A comprehensive toolkit that enables AI agents to autonomously handle outbound and inbound phone calls using Twilio integration.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agentic-calling
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install agentic-calling using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Agentic Calling Skill empowers your AI workflows with voice capabilities, allowing agents to bridge the gap between digital processing and telephonic communication. By leveraging this Openclaw Skills extension, developers can programmatically trigger outbound calls with custom voice messages or set up robust inbound handling systems.
This skill utilizes high-quality Text-to-Speech (TTS) and Speech-to-Text (STT) technologies to ensure natural interactions, making it an essential component for agents requiring real-world voice outreach and response management. It integrates directly with Twilio to provide reliable infrastructure for automated communication workflows.
First, ensure you have a Twilio Account SID, Auth Token, and a Voice-enabled phone number. Configure your Openclaw Skills environment by creating a configuration file at ~/.clawdbot/twilio-config.json:
{
"accountSid": "YOUR_ACCOUNT_SID",
"authToken": "YOUR_AUTH_TOKEN",
"phoneNumber": "+1XXXXXXXXXX"
}
Alternatively, you can set your credentials using environment variables in your terminal:
export TWILIO_ACCOUNT_SID="YOUR_ACCOUNT_SID"
export TWILIO_AUTH_TOKEN="YOUR_AUTH_TOKEN"
export TWILIO_PHONE_NUMBER="+1XXXXXXXXXX"
Test your installation by making a test call to verify the connection:
./scripts/make-call.sh --to "+15551234567" --message "Openclaw Skills calling system is now active."
The skill manages data through configuration files and external API responses to maintain state and history. Key data structures include:
| Component | Description | Format |
|---|---|---|
| Configuration | Stores API keys and default phone numbers | JSON |
| Call Metadata | Logs SID, duration, status, and cost per call | Twilio Response |
| Recordings | Audio files of conversations stored for review | MP3 / WAV |
| Transcriptions | Text-based conversion of call audio for agents | Plain Text |
| IVR Menus | Logic for handling keypress responses | TwiML / XML |
Loading
A sophisticated headless search and web scraping tool that leverages the Brave Search API to provide structured, markdown-formatted web content.

An automated technical analyst that transforms complex text into structured markdown summaries, key points, and risk assessments.

A professional AI-driven skill that converts long technical documents into structured Markdown summaries including key points and risks.

A browser-based automation tool for X (Twitter) that enables automated posting and follower management without requiring an official API key.

A lightweight, file-based memory system that allows AI agents to persist learnings and decisions with sub-20ms search performance.

A powerful multi-column web interface for side-by-side management and interaction with multiple OpenClaw agents.








































