clawface

29
2
Source

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".

Install

mkdir -p .claude/skills/clawface && curl -L -o skill.zip "https://mcp.directory/api/skills/download/4355" && unzip -o skill.zip -d .claude/skills/clawface && rm skill.zip

Installs to .claude/skills/clawface

About this skill

🤖 ClawFace

Give your OpenClaw a face!


Got a dedicated machine running OpenClaw with a monitor? Tired of staring at logs all day?

Give your agent a personality!

  • 9 emotions — from happy to angry, thinking to proud
  • 9 actions — coding, searching, reading, speaking...
  • 15 visual effects — matrix rain, fire, confetti, radar scan...

That's 1,215 unique combinations + custom messages from your agent!

Perfect for:

  • 💻 Laptop setups where you want to SEE your agent working
  • 🖥️ Dedicated OpenClaw machines with a monitor
  • 🎮 Making your AI assistant feel alive
  • 📺 Impressing your friends/coworkers

⚠️ Note: Only tested on macOS. Should work on Windows/Linux but YMMV.


🚀 Quick Test (try it now!)

# 1. Check if you have Python + tkinter:
python3 -c "import tkinter; print('Ready!')"

Terminal 1 — Run ClawFace:

python3 SKILL_PATH/scripts/avatar.py --mode robot

Terminal 2 — Run Demo:

python3 SKILL_PATH/scripts/avatar.py --demo

Watch the avatar cycle through all emotions, actions, and effects automatically! 🎉

Manual control:

echo '{"emotion":"excited","action":"success","effect":"confetti","message":"It works!"}' > ~/.clawface/avatar_state.json

⚠️ Requirements

Python 3.10+ with tkinter:

# Check:
python3 -c "import tkinter; print('OK')"

# Install if missing:
# macOS:   brew install [email protected]
# Ubuntu:  sudo apt install python3-tk
# Windows: reinstall Python, check "tcl/tk and IDLE" during install

📦 Full Installation

1. Install the auto-thinking hook (recommended):

cp -r SKILL_PATH/hooks/clawface-thinking ~/.openclaw/hooks/
openclaw hooks enable clawface-thinking

This makes the avatar show "thinking" automatically when a turn starts — no delay!

2. Launch the avatar:

nohup python3 SKILL_PATH/scripts/avatar.py --mode robot > /dev/null 2>&1 &

Note: Replace SKILL_PATH with actual path, e.g., /usr/local/lib/node_modules/openclaw/skills/clawface


🎯 Core Principle: BE DYNAMIC!

Don't set one state and forget it. Update the avatar continuously as you work:

User asks question
  → thinking/reading    (reading their message)
  → thinking/thinking   (analyzing)
  → happy/speaking      (formulating response)  
  → neutral/idle        (sent, waiting)

Every action you take should be reflected. The avatar is your LIVE status indicator.


🎭 State Reference

Emotions

EmotionUse when...
neutralDefault, waiting
thinkingProcessing, analyzing
happyThings going well
excitedBig win, celebration
proudPersonal achievement
confusedUncertain, unexpected
tiredLong task
sadFailed despite trying
angryError, frustration

Actions

ActionUse when...
idleWaiting for user
readingReading files/docs
thinkingAnalyzing, planning
searchingWeb search, grep
codingWriting code
loadingRunning commands
speakingSending response
successCompleted task
errorSomething failed

Effects

EffectVibe
noneClean, minimal
matrixTechy, data flow
radarScanning, searching
brainwaveDeep thinking
typingWriting
soundwaveSpeaking
gearMechanical work
fireIntense, productive
lightningFast, powerful
confettiCelebration!
heartAffection
glitchError, broken
sparklesMagic
pulseActive but calm
progressbar:XXProgress (0-100)

⚡ Best Practices

🔴 MINIMUM FLOW FOR EVERY RESPONSE:

thinking  →  processing user input
speaking  →  sending your reply  
idle      →  done, waiting

This is mandatory. Every single reply should show this progression.

Tips:

  1. Update BEFORE each action — set reading before you read
  2. Update AFTER completion — show success/error, then idle
  3. Match intensity — small task = subtle, big task = expressive
  4. Always return to idle — when waiting for user

🔧 Technical Reference

State File

Write JSON to ~/.clawface/avatar_state.json:

{
  "emotion": "happy",
  "action": "coding",
  "effect": "fire",
  "message": "Building something awesome!"
}

Display Modes

🤖 Robot Mode (--mode robot) — default

  • LED-style pixel eyes with animations
  • Mechanical arms with claws
  • Retro-futuristic cyberpunk vibe
  • Best for: tech aesthetic, dedicated screens

😊 Face Mode (--mode face)

  • Simplified cartoon face
  • Expressive eyes and mouth
  • Friendly, approachable look
  • Best for: casual use, smaller windows

Switch modes with buttons in the UI or restart with different --mode.

Window Controls

  • Drag to move
  • Drag edges to resize
  • F for fullscreen
  • Q to quit

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

1,6831,428

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

1,2601,319

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

1,5271,144

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

1,350807

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

1,262727

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

1,474681