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
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
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. Push Notification (Critical)
- Context: The user is likely not looking at the terminal or chat window.
- Action: Use the system's primary notification tool.
- macOS:
osascript -e 'display notification "Your prediction..." with title "Daily Oracle"'
- Linux:
notify-send "Daily Oracle" "Your prediction..."
- Format:
🔮 Daily Oracle: [Your Prediction Here]
Constraints & Safety
- One-Shot Execution: This process must run from start to finish without pausing for user input.
- Failure Mode: If data is insufficient to make a specific prediction, fall back to a generic personalized wellness tip based on the weather. Do NOT fail silently.
- Data Hygiene: Clearly wipe the temporary context/memory of the gathered data once the prediction is sent.
- Silence on Sources: The output message must strictly contain the prediction and subtle reason for prediction. Do not list the data sources in the notification.
1---2name: daily-oracle3version: 1.1.04description: A background agent that generates a daily life prediction by analyzing local data and social signals.5author: https://github.com/Invelene6repository: https://github.com/Invelene/Futurizzm/daily-oracle7requirements:8 - browser-automation9 - calendar-access10 - local-file-search11 - sqlite-access12permissions:13 - read: browser_cookies (instagram.com, twitter.com)14 - read: local_db (imessage/chat.db)15 - read: calendar16 - read: filesystem (downloads)17safety_policy: "local-only"18metadata:19 source: https://skillmd.com/skills/bishal-pdmsft/daily-oracle20---2122# Daily Oracle (Automated)2324This 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.2526**⚠️ 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.2728## Execution Routine2930### 1. Initialization & Anti-Ban Jitter3132- **Context**: Since this task is triggered by a precise Cron timer (e.g., exactly 08:00:00), immediate execution creates a detectable bot pattern.33- **Action**: Generate a random integer between 120 and 900 (seconds).34- **Wait**: Sleep for that duration before making any network requests.35 ```bash36 sleep $(( RANDOM % 780 + 120 ))37 ```3839### 2. Silent Data Gathering4041#### A. Calendar Context4243- **Action**: Read the local calendar for today's agenda (00:00 to 23:59).44- **Tool Usage**: Use `calendar-access` or CLI equivalents (e.g., `icalBuddy` on macOS).45 - _Prompt_: "Summarize my calendar events for today from 00:00 to 23:59. Focus on constraints (meetings) and opportunities (free blocks)."4647#### B. Social Context (Headless)4849- **Action**: Open a headless browser session using _existing_ cookies.50- **Target**: Scan "Close Friends" or specific mutuals who appear in the user's recent calendar/messages.51- **Safety**: Limit scrolling to max 5 posts/stories. **Abort immediately** if login is requested to prevent session flagging.52- **Data Extraction**: Screenshot or scrape text from the first viewport of specific curated URLs (e.g., `instagram.com/direct/inbox/`).5354#### C. Communications (iMessage/Local DB)5556- **Action**: Read the last 50 messages from the local `chat.db`.57- **Query**:58 ```sql59 SELECT60 text,61 datetime(date/1000000000 + 978307200, 'unixepoch', 'localtime') as date_sent62 FROM message63 WHERE date_sent > datetime('now', '-24 hours')64 ORDER BY date DESC65 LIMIT 50;66 ```67- **Filtering**: Look for intent keywords: "tomorrow", "gym", "coffee", "meet", "lunch", "tonight".6869#### D. System Signals7071- **Action**: Check `~/Downloads` for recent files.72 ```bash73 find ~/Downloads -type f -mtime -1 -print74 ```75- **Inference**: Determine active deliverables or recent interests based on file types (e.g., PDFs vs. Images).7677### 3. The Oracle's Inference7879- **Synthesize**: Combine the hard data (Calendar: "Gym at 5pm") with soft data (Social: "Amy posted about coffee").80- **Predict**: Formulate a single, high-confidence sentence in the future tense.81- **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"_8283### 4. Push Notification (Critical)8485- **Context**: The user is likely not looking at the terminal or chat window.86- **Action**: Use the system's primary notification tool.87 - _macOS_: `osascript -e 'display notification "Your prediction..." with title "Daily Oracle"'`88 - _Linux_: `notify-send "Daily Oracle" "Your prediction..."`89- **Format**:90 > 🔮 **Daily Oracle**: [Your Prediction Here]9192## Constraints & Safety93941. **One-Shot Execution**: This process must run from start to finish without pausing for user input.952. **Failure Mode**: If data is insufficient to make a specific prediction, fall back to a generic personalized wellness tip based on the weather. Do NOT fail silently.963. **Data Hygiene**: Clearly wipe the temporary context/memory of the gathered data once the prediction is sent.974. **Silence on Sources**: The output message must strictly contain the _prediction_ and subtle reason for prediction. Do not list the data sources in the notification.