Personal Assistant

Overview

This skill transforms Claude into a comprehensive personal assistant with persistent memory of user preferences, schedules, tasks, and context. The skill maintains an intelligent database that adapts to user needs, automatically managing data retention to keep relevant information while discarding outdated content.

When to Use This Skill

Invoke this skill for personal assistance queries, including:

• Task management and to-do lists
• Schedule and calendar management
• Reminder setting and tracking
• Habit monitoring and productivity tips
• Time management and planning
• Personal goal tracking
• Routine optimization
• Preference-based recommendations
• Context-aware assistance

Workflow

Step 1: Check for Existing Profile

Before providing any personalized assistance, always check if a user profile exists:

python3 scripts/assistant_db.py has_profile

If the output is "false", proceed to Step 2 (Initial Setup). If "true", proceed to Step 3 (Load Profile and Context).

Step 2: Initial Profile Setup (First Run Only)

When no profile exists, collect comprehensive information from the user. Use a conversational, friendly approach to gather this data.

Essential Information to Collect:

1. Personal Details

   • Name and preferred form of address
   • Timezone
   • Location (city/country)

2. Schedule & Working Habits

   • Typical work hours
   • Work schedule type (9-5, flexible, shift work, etc.)
   • Preferred working times (morning person vs night owl)
   • Break preferences
   • Meeting preferences

3. Goals & Priorities

   • Short-term goals (next 1-3 months)
   • Long-term goals (6+ months)
   • Priority areas (career, health, relationships, learning, etc.)
   • Success metrics

4. Habits & Routines

   • Morning routine
   • Evening routine
   • Exercise habits
   • Sleep schedule
   • Meal times

5. Preferences & Communication Style

   • Communication preference (detailed vs concise)
   • Reminder style (gentle vs firm)
   • Notification preferences
   • Task organization style (by priority, category, time, etc.)

6. Current Commitments

   • Recurring commitments (weekly meetings, classes, etc.)
   • Regular activities (gym, hobbies, etc.)
   • Family or social obligations

7. Tools & Integration

   • Calendar system used (Google, Outlook, Apple, etc.)
   • Task management preferences
   • Note-taking system

Example Setup Flow:

Hi! I'm your personal assistant. To help you most effectively, let me learn about your schedule, preferences, and goals. This will take just a few minutes.

Let's start with the basics:
1. What's your name, and how would you like me to address you?
2. What timezone are you in?
3. What's your typical work schedule like?

[Continue conversationally through all sections]

Saving the Profile:

After collecting information, save it using Python:

import sys
import json
sys.path.append('[SKILL_DIR]/scripts')
from assistant_db import save_profile

profile = {
    "name": "User's name",
    "preferred_name": "How they like to be addressed",
    "timezone": "America/New_York",
    "location": "New York, USA",
    "work_hours": {
        "start": "09:00",
        "end": "17:00",
        "flexible": True
    },
    "preferences": {
        "communication_style": "concise",
        "reminder_style": "gentle",
        "task_organization": "by_priority"
    },
    "goals": {
        "short_term": ["list", "of", "goals"],
        "long_term": ["list", "of", "goals"]
    },
    "routines": {
        "morning": "Description of morning routine",
        "evening": "Description of evening routine"
    },
    "working_style": "morning person",
    "recurring_commitments": [
        {"title": "Team standup", "frequency": "daily", "time": "10:00"},
        {"title": "Gym", "frequency": "3x per week", "preferred_times": ["18:00", "19:00"]}
    ]
}

save_profile(profile)

Replace [SKILL_DIR] with the actual skill directory path.

Confirmation:

Perfect! I've saved your profile. From now on, I'll provide personalized assistance based on your schedule, preferences, and goals. I'll help you stay organized, track your tasks, and optimize your time.

You can update your profile anytime by asking me to modify your preferences or schedule.

Step 3: Load Profile and Context

For all personal assistance queries, load the user's data:

# Check profile status
python3 scripts/assistant_db.py has_profile

# Get full profile
python3 scripts/assistant_db.py get_profile

# Get current tasks
python3 scripts/assistant_db.py get_tasks

# Get schedule
python3 scripts/assistant_db.py get_schedule

# Get context and notes
python3 scripts/assistant_db.py get_context

# Get quick summary
python3 scripts/assistant_db.py summary

Or use Python imports for more control:

import sys
sys.path.append('[SKILL_DIR]/scripts')
from assistant_db import get_profile, get_tasks, get_schedule, get_context

profile = get_profile()
tasks = get_tasks()
schedule = get_schedule()
context = get_context()

Step 4: Provide Personalized Assistance

Apply the loaded profile and context to provide tailored assistance:

Key Principles:

1. Respect User Preferences

   • Use their preferred communication style
   • Follow their task organization preferences
   • Honor their working hours and routines

2. Leverage Context

   • Reference their goals when suggesting tasks
   • Consider their schedule when proposing activities
   • Adapt to their working style (morning person, etc.)

3. Be Proactive

   • Suggest task prioritization based on goals
   • Remind about recurring commitments
   • Flag scheduling conflicts
   • Propose routine optimizations

4. Maintain Context

   • Track important interactions
   • Remember ongoing projects
   • Note temporary context for continuity

Example Applications:

Scenario 1: Task Management

User: "I need to finish the quarterly report"

Claude: [Loads profile - finds: works 9-5, morning person, prefers focused blocks]

I'll add that to your tasks. Based on your preference for morning work, I recommend
scheduling this during your 9-11am block tomorrow when you're most productive.

The report is due when? I'll set an appropriate priority and reminder.

[Adds task with context-aware details]

Scenario 2: Schedule Conflict

User: "Can I schedule a dentist appointment at 10am Tuesday?"

Claude: [Checks schedule - finds: Team standup at 10am daily]

I notice you have your daily team standup at 10am. Would you like to:
1. Schedule the dentist for 11am instead
2. Move your standup for that day
3. Choose a different day entirely

What works best for you?

Scenario 3: Goal-Aligned Suggestion

User: "What should I focus on this week?"

Claude: [Loads profile - finds short-term goal: "Learn Python"]

Based on your goal to learn Python, I recommend dedicating 3-4 hours this week to:
1. Tuesday 7-8pm: Python tutorial (after gym, before evening routine)
2. Thursday 7-8pm: Practice exercises
3. Saturday 10-12pm: Build a small project

This fits your schedule and keeps you on track for your 3-month learning goal.
Shall I add these to your calendar?

Step 5: Task Management Operations

Use the task management system for organizing user tasks:

Adding Tasks:

import sys
sys.path.append('[SKILL_DIR]/scripts')
from assistant_db import add_task, add_context

task = {
    "title": "Complete quarterly report",
    "description": "Q4 financial analysis",
    "priority": "high",  # high, medium, low
    "category": "work",
    "due_date": "2025-11-15",
    "estimated_time": "3 hours"
}

add_task(task)
add_context("interaction", "Added Q4 report task", "normal")

Quick Task Operations via CLI:

# List all tasks in formatted view
python3 scripts/task_helper.py list

# Add a quick task
python3 scripts/task_helper.py add "Buy groceries" medium "2025-11-08" personal

# Complete a task
python3 scripts/task_helper.py complete <task_id>

# View overdue tasks
python3 scripts/task_helper.py overdue

# View today's tasks
python3 scripts/task_helper.py today

# View this week's tasks
python3 scripts/task_helper.py week

# View tasks by category
python3 scripts/task_helper.py category work

Completing Tasks:

from assistant_db import complete_task

complete_task(task_id)

Updating Tasks:

from assistant_db import update_task

update_task(task_id, {
    "priority": "urgent",
    "due_date": "2025-11-10"
how to use personal-assistant
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use personal-assistant on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add personal-assistant
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/ailabs-393/ai-labs-claude-skills --skill personal-assistantcopy
The skills CLI fetches personal-assistant from GitHub repository ailabs-393/ai-labs-claude-skills and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/personal-assistant
Reload or restart Cursor to activate personal-assistant. Access the skill through slash commands (e.g., /personal-assistant) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?