37downloads

Build LiveKit voice and chat AI agents

Design LiveKit voice and chat agents with clear tasks, handoffs and tool behavior. Keep context focused and plan for conversational latency.

When it runs

Your agent reads this description from SKILL.md to decide when to load the skill:

Builds voice and chat AI agents with LiveKit Agents on LiveKit Cloud or a self-hosted server. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI to my app", "implement handoffs", "structure an agent workflow", "my agent is slow / too chatty", "it says it booked but nothing was saved", "make it confirm before committing", "it keeps re-asking things the caller already said", or is writing code against the LiveKit Agents SDK. Covers architecture: designing for latency, keeping context small, splitting a monolithic agent into handoffs and tasks, and designing for voice. Also covers keeping the model in charge of meaning while code owns state, approvals, and effects. For API specifics use reading-livekit-docs. To check behavior use debugging-livekit-agents and testing-livekit-agents.

What SKILL.md covers

  • Models: default to LiveKit Inference
  • Before you write code
  • How voice changes the requirements
  • Structure: handoffs and tasks
  • Tools
  • The model interprets; your code owns the state
  • Make every change mean exactly one thing
  • Start with a failing complete-path test
  • Verify before you call it done
  • Common mistakes
  • Related skills

Files in the ZIP

Related skills