Agent skill
eleven-agent-manager
Manage ElevenLabs Conversational AI agent configuration including prompts, voice settings, MCP servers, and conversation settings. Use when updating agent behavior, voice, or integrations.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/eleven-agent-manager
SKILL.md
ElevenLabs Agent Manager
Overview
This skill provides tools and workflows for managing ElevenLabs Conversational AI agents, including updating prompts, voice settings, MCP server configurations, and monitoring conversations.
API Configuration
- API Key: Set in environment as
ELEVENLABS_API_KEY - Agent ID:
agent_2601kf1fmbnseaxvp5kvc4zc21bz(Mega Agent 2) - Base URL:
https://api.elevenlabs.io/v1/convai
Available Operations
1. Update Agent Prompt
Update the system prompt that guides agent behavior.
python3 scripts/eleven_api.py update-prompt "Your new prompt here"
2. Get Agent Config
Retrieve current agent configuration.
python3 scripts/eleven_api.py get-config
3. Update Voice Settings
Change voice ID, stability, speed, or similarity boost.
python3 scripts/eleven_api.py update-voice --voice-id "HHstJSjlLg0NG8fanfeK" --speed 1.1
4. List MCP Servers
Show linked MCP servers.
python3 scripts/eleven_api.py list-mcp
5. Get Recent Conversations
View recent conversation summaries.
python3 scripts/eleven_api.py conversations --limit 10
6. Get Conversation Transcript
Get full transcript of a specific conversation.
python3 scripts/eleven_api.py transcript <conversation_id>
Configuration Options
Voice Settings
| Parameter | Description | Default |
|---|---|---|
| voice_id | ElevenLabs voice ID | HHstJSjlLg0NG8fanfeK |
| stability | Voice consistency (0-1) | 0.5 |
| speed | Speech rate | 1.1 |
| similarity_boost | Voice similarity (0-1) | 0.8 |
Turn Settings
| Parameter | Description | Default |
|---|---|---|
| turn_timeout | Seconds to wait for response | 7.0 |
| mode | Conversation mode | turn |
MCP Server Settings
| Parameter | Description |
|---|---|
| approval_policy | auto_approve_all, require_approval_all, require_approval_per_tool |
| transport | SSE or HTTP |
| url | MCP server endpoint |
Workflow Examples
Update Agent for New Use Case
- Get current config:
python3 scripts/eleven_api.py get-config - Draft new prompt based on requirements
- Update prompt:
python3 scripts/eleven_api.py update-prompt "..." - Test via voice widget
Add Skills to Agent Context
- List current skills in prompt
- Generate skill summary from /home/ec2-user/mega-agent2/.claude/skills/
- Update prompt with new skills list
Troubleshoot MCP Integration
- Check MCP server status:
curl http://127.0.0.1:8082/health - List MCP servers:
python3 scripts/eleven_api.py list-mcp - Check tool discovery: Use ElevenLabs API to verify tools
Resources
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?