Setup & Installation
openclaw skills install @mkoslacz/claw-face
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install claw-face
What This Skill Does
Floating avatar widget that displays an AI agent's current emotion, active action, and visual effect in a draggable desktop window. State is controlled by writing JSON to ~/.clawface/avatar_state.json. Supports 9 emotions, 9 actions, and 15 visual effects across two display modes.
Replaces log-watching with a live visual indicator that shows exactly what an agent is doing at a glance, without parsing terminal output.
When to use it
- Watching agent progress on a dedicated monitor without reading logs
- Auto-showing a thinking animation at the start of each agent turn
- Displaying confetti or fire effects when a long task finishes
- Demoing an AI assistant live to coworkers
- Tracking agent state across reading, searching, coding, and speaking phases
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: 'Search the web and summarize the latest AI news'
AGENT
- 1Sets emotion 'thinking', action 'reading' while parsing the request
- 2Updates to emotion 'thinking', action 'searching' with 'radar' effect during web search
- 3Switches to emotion 'happy', action 'coding' with 'typing' effect while drafting the summary
- 4Updates to emotion 'happy', action 'speaking' with 'soundwave' effect when sending the reply
- 5Returns to emotion 'neutral', action 'idle' after the response is delivered
OUTPUT
Avatar cycles through visible states in real time, reflecting each phase of the agent's work