agentmail-to-inbox-ops
Manage Agentmail.to inbox operations with deterministic Python scripts: list/read messages, download and analyze attachments, reply with sender filters, and set read/unread state. Use when handling inbox workflows for any Agentmail.to inbox.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/4ur3l/agentmail-to-inbox-opsWhat This Skill Does
The agentmail-to-inbox-ops skill is the primary, deterministic interface for interacting with Agentmail.to services within an OpenClaw environment. It is designed to handle complex inbox workflows by abstracting raw API requests into reliable, script-driven operations. This tool allows users to programmatically list, read, and manage email communication, as well as handle file-based attachments with safety-guarded extraction and analysis. By shifting from ad-hoc API calls to a structured Python-based script library located in your repository, the skill ensures that inbox management is reproducible, version-controlled, and highly performant for automated AI agent workflows.
Installation
To integrate this skill, navigate to your project's root directory and run: clawhub install openclaw/skills/skills/4ur3l/agentmail-to-inbox-ops. Ensure you have initialized your project with uv to manage dependencies. After installation, create a .env file in your root folder to house your AGENTMAIL_API_KEY and any specific AGENTMAIL_INBOX or AGENTMAIL_ALLOWED_SENDERS configurations. Finally, run uv sync to install all necessary Python requirements. You can verify your environment setup by executing uv run python scripts/check_onboarding.py.
Use Cases
This skill is perfect for scenarios requiring high-reliability email automation. Use it for automated help-desk ticketing where attachments need to be scraped and stored, batch processing of unread communications for summarization, or filtered reply workflows where only specific verified senders receive automated responses. It is essential when you need to audit inbox behavior or ensure that email attachments are scanned and analyzed without exposing the environment to unvetted API logic.
Example Prompts
- "Check my inbox for unread messages from [email protected] and summarize the contents of the latest PDF attachment."
- "List the 10 most recent emails in my default inbox, then download all attachments from the message with ID 88291 to the ./downloads folder."
- "Reply to all unread emails from allowed senders with a confirmation message stating that the request is being processed, and mark them as read."
Tips & Limitations
Always use the --dry-run flag during initial setup to test your filters before executing mass replies. Ensure your .gitignore includes downloads/, .env, and inbox_ops.log to maintain repository safety. Note that document analysis is guarded by resource limits; do not attempt to process extremely large files without checking script timeouts. The skill relies on deterministic script execution, so if you modify the local scripts, ensure you maintain the expected input/output interfaces.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-4ur3l-agentmail-to-inbox-ops": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api, code-execution