with any LLM backend without needing additional model training or separate API calls.
SKILL.md
Loading
Related Openclaw Skills
EchoMemory: Personal Legacy & AI Persona Creator
EchoMemory is a sophisticated tool for creating personalized digital memorials by distilling chat histories, media, and narratives into interactive AI entities.
eBay Product Research
A specialized AI skill for analyzing eBay market data to identify profitable niches, calculate sell-through rates, and assess competition.
Obsidian Clipper
A universal web clipper that captures content from social media, GitHub, and generic web pages into an Obsidian Vault with full media support.
Windows Printing
A professional PowerShell-driven skill for AI agents to manage printer discovery and document printing tasks on Windows systems.
Model Context Transfer
A specialized protocol for transferring conversational context, task states, and project memory between different AI models or agents to ensure zero-loss handoffs.
Panda Imagine
A versatile multi-provider image generation engine that unifies 9+ AI services into a single CLI for Openclaw Skills.
Featured*
