Agent skill · AI & Agents

livekit-skills

Build voice AI agents with LiveKit Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Covers both LiveKit Cloud and self-hosted deployments using lk CLI.

fcakyongithub.com/fcakyonGitHub ↗
claude-codecodexcursorApache-2.0
Install
npx skills add fcakyon/claude-codex-settings --skill livekit-skills --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 5
SKILL.md size: 14 KB
Bundled scripts: none
Version: 0.3.1
Declared author: livekit
Path: plugins/livekit-skills/skills/livekit-skills/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 967
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# LiveKit Voice Agent Development This skill provides guidance for building voice AI agents with the LiveKit Agents SDK. It covers both LiveKit Cloud and self-hosted deployments, using the `lk` CLI for documentation access and project management. All factual information about APIs, methods, and configurations must come from live documentation. ## MANDATORY: Read This Checklist Before Starting Before writing ANY code, complete this checklist: 1. **Read this entire skill document** - Do not skip sections 2. **Set up LiveKit credentials** (Cloud project or self-hosted server) - You need `LIVEKIT_URL`, `LIVEKIT_API_KEY`, and `LIVEKIT_API_SECRET` 3. **Set up documentation access** - Install `lk` CLI for `lk docs` commands 4. **Plan to write tests** - Every agent implementation MUST include tests (see testing section below) 5. **Verify all APIs against live docs** - Never rely on model memory for LiveKit APIs ## Setup ### LiveKit Cloud LiveKit Cloud is the fastest way to get a voice agent running. It provides: - Managed infrastructure (no servers to deploy) - **LiveKit Inference** for AI models (no separate API keys needed) - Built-in noise cancellation, turn detection, and other voice f

What's inside
Steps it walks through
  1. MANDATORY: Read This Checklist Before Starting
  2. Setup
  3. LiveKit Cloud
  4. Connect to Your Cloud Project
  5. Use LiveKit Inference for AI Models
  6. Self-Hosted Setup
  7. Using Your Own Model Providers
  8. Project Templates
  9. Critical Rule: Never Trust Model Memory for LiveKit APIs
  10. Use LiveKit CLI for Documentation
  11. Search documentation
  12. Fetch specific pages
  13. Search SDK source code
  14. Check changelogs
Ships with 4 files
  • references/agent-tools.md
  • references/cli-reference.md
  • references/quickstart.md
  • references/self-hosting.md
Commands it runs
livekit-server --dev
STT (Speech-to-Text)
LLM
TTS (Text-to-Speech)
or
lk agent init my-agent --template agent-starter-python
lk agent init my-agent --template agent-starter-node
lk agent init my-frontend --template agent-starter-react
lk agent init my-frontend --template agent-starter-react-native
lk docs search "voice agent quickstart"
More from claude-codex-settings
All skills →
About this skill
What does the livekit-skills skill do?

Build voice AI agents with LiveKit Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Covers both LiveKit Cloud and self-hosted deployments using lk CLI.

How do I install it?

Run `npx skills add fcakyon/claude-codex-settings --skill livekit-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From fcakyon/claude-codex-settings, a repository with 967 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going