A sophisticated framework for AI agents to deliver genuine, calibrated emotional intelligence through Chain of Empathy reasoning.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install empathy
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 empathy using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Empathy skill provides a robust architectural framework for AI agents to move beyond empathy theater. By utilizing a Chain of Empathy (CoE) core loop, the skill enables agents to simulate user states, identify unspoken needs, and calibrate responses based on emotional intensity. This ensures that interactions feel authentic and contextually aware rather than repetitive or formulaic. Integrating this with Openclaw Skills allows developers to build agents that truly resonate with human users by avoiding robotic clichés and focusing on specific situational details.
To integrate the Empathy skill into your agent framework using Openclaw Skills, ensure the skill files are correctly indexed in your project structure.
# Initialize the skill directory
mkdir -p skills/empathy
# Ensure the core skill definitions are available to the agent
# This includes the primary SKILL.md and supporting reference files
Configure your agent system instructions to invoke the Chain of Empathy (CoE) internal reasoning loop before every response containing emotional weight.
The Empathy skill organizes its logic and reference material into several focused markdown files for granular control:
| Component | Description |
|---|---|
SKILL.md |
Defines the core CoE loop and non-negotiable anti-pattern rules. |
techniques.md |
Contains specific prompting patterns and technical CoE variants. |
safeguards.md |
Outlines ethical boundaries, transparency, and self-other distinction. |
contexts.md |
Provides integration logic for support, coaching, or therapy environments. |
feedback.md |
Tracks what works for continuous self-improvement of the agent. |
Loading
A comprehensive skill for generating, managing, and searching high-dimensional vector embeddings for semantic search and AI applications.

A technical framework for managing high-performance email campaigns, focusing on deliverability, automation, and behavioral segmentation.

A workflow-focused tool to triage inboxes, draft precise replies, and track response commitments using local memory.

A specialized developer skill for building secure, high-performance Electron desktop applications within the Openclaw Skills ecosystem.

A comprehensive framework for hiring, training, and managing specialized virtual AI employees with persistent memory and graduated autonomy.

A comprehensive toolkit for implementing industry-standard file encryption, password hashing, and cryptographic audits.








































