### Old Method Name Example Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/references/freshness-rules.md Demonstrates a potentially outdated method name for starting a session, illustrating API drift and the importance of checking current documentation. ```python agent.start_session() ``` -------------------------------- ### Repository Structure Example Source: https://github.com/livekit/agent-skills/blob/main/AGENTS.md Illustrates the directory structure for the agent-skills repository. ```tree agent-skills/ ├── README.md # User-facing documentation ├── AGENTS.md # This file (for AI agents) ├── CLAUDE.md # Points to AGENTS.md └── skills/ └── livekit-agents/ # LiveKit Agents skill ├── SKILL.md # The skill content └── references/ # Supporting documentation ``` -------------------------------- ### Verified Code Example Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/references/freshness-rules.md Use this template when code has been verified against current LiveKit Agents documentation. ```markdown According to the LiveKit Agents documentation, the correct approach is... [implementation] ``` -------------------------------- ### SKILL.md Frontmatter Example Source: https://github.com/livekit/agent-skills/blob/main/AGENTS.md Defines the required YAML frontmatter for a skill's SKILL.md file, including name, description, license, and metadata. ```yaml --- name: skill-name-kebab-case description: Trigger phrases and brief description. Include phrases like "build a voice agent" that help agents recognize when to use this skill. license: MIT metadata: author: livekit version: "X.Y.Z" --- ``` -------------------------------- ### Old Python VoiceAgent Configuration Example Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/references/freshness-rules.md Illustrates an outdated way of configuring a VoiceAgent using a dictionary, highlighting the need for verification due to potential API evolution. ```python agent = VoiceAgent(config={"model": "gpt-4"}) ``` -------------------------------- ### MCP Server Unavailable Guidance Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/references/freshness-rules.md Steps to take when the LiveKit MCP server is not installed or accessible, emphasizing immediate user notification, recommending installation, proceeding with caution, and suggesting manual verification. ```markdown 1. **Inform the user immediately** - They should know verification isn't possible 2. **Recommend installation** - Point to https://docs.livekit.io/mcp 3. **Proceed with caution** - Clearly mark all LiveKit-specific code as unverified 4. **Suggest manual verification** - User should check docs before using the code ``` -------------------------------- ### Current Method Name Example Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/references/freshness-rules.md Presents a possibly current method name for initiating an agent's action, contrasting with older versions and underscoring the need for API verification. ```python agent.start() ``` -------------------------------- ### Install LiveKit Agent Skills Source: https://github.com/livekit/agent-skills/blob/main/README.md Use this command to add the livekit/agent-skills package to your project. Skills activate automatically based on detected agent tasks. ```bash npx skills add livekit/agent-skills ``` -------------------------------- ### LiveKit Cloud Project Credentials Setup Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/SKILL.md Set your LiveKit Cloud project credentials as environment variables. These are required for authentication and connecting to your project. ```bash LIVEKIT_URL=wss://your-project.livekit.cloud LIVEKIT_API_KEY=your-api-key LIVEKIT_API_SECRET=your-api-secret ``` -------------------------------- ### Partially Verified Code Example Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/references/freshness-rules.md Use this template when the general workflow is verified, but specific details could not be confirmed against current documentation. ```markdown The workflow structure follows LiveKit's documented patterns. However, I could not verify [specific detail] against current documentation. Please confirm this matches your SDK version. ``` -------------------------------- ### Current Python VoiceAgent Configuration Example Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/references/freshness-rules.md Shows a more current API pattern for configuring a VoiceAgent, likely involving class instantiation for language models, emphasizing the need to verify against the latest documentation. ```python agent = VoiceAgent(llm=SomeLLMClass(...)) ``` -------------------------------- ### Unverified Code Example Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/references/freshness-rules.md Use this template when code cannot be verified against current LiveKit documentation, indicating it's based on general patterns and may need adjustment. It includes recommendations for manual verification. ```markdown I cannot verify this implementation against current LiveKit documentation. This is based on general patterns and may require adjustment. I recommend: 1. Checking the official documentation at [link] 2. Testing this implementation before relying on it ``` -------------------------------- ### New Skill Directory Structure Source: https://github.com/livekit/agent-skills/blob/main/CONTRIBUTING.md Illustrates the required directory structure for a new skill, including the main skill file and a references directory. ```bash skills/ └── your-skill-name/ ├── SKILL.md # The skill content └── references/ # Supporting documentation ``` -------------------------------- ### Search LiveKit Agents Testing Documentation Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/SKILL.md Use this command to search for current patterns in LiveKit's testing framework. Consult the testing documentation via MCP for detailed guidance. ```bash search: "livekit agents testing" ``` -------------------------------- ### Python Import Restructuring Source: https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/references/freshness-rules.md Demonstrates a change in how VoiceAgent is imported in Python. This highlights the need for up-to-date documentation as such restructuring is not always predictable. ```python from livekit.agents.voice import VoiceAgent ``` ```python from livekit.agents import VoiceAgent ``` -------------------------------- ### Skill YAML Frontmatter Source: https://github.com/livekit/agent-skills/blob/main/CONTRIBUTING.md Defines the essential YAML frontmatter required for every skill, including name, description, license, and metadata. ```yaml --- name: skill-name-kebab-case description: >- Trigger phrases and brief description that help agents recognize when to activate this skill. license: MIT metadata: author: your-name version: "0.1.0" --- ``` === COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.