personal-assistant
This skill should be used whenever users request personal assistance tasks such as schedule management, task tracking, reminder setting, habit monitoring, productivity advice, time management, or any query requiring personalized responses based on user preferences and context. On first use, collects comprehensive user information including schedule, working habits, preferences, goals, and routines. Maintains an intelligent database that automatically organizes and prioritizes information, keeping relevant data and discarding outdated context.
What this skill does
# 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database that adapts to user needs, automatically managing data retention to keep relevant information while discarding outdated content.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:
```bash
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:
```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:
```bash
# 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:
```python
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:**
```python
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:**
```bash
# List all tasks in formatted view
python3 scripts/task_helper.py list
# Add a quick task
python3 scripts/task_helper.py add "Buy grocerRelated in Productivity
gitea-workflow
IncludedOrchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow', 'continue working', 'what's next', 'complete the task cycle', 'start my day', 'end the sprint', 'implement the next task', or wanting guided step-by-step development assistance. Keywords: workflow, orchestrate, agile, task cycle, sprint, daily, implement, review, PR, standup, retrospective, gitea, tea.
microsoft-graph-gateway
IncludedRoute Microsoft Graph work in this workspace. Use when users want to read or write Outlook mail, calendar events, contacts, OneDrive or SharePoint files, Teams, Planner, To Do, users, groups, directory data, or arbitrary Microsoft Graph endpoints from VS Code. Prefer WorkIQ for common read scenarios. Use Microsoft Graph for write actions and gap-read scenarios that need exact Graph properties, filters, permissions, or endpoints.
copilotkit
IncludedUse when building with CopilotKit — setup, development, integrations, debugging, upgrading, or contributing. Routes to the appropriate specialized skill based on the task.
wordly-wisdom
IncludedProvides calibrated decision analysis using Charlie Munger-style multiple mental models, inversion, incentive mapping, circle-of-competence checks, misjudgment audits, second-order effects, and forecast updates. Use when the user asks for an oracle take, a hard call, a decision memo, a premortem, an outside view, a red-team, a sanity-check, what am I missing, think this through, or wants a strategy, hire, investment, plan, product, partnership, or major life choice analysed. Avoid for simple factual lookups or time-sensitive legal, medical, or market questions without fresh evidence.
swain-session
IncludedSession management and project status dashboard. Owns the full session lifecycle (start/work/close/resume), focus lane, bookmarks, worktree detection, and tab naming. Also serves as the project status dashboard — shows active epics, progress, actionable next steps, blocked items, tasks, GitHub issues, and recommendations. Worktree creation is deferred to swain-do task dispatch (SPEC-195). Triggers on: 'session', 'status', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on', 'show me priorities', 'bookmark', 'focus on', 'session info'.
gandi
IncludedComprehensive Gandi domain registrar integration for domain and DNS management. Register and manage domains, create/update/delete DNS records (A, AAAA, CNAME, MX, TXT, SRV, and more), configure email forwarding and aliases, check SSL certificate status, create DNS snapshots for safe rollback, bulk update zone files, and monitor domain expiration. Supports multi-domain management, zone file import/export, and automated DNS backups. Includes both read-only and destructive operations with safety controls.