Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
• 🔑 Keyword triggers • ⏰ Time windows • 📊 Statistics tracking • 🚦 Daily reply cap • Bug fixes (race condition) • Documentation improvements
What This Skill Does
Monitors iMessage and SMS conversations on macOS and sends AI-generated replies to configured contacts. Each contact gets its own prompt, rate limit, time window, and keyword trigger rules. Managed via Telegram slash commands or natural language.
Runs persistently on macOS with per-contact AI personalities, rate limits, and time windows without requiring a hosted service or third-party subscription.
When to use it
- Auto-replying to a friend while traveling without phone access
- Setting a polite busy-response for specific contacts during work hours
- Previewing AI-generated replies in test mode before enabling live responses
- Restricting auto-replies to messages containing keywords like "urgent" or "help"
- Reviewing what the auto-responder sent to a contact over the past few days
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Add my mom's number +15559876543 to auto-reply warmly and briefly
- 1Parse the phone number and desired tone from the request
- 2Run `node manage.js add "+15559876543" "Reply warmly and briefly, as if I'm responding myself. Keep it under 160 characters." "Mom"`
- 3Confirm the contact appears in the watch list via `node manage.js list`
- 4Remind the user to restart the watcher for the new contact to take effect
Mom's number added to the watch list with the warm brief prompt. Watcher restart required.
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.