Daily Oracle (Automated)

This skill is designed to run as a background process (Cron Job). It wakes up, analyzes the user's digital footprint, generates a prediction, pushes the notification, and then terminates.

⚠️ PRIVACY NOTICE: This skill processes highly sensitive personal data. All analysis must be performed within the local LLM context. No data is to be sent to third-party logging services.

Execution Routine

1. Initialization & Anti-Ban Jitter

• Context: Since this task is triggered by a precise Cron timer (e.g., exactly 08:00:00), immediate execution creates a detectable bot pattern.
• Action: Generate a random integer between 120 and 900 (seconds).
• Wait: Sleep for that duration before making any network requests.

  sleep $(( RANDOM % 780 + 120 ))
  

2. Silent Data Gathering

A. Calendar Context

• Action: Read the local calendar for today's agenda (00:00 to 23:59).
• Tool Usage: Use calendar-access or CLI equivalents (e.g., icalBuddy on macOS).
  • Prompt: "Summarize my calendar events for today from 00:00 to 23:59. Focus on constraints (meetings) and opportunities (free blocks)."

B. Social Context (Headless)

• Action: Open a headless browser session using existing cookies.
• Target: Scan "Close Friends" or specific mutuals who appear in the user's recent calendar/messages.
• Safety: Limit scrolling to max 5 posts/stories. Abort immediately if login is requested to prevent session flagging.
• Data Extraction: Screenshot or scrape text from the first viewport of specific curated URLs (e.g., instagram.com/direct/inbox/).

C. Communications (iMessage/Local DB)

• Action: Read the last 50 messages from the local chat.db.
• Query:

  SELECT
      text,
      datetime(date/1000000000 + 978307200, 'unixepoch', 'localtime') as date_sent
  FROM message
  WHERE date_sent > datetime('now', '-24 hours')
  ORDER BY date DESC
  LIMIT 50;
  

• Filtering: Look for intent keywords: "tomorrow", "gym", "coffee", "meet", "lunch", "tonight".

D. System Signals

• Action: Check ~/Downloads for recent files.

  find ~/Downloads -type f -mtime -1 -print
  

• Inference: Determine active deliverables or recent interests based on file types (e.g., PDFs vs. Images).

3. The Oracle's Inference

• Synthesize: Combine the hard data (Calendar: "Gym at 5pm") with soft data (Social: "Amy posted about coffee").
• Predict: Formulate a single, high-confidence sentence in the future tense.
• Tone: Insightful but grounded. Example: "You will meet Amy at the gym today, and she will likely suggest getting coffee after workout because she posted about craving caffeine"

4.