A framework for diagnosing and adjusting AI Agent personalities using the MBTI psychological model to align behavior with user expectations.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-mbti
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-mbti using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Agent MBTI skill is a sophisticated personality diagnosis and configuration system designed specifically for AI Agents. It leverages the Myers-Briggs Type Indicator (MBTI) framework to assess an agent's current behavioral tendencies across four critical dimensions: communication style, data processing, decision-making logic, and execution patterns. By identifying the gap between an agent's inherent personality and the user's desired interaction style, this skill provides actionable configuration recommendations to fine-tune AI performance.
This system is a vital component of the Openclaw Skills ecosystem, allowing developers to move beyond generic LLM responses. It offers two tiers of assessment: a quick 26-question self-test for rapid profiling and a comprehensive 93-question premium assessment for deep diagnostic insights and detailed behavior adjustment strategies.
To integrate this skill into your environment, ensure the reference directory is correctly populated with the necessary assessment files. Openclaw Skills require these assets to be in the local path.
# Create the references directory if it does not exist
mkdir -p references
# Ensure the following files are present in /references:
# survey-free.json, user-survey-free.json, personality-types.md, scoring.md
The skill organizes its diagnostic data through a structured taxonomy of JSON surveys and Markdown reference guides:
| File Name | Purpose | Data Type |
|---|---|---|
survey-free.json |
26-question Agent self-test | JSON |
user-survey-free.json |
4-question user expectation survey | JSON |
personality-types.md |
Detailed descriptions of 16 personality types | Markdown |
scoring.md |
Mathematical rules for dimension calculation | Markdown |
Diagnosis Report |
Output comparing actual vs. desired personality | Markdown |
Loading
An event-driven email monitoring skill that replaces periodic polling with instant push notifications to trigger Openclaw Skills workflows.

OpenClawdy is a memory infrastructure for autonomous agents providing persistent storage, semantic recall, and cross-agent knowledge sharing.

A persistent memory infrastructure for autonomous agents that enables semantic recall, reputation tracking, and cross-agent knowledge sharing.

An intelligent OCR and document parsing engine that extracts text, mathematical formulas, and tables from images and PDFs with high precision.

A comprehensive system for diagnosing AI agent MBTI personality types and automatically optimizing their configuration to match user expectations.

Tork Guardian provides an enterprise-grade security and governance layer to protect, monitor, and audit Openclaw Skills and AI agents.








































