elevenlabs-agents
Build conversational AI voice agents with ElevenLabs Platform. Configure agents, tools, RAG knowledge bases, agent versioning with A/B testing, and MCP security. React, React Native, or Swift SDKs. Prevents 34 documented errors. Use when: building voice agents, AI phone systems, agent versioning/branching, MCP security, or troubleshooting @11labs deprecated, webhook errors, CSP violations, localhost allowlist, tool parsing errors.
npx skills add majiayu000/claude-skill-registry --skill elevenlabs-agents-brendadeeznuts1111-tier-1380-omega --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill guides building conversational AI voice agents using the ElevenLabs platform. It covers coordinating core components (ASR, LLM, TTS, Turn-Taking Model), managing agent configuration, and enabling tools (client, server, MCP, and system tools). It includes package selections for different environments and provides details on agent workflows, dynamic variables, RAG, and language features. It also documents how to configure and migrate tool formats, handle dynamic variables, and use SDKs for React, React Native, Swift, and server/browser contexts.
How it works
- It describes installing and using ElevenLabs SDKs for different environments (React, React Native, server JS with elevenlabs-js, and agents-cli).
- It specifies how to configure an agent's prompt architecture (personality, environment, tone, goal, guardrails, tools) and how to set LLM model and temperature.
- It explains Tool usage in four types: Client Tools (browser/mobile), Server Tools (webhooks), MCP Tools (model context protocol), and System Tools (built-ins like end_call, detect_language, transfer_agent).
- It covers knowledge bases via a RAG workflow: upload documents, computeRagIndex, and retrieval during conversations, including parameters like max_chunks and vector_distance_threshold.
- It includes dynamic variables syntax and secret variable handling, plus error notes about missing variables.
- It outlines multi-voice, pronunciation, speed controls, and language presets for multilingual conversations.
- It provides migration notes for tool formats (new required tool_ids/built_in_tools over legacy prompt.tools) and examples for client and server tool definitions.
- It lists platform availability and versions for each SDK and references to updated packages and breaking changes.
When to use it
Use when building voice agents, AI phone systems, agent versioning/branching, MCP security, or troubleshooting webhook errors, CSP violations, localhost allowlist, or tool parsing errors related to ElevenLabs agents.
What it can touch
- ClientTools for browser/mobile integration (clientTools: { ... }).
- Server Tools with HTTP endpoints (name, url, method, headers, parameters).
- MCP Tools for connecting to MCP servers and managing approvals.
- System Tools including end_call, detect_language, transfer_agent, transfer_to_number, dtmf_playpad, and voicemail_detection.
- SDKs and packages: @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, and @elevenlabs/agents-cli.
Caveats
- Deprecation and migration: legacy prompt.tools is removed; use prompt.tool_ids or built_in_tools.
- Some features depend on specific versions (e.g., Turbo v2/v2.5 for TTS, WebRTC vs WebSocket tradeoffs).
- RAG adds latency (~500ms) and indexing can take minutes.
- Secret variables can only be used in headers, not URL/body.
- Missing variables trigger errors: "Missing required dynamic variables".
- Some 2025 updates mention experimental features (Scribe, WebRTC, etc.) with caveats about compatibility.
# ElevenLabs Agents Platform ## Overview ElevenLabs Agents Platform is a comprehensive solution for building production-ready conversational AI voice agents. The platform coordinates four core components: 1. **ASR (Automatic Speech Recognition)** - Converts speech to text (32+ languages, sub-second latency) 2. **LLM (Large Language Model)** - Reasoning and response generation (GPT, Claude, Gemini, custom models) 3. **TTS (Text-to-Speech)** - Converts text to speech (5000+ voices, 31 languages, low latency) 4. **Turn-Taking Model** - Proprietary model that handles conversation timing and interruptions ### 🚨 Package Updates (January 2026) ElevenLabs migrated to new scoped packages in August 2025. **Current packages:** ```bash npm install @elevenlabs/react@0.12.3 # React SDK (Dec 2025: localization, Scribe fixes) npm install @elevenlabs/client@0.12.2 # JavaScript SDK (Dec 2025: localization) npm install @elevenlabs/react-native@0.5.7 # React Native SDK (Dec 2025: mic fixes, speed param) npm install @elevenlabs/elevenlabs-js@2.30.0 # Base SDK (Jan 2026: latest) npm install -g @elevenlabs/agents-cli@0.6.1 # CLI ``` **DEPRECATED:** `@11labs/react`, `@11labs/client` (uninstall if present
- Overview
- 🚨 Package Updates (January 2026)
- December 2025 Updates
- Package Selection Guide
- 1. Quick Start
- React SDK
- CLI ("Agents as Code")
- API (Programmatic)
- 2. SDK Parameter Naming (camelCase vs snakecase)
- 3. Agent Configuration
- System Prompt Architecture (6 Components)
- Turn-Taking Modes
- Workflows & Agent Management (2025)
- Dynamic Variables
npm install @elevenlabs/react@0.12.3 # React SDK (Dec 2025: localization, Scribe fixes) npm install @elevenlabs/client@0.12.2 # JavaScript SDK (Dec 2025: localization) npm install @elevenlabs/react-native@0.5.7 # React Native SDK (Dec 2025: mic fixes, speed param) npm install @elevenlabs/elevenlabs-js@2.30.0 # Base SDK (Jan 2026: latest) npm install -g @elevenlabs/agents-cli@0.6.1 # CLI npm install @elevenlabs/react zod npm install -g @elevenlabs/agents-cli elevenlabs auth login elevenlabs agents init # Creates agents.json, tools.json, tests.json elevenlabs agents add "Bot" --template customer-service
What does the elevenlabs-agents skill do?
Build conversational AI voice agents with ElevenLabs Platform. Configure agents, tools, RAG knowledge bases, agent versioning with A/B testing, and MCP security. React, React Native, or Swift SDKs. Prevents 34 documented errors. Use when: building voice agents, AI phone systems, agent versioning/branching, MCP security, or troubleshooting @11labs deprecated, webhook errors, CSP violations, localhost allowlist, tool parsing errors.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill elevenlabs-agents-brendadeeznuts1111-tier-1380-omega --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 majiayu000/claude-skill-registry, a repository with 534 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.