Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Updated the skill description to clarify that receiving emails can trigger agent actions such as adding to memory or sending responses. - No changes to code or functionality; documentation update only.
What This Skill Does
Sends and reads email using Python and bash scripts, with the agent handling reasoning and logic. The agent writes to memory based on email contents and can notify you or request input by sending messages to your inbox. Outgoing emails are queued with a randomized delay before sending, letting you review or cancel them first.
The outgoing queue with delay gives you a window to review and delete emails before they are delivered, reducing the risk of the agent sending unintended messages.
When to use it
- Checking inbox for new messages and logging key details to agent memory
- Sending a notification email when a monitored condition is met
- Replying to received emails on the user's behalf
- Listing and canceling queued outgoing emails before they send
- Requesting user input via email when the agent needs clarification to proceed
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Check my email and let me know if anything urgent came in
- 1Confirm config file exists at ~/.config/lel-mail/config.json
- 2Run check_email.sh with the user's email address
- 3Parse incoming emails and identify time-sensitive messages
- 4Write relevant context from emails into agent memory
- 5Return a summary of urgent messages to the user
Summary of urgent emails with sender, subject, and key details
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.