voice-agent-expert
This skill is a practical, 'use-it-while-debugging' reference for getting a LiveKit + Letta voice agent working reliably.
What this skill does
# Voice Agent Expert – Debugging Cheat Sheet (Skill)
This skill is a practical, "use-it-while-debugging" reference for getting a LiveKit + Letta voice agent working reliably.
---
## Core rules (fix 90% of issues)
1. **Override the right LiveKit hook**
- The framework calls `llm_node`, **not** `generate_reply`.
- If you override the wrong method, your changes won't run and your agent may "look alive" but never route text correctly.
2. **Only ONE voice-agent process can run at a time**
- Duplicate processes commonly cause:
- timeouts
- audio cutting out
- inconsistent behavior (you're looking at logs from one process while another is actually serving)
3. **Use `dev` mode for local testing**
- `start` can sit waiting for dispatch and look "broken."
- If you're actively testing locally, `dev` mode is the fast path.
---
## Nuclear reset (when it's just stuck)
Run this when things are wedged, timeouts are happening, or audio is cutting out.
It kills old processes, restarts LiveKit in dev mode, then restarts the Letta voice agent.
```bash
pkill -9 -f letta_voice_agent.py
pkill -f livekit-server
sleep 2
cd /home/adamsl/ottomator-agents/livekit-agent
nohup ./livekit-server --dev --bind 0.0.0.0 > /tmp/livekit.log 2>&1 &
cd /home/adamsl/planner/a2a_communicating_agents/hybrid_letta_agents
/home/adamsl/planner/.venv/bin/python3 letta_voice_agent.py dev > /tmp/letta_voice_agent.log 2>&1 &
```
---
## Is it alive? checks (fastest signals)
1. **LiveKit responding (not just "listening")**
```bash
curl -v http://localhost:7880/ 2>&1 | head -20
```
If this hangs or times out, LiveKit is stuck → restart it.
2. **Confirm you don't have duplicate voice-agent processes**
```bash
ps aux | grep letta_voice_agent | grep -v grep
```
You should see exactly one.
3. **Confirm Letta routing is actually being used**
Watch your logs for your 🎤 marker (or equivalent logging) that proves `llm_node` is being hit.
---
## Common gotchas
### WebSocket double-slash problem
If the browser tries:
```
ws://127.0.0.1:7880//rtc
```
Use instead:
```
ws://localhost:7880
```
**Reason:** The client appends `/rtc`, and some configs end up producing a double-slash.
### Code changes not taking effect
- Edits don't apply until you kill + restart the running process.
- If you edited code and nothing changed, assume you're running an old process.
---
## If messages aren't showing up in Letta Desktop
Most common causes:
- You overrode the wrong method (`generate_reply` instead of `llm_node`)
- An old process is still running (your edits aren't live)
- The session LLM is bypassing Letta routing
### Recommended fix flow
1. Search your code for `llm_node` and confirm your override is in place.
2. Kill all running agent processes.
3. Restart cleanly using the Nuclear reset section above.
4. Tail logs and confirm you see your 🎤 marker.
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.