audio-room
Audio-only room with LiveKit — circular avatar grid, speaking indicators, raise hand queue. Twitter Spaces / Clubhouse style. Use this skill when the user says "add audio room", "audio chat", "voice room", "spaces", "clubhouse", or "audio-only room".
What this skill does
# Audio Room (LiveKit)
Audio-only room experience using [LiveKit](https://livekit.io). Participants appear as circular avatars in a grid layout with real-time speaking indicators (pulsing rings), raise hand queue, mute/deafen controls, and no video tracks published. Designed to feel like Twitter Spaces or Clubhouse.
## Prerequisites
- Next.js app with `src/` directory and App Router
- `video-room` skill applied (provides `livekit-client`, `@livekit/components-react`, LiveKit token server, and room connection infrastructure)
- `add-shadcn` skill applied (provides `Button`, `Badge`, `Card`, `Avatar`, `Tooltip` components)
## Installation
No additional packages required. Uses `livekit-client` and `@livekit/components-react` from the `video-room` skill.
## Environment Variables
Uses the same LiveKit environment variables from the `video-room` skill:
```env
LIVEKIT_API_KEY=your_api_key
LIVEKIT_API_SECRET=your_api_secret
NEXT_PUBLIC_LIVEKIT_URL=wss://your-project.livekit.cloud
```
## What Gets Created
```
src/
├── components/
│ └── video/
│ ├── audio-room.tsx # Audio-only room layout — circular avatar grid
│ ├── audio-controls.tsx # Mute, deafen, raise hand, leave controls
│ └── speaking-indicator.tsx # Pulsing ring animation for speaking state
└── lib/
└── video/
└── use-audio-room.ts # Hook: join room with audio-only config, speaking state
```
## Setup Steps
### Step 1: Create `src/lib/video/use-audio-room.ts`
```typescript
"use client";
import { useCallback, useEffect, useState } from "react";
import {
Room,
RoomEvent,
Track,
type RemoteParticipant,
type LocalParticipant,
type Participant,
type RoomOptions,
type AudioCaptureOptions,
ConnectionState,
} from "livekit-client";
type AudioParticipant = {
identity: string;
name: string;
isSpeaking: boolean;
isMuted: boolean;
isLocal: boolean;
audioLevel: number;
metadata: string | undefined;
};
type RaiseHandEntry = {
identity: string;
name: string;
raisedAt: number;
};
type UseAudioRoomOptions = {
token: string;
serverUrl: string;
onDisconnected?: () => void;
};
type UseAudioRoomReturn = {
room: Room | null;
participants: AudioParticipant[];
isConnected: boolean;
isConnecting: boolean;
isMuted: boolean;
isDeafened: boolean;
handRaised: boolean;
raiseHandQueue: RaiseHandEntry[];
toggleMute: () => Promise<void>;
toggleDeafen: () => void;
toggleRaiseHand: () => void;
disconnect: () => void;
};
const RAISE_HAND_EVENT = "raise-hand";
const LOWER_HAND_EVENT = "lower-hand";
function participantToAudio(
participant: Participant,
isLocal: boolean
): AudioParticipant {
const audioPublication = participant.getTrackPublications().find(
(pub) => pub.track?.kind === Track.Kind.Audio
);
return {
identity: participant.identity,
name: participant.name ?? participant.identity,
isSpeaking: participant.isSpeaking,
isMuted: audioPublication?.isMuted ?? true,
isLocal,
audioLevel: participant.audioLevel,
metadata: participant.metadata,
};
}
export function useAudioRoom({
token,
serverUrl,
onDisconnected,
}: UseAudioRoomOptions): UseAudioRoomReturn {
const [room, setRoom] = useState<Room | null>(null);
const [participants, setParticipants] = useState<AudioParticipant[]>([]);
const [isConnected, setIsConnected] = useState(false);
const [isConnecting, setIsConnecting] = useState(false);
const [isMuted, setIsMuted] = useState(false);
const [isDeafened, setIsDeafened] = useState(false);
const [handRaised, setHandRaised] = useState(false);
const [raiseHandQueue, setRaiseHandQueue] = useState<RaiseHandEntry[]>([]);
const updateParticipants = useCallback((currentRoom: Room) => {
const local = participantToAudio(currentRoom.localParticipant, true);
const remotes = Array.from(currentRoom.remoteParticipants.values()).map(
(p) => participantToAudio(p, false)
);
setParticipants([local, ...remotes]);
}, []);
useEffect(() => {
if (!token || !serverUrl) return;
const roomOptions: RoomOptions = {
audioCaptureDefaults: {
autoGainControl: true,
echoCancellation: true,
noiseSuppression: true,
} satisfies AudioCaptureOptions,
adaptiveStream: false,
};
const newRoom = new Room(roomOptions);
setRoom(newRoom);
setIsConnecting(true);
const handleParticipantChange = () => updateParticipants(newRoom);
const handleActiveSpeakersChanged = (speakers: Participant[]) => {
void speakers;
updateParticipants(newRoom);
};
const handleDisconnected = () => {
setIsConnected(false);
setIsConnecting(false);
setParticipants([]);
setRaiseHandQueue([]);
onDisconnected?.();
};
const handleDataReceived = (
payload: Uint8Array,
participant?: RemoteParticipant
) => {
const decoder = new TextDecoder();
const message = decoder.decode(payload);
if (message === RAISE_HAND_EVENT && participant) {
setRaiseHandQueue((prev) => {
if (prev.some((entry) => entry.identity === participant.identity)) {
return prev;
}
return [
...prev,
{
identity: participant.identity,
name: participant.name ?? participant.identity,
raisedAt: Date.now(),
},
];
});
}
if (message === LOWER_HAND_EVENT && participant) {
setRaiseHandQueue((prev) =>
prev.filter((entry) => entry.identity !== participant.identity)
);
}
};
newRoom.on(RoomEvent.ParticipantConnected, handleParticipantChange);
newRoom.on(RoomEvent.ParticipantDisconnected, handleParticipantChange);
newRoom.on(RoomEvent.TrackSubscribed, handleParticipantChange);
newRoom.on(RoomEvent.TrackUnsubscribed, handleParticipantChange);
newRoom.on(RoomEvent.TrackMuted, handleParticipantChange);
newRoom.on(RoomEvent.TrackUnmuted, handleParticipantChange);
newRoom.on(RoomEvent.ActiveSpeakersChanged, handleActiveSpeakersChanged);
newRoom.on(RoomEvent.Disconnected, handleDisconnected);
newRoom.on(RoomEvent.DataReceived, handleDataReceived);
newRoom
.connect(serverUrl, token)
.then(() => {
setIsConnected(true);
setIsConnecting(false);
// Publish audio only — no video
return newRoom.localParticipant.setMicrophoneEnabled(true);
})
.then(() => {
updateParticipants(newRoom);
})
.catch((err: unknown) => {
console.error("Failed to connect to audio room:", err);
setIsConnecting(false);
});
return () => {
newRoom.off(RoomEvent.ParticipantConnected, handleParticipantChange);
newRoom.off(RoomEvent.ParticipantDisconnected, handleParticipantChange);
newRoom.off(RoomEvent.TrackSubscribed, handleParticipantChange);
newRoom.off(RoomEvent.TrackUnsubscribed, handleParticipantChange);
newRoom.off(RoomEvent.TrackMuted, handleParticipantChange);
newRoom.off(RoomEvent.TrackUnmuted, handleParticipantChange);
newRoom.off(RoomEvent.ActiveSpeakersChanged, handleActiveSpeakersChanged);
newRoom.off(RoomEvent.Disconnected, handleDisconnected);
newRoom.off(RoomEvent.DataReceived, handleDataReceived);
if (newRoom.state !== ConnectionState.Disconnected) {
newRoom.disconnect();
}
};
}, [token, serverUrl, updateParticipants, onDisconnected]);
const toggleMute = useCallback(async () => {
if (!room) return;
const newMuted = !isMuted;
await room.localParticipant.setMicrophoneEnabled(!newMuted);
setIsMuted(newMuted);
}, [room, isMuted]);
const toggleDeafen = useCallback(() => {
if (!room) return;
const newDeafened = !isDeafened;
setIsDeafened(newDeafened);
// Enable/disable all remote audio track publications using RemoteParticipant's Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.