원클릭으로
elevenlabs-calls
Make AI phone calls using ElevenLabs Conversational AI and Twilio.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Make AI phone calls using ElevenLabs Conversational AI and Twilio.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Maintain Rick's control plane: approvals, dependency gaps, scoreboard, and morning briefs. Use when Rick needs to rank work, ask the founder for something, summarize operating status, or keep the CEO loop coherent.
Production hardening patterns for AI agents running on OpenClaw. Adds destructive command safety (trash > rm), session rotation protocol, context window discipline, tool pre-flight checks, heartbeat batching with state-file gating, and memory trimming workflow. Battle-tested by Rick (meetrick.ai) over 30+ days of autonomous production operation. Use when setting up a new agent for production, auditing an existing deployment, or after experiencing context degradation, token waste, or operational drift.
Diagnose stuck agents, restart failed processes, manage tmux sessions, run health checks, and resolve common operational failures.
Connect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact with external services. Security: The MATON_API_KEY authenticates with Maton.ai but grants NO access to third-party services by itself. Each service requires explicit OAuth authorization by the user through Maton's connect flow. Access is strictly scoped to connections the user has authorized. Provided by Maton (https://maton.ai).
Run long-lived AI coding agents (Codex, Claude Code) in persistent tmux sessions with Ralph retry loops and completion hooks. Use when running multi-step coding tasks, PRD-based workflows, or any programming agent that needs to survive restarts, retry on failure, and notify on completion.
Run long-lived AI coding agents (Codex CLI, Claude Code, Ralph loops) in persistent tmux sessions with completion hooks and automatic monitoring. Use when launching coding agents for multi-step tasks, managing background programming sessions, running Ralph loops with PRD validation, or needing coding work that survives process restarts.
| name | elevenlabs-calls |
| description | Make AI phone calls using ElevenLabs Conversational AI and Twilio. |
| homepage | https://elevenlabs.io/docs/agents-platform/overview |
| metadata | {"clawdbot":{"emoji":"📞","requires":{"bins":["curl","jq"],"env":["ELEVENLABS_API_KEY"]},"primaryEnv":"ELEVENLABS_API_KEY"}} |
Make outbound AI phone calls using ElevenLabs Conversational AI agents via Twilio.
ELEVENLABS_API_KEY env var# List your agents
{baseDir}/scripts/agents.sh
# List your phone numbers
{baseDir}/scripts/phones.sh
# Make a call
{baseDir}/scripts/call.sh --agent <agent_id> --phone <phone_number_id> --to "+15551234567"
# Check conversation transcript
{baseDir}/scripts/conversation.sh <conversation_id>
{baseDir}/scripts/agents.sh [--search "name"]
{baseDir}/scripts/phones.sh
{baseDir}/scripts/call.sh \
--agent <agent_id> \
--phone <phone_number_id> \
--to "+15551234567" \
[--vars '{"name":"John","appointment":"Monday 9am"}']
Options:
--agent / -a: Agent ID (required)--phone / -p: Phone number ID from ElevenLabs (required)--to / -t: Phone number to call in E.164 format (required)--vars / -v: JSON object of dynamic variables to pass to the agent (optional){baseDir}/scripts/conversation.sh <conversation_id>
{baseDir}/scripts/conversation.sh <conversation_id> --transcript
{baseDir}/scripts/conversation.sh <conversation_id> --audio > call.mp3
{baseDir}/scripts/conversations.sh [--agent <agent_id>] [--limit 10]
You are calling on behalf of [User Name] to schedule a vehicle service appointment.
Your goal:
1. Introduce yourself and state the purpose (schedule Honda Odyssey inspection)
2. Request a morning appointment next week
3. Confirm the date/time offered
4. Provide contact info if asked: [phone] and [email]
Be polite, concise, and professional. If asked questions you can't answer,
say you'll have the owner follow up.
Pass context to your agent using dynamic variables:
{baseDir}/scripts/call.sh \
--agent abc123 \
--phone phone_xyz \
--to "+15121234567" \
--vars '{"customer_name":"Customer","vehicle":"Honda Odyssey","preferred_time":"morning next week"}'
Reference these in your agent's system prompt as {{customer_name}}, {{vehicle}}, etc.