# Troubleshoot LiveKit Letta Voice Agents

Voice agent failures are hard to diagnose when audio, WebRTC, tokens, and process state interact. This skill gives focused checks, workflows, and helper scripts for LiveKit and Letta debugging.

## Install

```bash
npx skillstore add egadams/voice-agent-expert
```

## Metadata

- Status: approved
- Slug: egadams-voice-agent-expert
- Skillstore revision: r1
- Version status: missing
- Tree hash: 3de833f0b449f74cddbfc9fe42ececf24bd942b954925d2ad9b08472a24fbcd9
- Author: EGAdams
- GitHub username: EGAdams
- License: MIT
- Repository: https://github.com/EGAdams/planner/tree/main/.claude/skills/voice-agent-expert
- Ref: 72d5025b022c77f7a51bdf5c1637c689c80e89d1
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: confirmation\_required
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: filesystem, network, external\_commands, env\_access
- Quality score: 38
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/egadams-voice-agent-expert
- Manifest: https://skillstore.pages.dev/api/skills/egadams-voice-agent-expert/manifest

## Capabilities

- Explains START versus DEV mode behavior for local voice testing.
- Lists common LiveKit, Letta, WebRTC, token, and duplicate-process failures.
- Provides checks for local ports, processes, logs, and service status.
- Includes scripts for diagnostics, connection token creation, and interactive startup.
- Documents duplicate prevention using PID and lock files.

## Use Cases

- Fix Local Voice Chat Setup: Diagnose why a local LiveKit and Letta voice session fails to connect or respond.
- Debug Audio Cutoffs: Trace intermittent audio failures to duplicate workers, stale rooms, or wrong agent mode.
- Prepare Support Runbooks: Turn repeated LiveKit and Letta failures into repeatable checks and escalation steps.

## Prompt Templates

### Diagnose a Connection Failure

```
My LiveKit and Letta voice agent does not connect. Ask for the error, then guide me through the safest checks first.
```

### Choose the Correct Agent Mode

```
Explain whether I should use START mode or DEV mode for local voice chat, and list the symptoms of choosing the wrong mode.
```

### Investigate Duplicate Workers

```
Help me determine whether duplicate voice-agent workers or stale LiveKit rooms are causing audio cutoffs.
```

### Design a Safer Startup Workflow

```
Review my local LiveKit and Letta startup workflow for security risks, secret handling, and safer process management.
```

## Limitations

- Uses hardcoded absolute paths from the original author workstation.
- Helper scripts expect Linux commands, LiveKit, Letta, and specific Python packages.
- Reads .env files and handles API secrets during token generation.
- Does not provide production deployment hardening or key rotation guidance.

## Best Practices

- Review every command before running it against local services or shell startup files.
- Move hardcoded paths into configuration before sharing this workflow across machines.
- Treat generated LiveKit tokens and .env contents as sensitive credentials.

## Anti Patterns

- Do not run broad process-kill commands without confirming the matching processes.
- Do not bind local development services to all interfaces without network controls.
- Do not paste generated tokens or .env-derived output into public issue reports.

## Security Audit

- Audited at: 2026-07-06T11:53:27.585\+00:00
- Summary: The skill appears intended for local LiveKit and Letta debugging, not covert exfiltration. Several findings are confirmed because helper scripts read .env files, handle API secrets, spawn shell commands, and start local services with hardcoded paths. Many markdown backtick and localhost URL findings are false positives, but the package needs hardening before broad marketplace distribution.

## Stats

- Views: 177
- Downloads: 6
- Favorites: 0
- Popularity score: 0