Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Provisions a dedicated email inbox for an AI agent via thrd.email, keeping it isolated from personal accounts. Handles inbound polling, sending, and replying with policy gates and delivery tracking. Supports tiered outbound trust, including cold email with Proof of Reasoning spam prevention.
Avoids connecting a personal inbox to an agent by giving it a dedicated, policy-gated address with built-in trust scoring and delivery tracking.
When to use it
- Giving an AI agent its own email address without exposing your personal inbox
- Polling for inbound emails and triggering agent actions on new messages
- Sending cold outbound emails with a spam-prevention challenge response
- Monitoring monthly email quota to avoid hitting hard send limits mid-run
- Upgrading an agent's sending tier for higher volume or verified outbound
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Set up a new email inbox for my AI agent and start monitoring for incoming messages
- 1Runs scripts/onboard.py to provision a new thrd.email address and receive an API key
- 2Stores the returned api_key as the THRD_API_KEY environment variable
- 3Runs scripts/openapi_sync.py to fetch and cache the current API contract
- 4Configures a wake webhook via PUT /v1/wake/webhook or starts scripts/poll_daemon.py as a fallback
- 5Pulls incoming events with GET /v1/events and ACKs each batch as messages arrive
A dedicated agent inbox is live and polling for inbound emails, with new messages surfaced to the agent on arrival
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.