ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified communication Safety 3/5

python-agentmail-send-receive

python files which are used to send an email and to download received emails from an inbox. The email provider is agentmail.to, which offers an API. This way of email handling is very AI-agent friendly.

Why use this skill?

Integrate email into your OpenClaw agent with the agentmail skill. Automate sending and receiving emails via a simple JSON-based API for seamless communication.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/lausser/python-agentmail-send-receive
Or

What This Skill Does

The python-agentmail-send-receive skill provides a robust bridge between the OpenClaw agent and the agentmail.to email infrastructure. Designed specifically for AI agents, it streamlines the complex processes of SMTP and IMAP into simple, script-driven operations. By deploying these specialized Python scripts into your workspace, your agent gains the ability to send outgoing messages and poll your inbox for incoming correspondence. The skill handles the heavy lifting of authentication and message parsing, delivering emails in a clean, agent-readable JSON format. This allows your agent to participate in human-like communication cycles, process automated notifications, or act as an autonomous email-based assistant.

Installation

Installation is performed via the ClawKit CLI using the clawhub install openclaw/skills/skills/lausser/python-agentmail-send-receive command. Once installed, ensure you have initialized your Python virtual environment within ~/.openclaw/workspace/agentmail/ as outlined in the setup guide. You must supply your AGENTMAIL_API_KEY via a .env file to authorize the agent to interact with the provider. Ensure your REPLACE_WITH_IDENTITY placeholder is updated in the scripts to match your assigned agentmail.to address to ensure messages are routed correctly.

Use Cases

This skill is ideal for agents tasked with long-running asynchronous workflows where email is the primary interface. Use it to build an agent that summarizes daily newsletter digests, monitors support tickets for specific keywords, or notifies human stakeholders when a long-running process concludes. It is perfect for integration with services that lack an API but offer email notification systems.

Example Prompts

  1. "Check for any unread emails from the project management team and extract the task list from the latest message."
  2. "Send a status update email to the client containing the current progress report summary and a link to the generated data file."
  3. "Summarize all incoming mail received in the last 24 hours and highlight any threads that require urgent attention from me."

Tips & Limitations

The skill relies on the agentmail.to API, so ensure your API key remains valid and secure. Always verify the permissions granted to the workspace directory, as the skill writes incoming emails as JSON files. Note that the scripts are designed for programmatic processing; if you are dealing with very high volumes of email, consider implementing a cron job to trigger check_mail.py at set intervals to keep the workspace clean and the agent updated.

Metadata

Author@lausser
Stars1656
Views0
Updated2026-02-28
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-lausser-python-agentmail-send-receive": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#email#automation#python#messaging#agent-tools
Safety Score: 3/5

Flags: network-access, file-write, file-read, external-api, code-execution