clawtime
Set up and operate ClawTime — webchat interface for OpenClaw with passkey auth, 3D avatars, and voice mode.
Install
mkdir -p .claude/skills/clawtime && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8527" && unzip -o skill.zip -d .claude/skills/clawtime && rm skill.zipInstalls to .claude/skills/clawtime
About this skill
ClawTime Skill
Operational reference for ClawTime — webchat interface for OpenClaw.
Installation
For first-time setup (clone, configure, deploy), see INSTALL.md.
Operations
# Status & logs
systemctl --user status clawtime
journalctl --user -u clawtime -f
# Restart after config changes
systemctl --user restart clawtime
# Get current tunnel URL
journalctl --user -u clawtime-tunnel | grep trycloudflare | tail -1
Widgets
ClawTime supports interactive widgets for richer user interactions. Include widget markup in your response and it renders as a UI component.
Widget Syntax
[[WIDGET:{"widget":"TYPE","id":"UNIQUE_ID",...properties}]]
The markup is stripped from the displayed message and rendered as interactive UI.
Available Widgets
Buttons
[[WIDGET:{"widget":"buttons","id":"choice1","label":"Pick a color:","options":["Red","Green","Blue"]}]]
label— Prompt text above buttonsoptions— Array of button labels
Confirm
[[WIDGET:{"widget":"confirm","id":"delete1","title":"Delete file?","message":"This cannot be undone."}]]
title— Bold header textmessage— Description text- Renders Cancel and Confirm buttons
Progress
[[WIDGET:{"widget":"progress","id":"upload1","label":"Uploading...","value":65}]]
label— Description textvalue— Progress percentage (0-100)
Code
[[WIDGET:{"widget":"code","id":"snippet1","filename":"example.py","code":"print('Hello')","language":"python"}]]
filename— File name in headercode— The code contentlanguage— Syntax highlighting hint- Includes a Copy button
Form
[[WIDGET:{"widget":"form","id":"survey1","label":"Quick Survey","fields":[{"name":"email","label":"Email","type":"text"},{"name":"rating","label":"Rating","type":"text"}]}]]
label— Form titlefields— Array of{name, label, type}
Datepicker
[[WIDGET:{"widget":"datepicker","id":"date1","label":"Select date:"}]]
label— Prompt text
Widget Responses
When user interacts with a widget:
[WIDGET_RESPONSE:{"id":"choice1","widget":"buttons","value":"Red","action":"submit"}]
Best Practices
- Always use unique IDs — Each widget needs a distinct
id - Keep options concise — Button labels should be short
- Use widgets for structured input — Better than "type 1, 2, or 3"
- Acknowledge responses — Confirm what the user selected
Task Panel
ClawTime includes a task panel for tracking work. Use this as your canonical task list.
File Format
Tasks stored at ~/.clawtime/tasks.json in markdown format:
# Tasks
## Active
- 🟡 Task you're working on right now
## Blocked
- ⏳ Task waiting on someone else
## Backlog
- Task to do later
## Done
- ✅ Completed task
Section Meanings
| Section | Meaning |
|---|---|
| Active | Currently working on — doing NOW |
| Blocked | Waiting for input/dependency |
| Backlog | Will work on later |
| Done | Completed (hidden in UI) |
Task Icons
| Icon | Meaning |
|---|---|
| 🟡 | Active/pending |
| ⏳ | Blocked/waiting |
| ✅ | Completed |
- [x] | Also marks done |
Avatar Creation
ClawTime uses Three.js voxel avatars — 3D characters built from simple shapes that animate based on state.
Avatar Template
Create at ~/.clawtime/avatars/<name>.js:
/* AVATAR_META {"name":"MyAgent","emoji":"🤖","description":"Custom 3D avatar","color":"4f46e5"} */
(function() {
'use strict';
var scene, camera, renderer, character;
var head, leftEye, rightEye, mouth;
var clock = new THREE.Clock();
var currentState = 'idle';
var isInitialized = false;
// ─── Required: Initialize the 3D scene ───
window.initAvatarScene = function() {
if (isInitialized) return;
var container = document.getElementById('avatarCanvas');
if (!container) return;
scene = new THREE.Scene();
scene.background = new THREE.Color(0x0f1318);
var w = container.clientWidth, h = container.clientHeight;
camera = new THREE.PerspectiveCamera(40, w / h, 0.1, 100);
camera.position.set(0, 2, 8);
camera.lookAt(0, 0, 0);
renderer = new THREE.WebGLRenderer({ antialias: true });
renderer.setSize(w, h);
renderer.setPixelRatio(Math.min(window.devicePixelRatio, 2));
container.appendChild(renderer.domElement);
// Lighting
scene.add(new THREE.AmbientLight(0x606080, 1.5));
var light = new THREE.DirectionalLight(0xffffff, 2.0);
light.position.set(4, 10, 6);
scene.add(light);
// Build your character
character = new THREE.Group();
buildCharacter();
scene.add(character);
isInitialized = true;
animate();
};
function buildCharacter() {
var bodyMat = new THREE.MeshLambertMaterial({ color: 0x4f46e5 });
var body = new THREE.Mesh(new THREE.BoxGeometry(1.5, 2, 1), bodyMat);
body.position.y = 0;
character.add(body);
var headMat = new THREE.MeshLambertMaterial({ color: 0x4f46e5 });
head = new THREE.Mesh(new THREE.BoxGeometry(1.2, 1.2, 1), headMat);
head.position.y = 1.8;
character.add(head);
var eyeMat = new THREE.MeshBasicMaterial({ color: 0xffffff });
leftEye = new THREE.Mesh(new THREE.SphereGeometry(0.15), eyeMat);
leftEye.position.set(-0.25, 1.9, 0.5);
character.add(leftEye);
rightEye = new THREE.Mesh(new THREE.SphereGeometry(0.15), eyeMat);
rightEye.position.set(0.25, 1.9, 0.5);
character.add(rightEye);
var pupilMat = new THREE.MeshBasicMaterial({ color: 0x000000 });
mouth = new THREE.Mesh(new THREE.BoxGeometry(0.4, 0.1, 0.1), pupilMat);
mouth.position.set(0, 1.5, 0.5);
character.add(mouth);
}
function animate() {
requestAnimationFrame(animate);
var t = clock.getElapsedTime();
if (character) {
character.position.y = Math.sin(t * 2) * 0.05;
}
if (currentState === 'thinking') {
head.rotation.z = Math.sin(t * 3) * 0.1;
} else if (currentState === 'talking') {
mouth.scale.y = 1 + Math.sin(t * 15) * 0.5;
} else {
head.rotation.z = 0;
mouth.scale.y = 1;
}
renderer.render(scene, camera);
}
// ─── Required: Handle state changes ───
window.setAvatarState = function(state) {
currentState = state;
};
// ─── Required: Handle connection state ───
window.setConnectionState = function(state) {
// state: 'online', 'connecting', 'offline'
};
// ─── Required: Handle resize ───
window.adjustAvatarCamera = function() {
if (!renderer) return;
var container = document.getElementById('avatarCanvas');
var w = container.clientWidth, h = container.clientHeight;
camera.aspect = w / h;
camera.updateProjectionMatrix();
renderer.setSize(w, h);
};
})();
Set as Default
Create/update ~/.clawtime/config.json:
{
"selectedAvatar": "<name>"
}
Avatar States
Each state should be visually distinct with unique activities and indicators. Users should immediately recognize which state the avatar is in.
| State | Purpose | Design Ideas |
|---|---|---|
idle | Default, waiting | Breathing, looking around, show-off poses, occasional blink |
thinking | Processing request | Head tilt, eyes up, thought bubble (❓), tapping foot/wing |
talking | Delivering response | Mouth animation, speech bubble, music notes (🎵), gesturing |
listening | User is speaking | Leaning forward, BIG attentive eyes, ears/crest perked |
working | Extended task | Laptop/tools visible, typing motion, focused squint |
happy | Positive outcome | Bouncing, hearts (❤️), squinty smile eyes (^_^), wagging |
celebrating | Major success | Jumping, spinning, confetti (⭐), maximum energy |
sleeping | Inactive/idle timeout | Eyes closed, Z's floating (💤), curled up, slow breathing |
error | Something went wrong | Shaking, exclamation (❗), ruffled, sweat drop, red tint |
reflecting | Thoughtful moment | Light bulb (💡), gazing upward, calm pose, one hand raised |
State Design Principles
- Visual indicators matter — Add floating symbols (❓❤️💡❗💤⭐) that appear per-state
- Body language is key — Each state needs distinct posture, movement speed, and energy level
- Eyes tell the story — Big/small, open/closed, squinty/wide, pupil direction
- Movement rhythm varies — Fast/bouncy for happy, slow/gentle for sleeping, shaky for error
- Props add clarity — Laptop for working, floating Z's for sleeping, confetti for celebrating
- Think like a character animator — What would a Pixar character do in this state?
Creative Examples
Parrot avatar:
thinking→ Scratches head with foot, question mark floatstalking→ Beak opens/closes, music notes float uperror→ Feathers fly off, squawking pose, wings spread in alarmcelebrating→ Full party parrot spin, confetti everywhere
Salamander avatar:
thinking→ Flames pulse brighter, one foot tapssleeping→ Flames become tiny embers, curled uperror→ Flames turn red, whole body shakesreflecting→ Light bulb appears, one paw raised thoughtfully
Avatar Design Tips
- Study
~/.clawtime/avatars/for full-featured examples with all states - Use voxel style (boxes, spheres) — matches ClawTime aesthetic
- Implement all states with distinct visuals — don't make states look similar
- Add connection status indicator (ring/glow on platform)
- Test on desktop and mobile
- Keep polygon count reasonable for mobile performance
- Hide/show indicator objects per-state (don't create/destroy every frame)
Key Files
| Path | Purpose |
|---|---|
~/.clawtime/.env | Secrets & config |
~/.clawtime/config.json | Avatar selection, preferences |
~/.clawtime/credentials.json | Passkey data |
| `~/.clawtime/sessions.json |
Content truncated.
More by openclaw
View all skills by openclaw →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.
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.
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."
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.
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.
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.
Related MCP Servers
Browse all serversArize Phoenix — unified interface for managing prompts, exploring datasets, and running LLM experiments across providers
Desktop Commander MCP unifies code management with advanced source control, git, and svn support—streamlining developmen
Solana Agent Kit: Easily deploy tokens, mint NFTs, and manage DeFi & cross-chain tasks with Solana integration in chat i
Claude Code is an AI powered coding assistant that streamlines coding tasks, file ops, Git, and searches by auto-bypassi
Connect MongoDB databases to chat interfaces. Manage AWS with MongoDB, explore Atlas cost, and inspect collections secur
Interact with Kubernetes resources using natural language instead of complex kubectl commands. Simplify cluster manageme
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.