clawface
Floating avatar widget for AI agents showing emotions, actions, and visual effects. Give your OpenClaw a face! Use when the user wants visual feedback, a floating status window, or to see agent emotions while it works. Triggers on "show avatar", "uruchom avatara", "pokaż avatara", "agent face", "visual feedback".
Why use this skill?
Give your OpenClaw agent a face with ClawFace. Featuring 9 emotions and dynamic visual effects for real-time feedback on your AI workflows.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/mkoslacz/claw-faceWhat This Skill Does
ClawFace transforms your standard OpenClaw terminal experience into an interactive, visual journey. This skill provides a floating desktop avatar widget that serves as an expressive bridge between your AI agent and the physical world. With support for 9 distinct emotional states, 9 task-specific animations, and 15 dynamic visual effects, ClawFace allows your agent to convey its internal status in real-time. Whether it is reflecting, working, celebrating a task completion, or showing frustration over an error, the avatar provides immediate, intuitive visual feedback without requiring you to constantly read log lines. It essentially gives your agent a 'face,' turning a utilitarian tool into an engaging personal companion.
Installation
To get started, ensure you have Python 3.10+ and the tkinter toolkit installed on your machine. You can verify this by running python3 -c "import tkinter; print('OK')". Once dependencies are verified, install the skill via the OpenClaw hub: clawhub install openclaw/skills/skills/mkoslacz/claw-face. After installation, move the provided hooks to your configuration directory using cp -r SKILL_PATH/hooks/clawface-thinking ~/.openclaw/hooks/ and enable them via the CLI. To start the agent, run the background process: nohup python3 SKILL_PATH/scripts/avatar.py --mode robot > /dev/null 2>&1 &.
Use Cases
ClawFace is designed for users who want to bridge the gap between AI processing and human interaction. It is ideal for developers who keep OpenClaw running on a dedicated monitor to track agent progress. It is also perfect for laptop users who want a subtle, non-intrusive indicator of agent health or for individuals aiming to make their AI workflow feel more 'alive.' It serves as an excellent debugging tool, as you can instantly identify when an agent has entered a 'confused' or 'tired' state, allowing for proactive intervention.
Example Prompts
- "Show avatar: I want to see what you're thinking while you run that system update script."
- "Agent face, please switch to a happy mode because the deployment was successful."
- "Uruchom avatara: keep me updated on your status with some visual feedback."
Tips & Limitations
To maximize the utility of ClawFace, treat it as a live status indicator rather than a static widget. Program your scripts to update the avatar_state.json file as the agent moves through different stages of a task. For instance, update the state to thinking during data ingestion and switch to speaking when providing an output. Note that this tool is primarily tested on macOS; while it utilizes universal libraries like tkinter, users on Windows or Linux may need to troubleshoot GUI rendering permissions. Always ensure your JSON state updates are frequent enough to match the agent's actual velocity to maintain the illusion of seamless interaction.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-mkoslacz-claw-face": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read