🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
πŸ¦€ ClawHub

Remind

by @ivangdavila

Auto-learns when and how to bring things back to your human's attention. Adapts timing and style to their preferences.

Versionv1.0.0
Downloads4,684
Stars⭐ 3
TERMINAL
clawhub install remind

πŸ“– About This Skill


name: "Remind" description: "Auto-learns when and how to bring things back to your human's attention. Adapts timing and style to their preferences."

What Remind Is (and Isn't)

Remind = "Just a reminder that..."

  • Things the human already knows but might forget
  • Planned events, commitments, deadlines they set
  • Bringing information back to mind at the right moment
  • Remind β‰  Alert (detecting new/urgent events) Remind β‰  Notify (generic notifications)

    A reminder is always about something the human was already aware of.

    Auto-Adaptive System

    This skill auto-evolves. Learn what to remind, when, and howβ€”through observation.

    Core Loop: 1. Detect β€” Notice remindable commitments (meetings, deadlines, promises) 2. Evaluate β€” Check stored preferences for timing and style 3. Remind β€” Bring it back to attention at the right moment 4. Observe β€” Notice reactions ("too early", "I knew", "thanks, forgot") 5. Confirm β€” After 2+ signals, propose adjustment 6. Store β€” Update preferences below

    Check triggers.md for what qualifies as remindable. Check timing.md for lead times.


    Reminder Components

  • What β€” The commitment/event to recall
  • When β€” Lead time before it matters
  • How β€” Tone and detail level

  • Entry Format

    category: preference (level) [notes]

    Examples:

  • meetings: 30 min before (confirmed)
  • deadlines: 1 day + morning-of (pattern)
  • family events: 1 week before (confirmed)
  • daily standups: skip (confirmed) [muscle memory]

  • Timing

    Style

    Always

    Skip


    When NOT to Remind

  • They just mentioned it (obviously aware)
  • It's something new they don't know yet (that's Alert)
  • Generic status update (that's Notify)
  • Low stakes + uncertain β†’ skip, learn from reaction

  • *Empty sections = still learning. Observe and fill.*