building-livekit-agents SKILL.md skillA

building-livekit-agents from fcakyon/claude-codex-settings is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add fcakyon/claude-codex-settings/building-livekit-agents@git:20261026.312fc10

Pins git:20261026.312fc10 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
fcakyon/claude-codex-settings
Path
plugins/livekit-skills/skills/building-livekit-agents/SKILL.md
Versions recorded
2
Latest version
git:20261026.312fc10, committed Oct 26, 2026
First version recorded
Oct 1, 2026
Size
10,885 bytes
Repository stars
1,200
License
Apache-2.0

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…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Building LiveKit agents

This skill covers how to structure a voice agent. It has no API specifics, because those change;
get them from `reading-livekit-docs`.

Where the agent runs and which LiveKit the project uses are separate questions. An agent the user
self-hosts (on their own servers instead of LiveKit Cloud's agent hosting) still connects to LiveKit
Cloud and can still use LiveKit Inference. Inference is a LiveKit Cloud feature, so it's only off
the table when the project runs on LiveKit OSS. The architecture advice applies either way; on
LiveKit OSS, models come from each provider's own plugin and API keys.

## Models: default to LiveKit Inference

Use LiveKit Inference for each model that the agent uses: STT, LLM, TTS, or a realtime model. Many
examples, and much of the LiveKit code that you remember, use a provider plugin for each model. Do
not copy that pattern. Inference is better for these reasons:

- **No extra credentials.** Inference uses the LiveKit Cloud credentials the agent already has. A
  plugin needs its own provider account, plus an API key in every environment the agent runs in.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add fcakyon/claude-codex-settings/building-livekit-agents@sha256:e004d7d2f4ce27ba

The line at the top of this page pins the label git:20261026.312fc10, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lxavdyae6wvutuhc.svg)](https://markdownregistry.com/a/art_lxavdyae6wvutuhc)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Oct 1, 2026 and Oct 26, 2026, about one every 25 days.

versioncommittedcommitsizeaudit
git:20261026.312fc10 latest2026-10-26 312fc10 10,885 BA view · diff
git:20261001.f7836da2026-10-01 f7836da 9,487 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10885 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

fcakyon/claude-codex-settings · 1,200 stars · license Apache-2.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lxavdyae6wvutuhc
GET https://markdownregistry.com/api/v1/resolve?ref=fcakyon/claude-codex-settings/building-livekit-agents
GET https://markdownregistry.com/api/v1/blob/e004d7d2f4ce27baa3da515bed504e2b072dcfec18688051a05923f4ab70a0d6

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from fcakyon/claude-codex-settings

CLAUDE.md@.claude CLAUDE.md file
fcakyon/claude-codex-settings · .claude/CLAUDE.md
git:20261107.0574bbb · audit A · 1,200 stars
AGENTS.md AGENTS.md file
fcakyon/claude-codex-settings · AGENTS.md
git:20251004.951ae6c · audit B · 1,200 stars
CLAUDE.md CLAUDE.md file
fcakyon/claude-codex-settings · CLAUDE.md
git:20261108.4e309a7 · audit A · 1,200 stars
adhd-output-style SKILL.md skill
fcakyon/claude-codex-settings · plugins/adhd-output-style/skills/adhd-output-style/SKILL.md · This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited…
git:20260721.7c9b5ff · audit A · 1,200 stars
aeo SKILL.md skill
fcakyon/claude-codex-settings · plugins/aeo/skills/aeo/SKILL.md · This skill should be used when the user asks to "build an AEO strategy", "improve AI search visibility", "track buyer…
git:20261028.a9921a5 · audit A · 1,200 stars
agent-browser SKILL.md skill
fcakyon/claude-codex-settings · plugins/agent-browser/skills/agent-browser/SKILL.md · Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow…
git:20261026.312fc10 · audit A · 1,200 stars
derive-client SKILL.md skill
fcakyon/claude-codex-settings · plugins/agent-browser/skills/derive-client/SKILL.md · Reverse-engineer a website's internal API by recording browser traffic into a HAR file, then generate a standalone…
git:20261001.f7836da · audit A · 1,200 stars
dogfood SKILL.md skill
fcakyon/claude-codex-settings · plugins/agent-browser/skills/dogfood/SKILL.md · Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to…
git:20261001.f7836da · audit A · 1,200 stars
electron SKILL.md skill
fcakyon/claude-codex-settings · plugins/agent-browser/skills/electron/SKILL.md · Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome…
git:20260401.ce7d4ce · audit A · 1,200 stars
ui-regression SKILL.md skill
fcakyon/claude-codex-settings · plugins/agent-browser/skills/ui-regression/SKILL.md · This skill should be used when the user asks to "verify UI changes", "audit UI quality", "test every screen and…
git:20261028.7007d7e · audit A · 1,200 stars
webmcp-gen SKILL.md skill
fcakyon/claude-codex-settings · plugins/agent-browser/skills/webmcp-gen/SKILL.md · Build and validate experimental WebMCP tools for an existing web page. Use when an agent needs to expose a site's real…
git:20261001.f7836da · audit A · 1,200 stars
docx SKILL.md skill
fcakyon/claude-codex-settings · plugins/anthropic-office-skills/skills/docx/SKILL.md · Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word…
git:20260720.d26d2c8 · audit A · 1,200 stars

Every file in fcakyon/claude-codex-settings

Other files named building-livekit-agents

building-livekit-agents SKILL.md skill
livekit/agent-skills · skills/building-livekit-agents/SKILL.md · Builds voice and chat AI agents with LiveKit Agents and LiveKit Cloud. Use when the user asks to "build a voice agent"…
git:20261021.e1195b4 · audit A · 74 stars

Browse by kind, by grade A, or by owner.