A floating, animated desktop avatar that visualizes your AI agent's emotions, tasks, and real-time status.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install claw-face
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 claw-face using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
ClawFace is a cross-platform visual feedback widget designed to give your AI assistants a tangible presence. By integrating with Openclaw Skills, it translates abstract agent operations into relatable animations, allowing developers to see exactly what their agent is feeling or doing at any given moment. Whether the agent is deep in thought, actively coding, or celebrating a successful task completion, ClawFace ensures you are never left guessing about the current state of your automation.
This tool is especially valuable for power users who maintain dedicated AI workstations. It offers a sophisticated layering system consisting of 9 distinct emotions, 9 functional actions, and 15 immersive visual effects. This creates a high-fidelity feedback loop that improves the transparency and engagement of local AI agent interactions.
Ensure Python and tkinter are installed on your system. To integrate with your existing Openclaw Skills environment, use the following commands:
# Verify tkinter installation
python3 -c "import tkinter; print('OK')"
# Enable the automatic thinking hook
cp -r SKILL_PATH/hooks/clawface-thinking ~/.openclaw/hooks/
openclaw hooks enable clawface-thinking
# Start the avatar in robot mode
python3 SKILL_PATH/scripts/avatar.py --mode robot &
The core state is managed via a JSON object which determines the visual output. This allows any external process within the Openclaw Skills ecosystem to control the avatar.
| Key | Allowed Values | Purpose |
|---|---|---|
emotion |
happy, thinking, proud, confused, etc. | Sets the facial expression |
action |
coding, searching, loading, speaking, etc. | Sets the activity animation |
effect |
matrix, radar, brainwave, fire, etc. | Sets the background visual vibe |
message |
Any string | Displays custom text feedback |
Loading
A dedicated monitoring tool to track and analyze token consumption across all Openclaw Skills sessions and sub-agents.

A defense-in-depth security layer that sanitizes external AI skills by regenerating them from scratch to eliminate hidden prompt injection and malicious payloads.

A specialized CLI tool for Openclaw Skills designed to analyze, compress, and optimize token consumption in AI agent sessions.

A specialized skill for building award-winning, immersive web experiences with advanced animations, creative interactions, and high-end visual storytelling.

ClawSmith is a comprehensive automation engine designed to help developers build, secure, and optimize high-quality Openclaw Skills with a single command.

A privacy-first AI agent skill that transforms a single piece of content into over seven platform-optimized formats entirely on your local machine.








































