Superset Agent Standup
superset-sh/superset
Sweeps every Superset workspace, task and agent terminal to report what finished, what needs review and what is blocked, read-only, and can publish the digest as a page.
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…
$ npx skills add ailabs-393/ai-labs-claude-skills --skill personal-assistant -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ailabs-393/ai-labs-claude-skills personal-assistant --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ailabs-393/ai-labs-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/skills/personal-assistant .claude/skills/personal-assistant && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "personal-assistant" agent skill from https://github.com/ailabs-393/ai-labs-claude-skills/tree/main/packages/skills/personal-assistant into .claude/skills/personal-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "personal-assistant", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ailabs-393/ai-labs-claude-skills/tree/main/packages/skills/personal-assistantType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ailabs-393/ai-labs-claude-skills --skill personal-assistant -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ailabs-393/ai-labs-claude-skills personal-assistant --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ailabs-393/ai-labs-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/skills/personal-assistant .agents/skills/personal-assistant && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "personal-assistant" agent skill from https://github.com/ailabs-393/ai-labs-claude-skills/tree/main/packages/skills/personal-assistant into .agents/skills/personal-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "personal-assistant", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ailabs-393/ai-labs-claude-skills --skill personal-assistant -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ailabs-393/ai-labs-claude-skills personal-assistant --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ailabs-393/ai-labs-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/skills/personal-assistant .cursor/skills/personal-assistant && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "personal-assistant" agent skill from https://github.com/ailabs-393/ai-labs-claude-skills/tree/main/packages/skills/personal-assistant into .cursor/skills/personal-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "personal-assistant", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ailabs-393/ai-labs-claude-skills.git --path packages/skills/personal-assistant--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ailabs-393/ai-labs-claude-skills --skill personal-assistant -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ailabs-393/ai-labs-claude-skills personal-assistant --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ailabs-393/ai-labs-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/skills/personal-assistant .gemini/skills/personal-assistant && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "personal-assistant" agent skill from https://github.com/ailabs-393/ai-labs-claude-skills/tree/main/packages/skills/personal-assistant into .gemini/skills/personal-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "personal-assistant", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ailabs-393/ai-labs-claude-skills personal-assistantInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ailabs-393/ai-labs-claude-skills --skill personal-assistant -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ailabs-393/ai-labs-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/skills/personal-assistant .github/skills/personal-assistant && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "personal-assistant" agent skill from https://github.com/ailabs-393/ai-labs-claude-skills/tree/main/packages/skills/personal-assistant into .github/skills/personal-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "personal-assistant", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ailabs-393/ai-labs-claude-skills --skill personal-assistant -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ailabs-393/ai-labs-claude-skills personal-assistant --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ailabs-393/ai-labs-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/skills/personal-assistant .opencode/skills/personal-assistant && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "personal-assistant" agent skill from https://github.com/ailabs-393/ai-labs-claude-skills/tree/main/packages/skills/personal-assistant into .opencode/skills/personal-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "personal-assistant", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
personal-assistantThis 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…
Personal Assistant is an agent skill from ailabs-393/ai-labs-claude-skills. 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…
Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `index.js`, `package.json` and `references/assistant_capabilities.md`).
It sits in Productivity & Automation, covering Task management. The repository describes itself as: This package is use to remove the hustle of finding claudeskills and shift them into any of the user project. This project become a bridge between user's usage and claude skills. The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 1a12bc7. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (Python and JavaScript), which the agent can run.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Personal Assistant loads about 4.9k tokens when it runs, and up to ~7.1k if it reads all its reference files. Until then it costs about 142 tokens; SKILL.md has 916 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from ailabs-393/ai-labs-claude-skills at commit 1a12bc7, republished under its MIT licence (© ailabs-393). 916 words, ~4,856 tokens.
.claude/skills/personal-assistant/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.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.
Invoke this skill for personal assistance queries, including:
Before providing any personalized assistance, always check if a user profile exists:
python3 scripts/assistant_db.py has_profileIf the output is "false", proceed to Step 2 (Initial Setup). If "true", proceed to Step 3 (Load Profile and Context).
When no profile exists, collect comprehensive information from the user. Use a conversational, friendly approach to gather this data.
Essential Information to Collect:
Personal Details
Schedule & Working Habits
Goals & Priorities
Habits & Routines
Preferences & Communication Style
Current Commitments
Tools & Integration
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.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 summaryOr 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()Apply the loaded profile and context to provide tailored assistance:
Key Principles:
Respect User Preferences
Leverage Context
Be Proactive
Maintain Context
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?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 workCompleting 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"
})Manage calendar events and recurring commitments:
Adding Events:
from assistant_db import add_event
# One-time event
event = {
"title": "Dentist appointment",
"date": "2025-11-12",
"time": "14:00",
"duration": "1 hour",
"location": "Downtown Dental",
"notes": "Bring insurance card"
}
add_event(event, recurring=False)
# Recurring event
recurring_event = {
"title": "Team standup",
"frequency": "daily",
"time": "10:00",
"duration": "15 minutes",
"days": ["Monday", "Tuesday", "Wednesday", "Thursday", "Friday"]
}
add_event(recurring_event, recurring=True)Getting Upcoming Events:
from assistant_db import get_events
# Get events for next 7 days
upcoming = get_events(days_ahead=7)
# Get events for next 30 days
monthly = get_events(days_ahead=30)Maintain context for continuity and personalized assistance:
Adding Context:
from assistant_db import add_context
# Track an interaction
add_context("interaction", "User mentioned struggling with morning productivity", "normal")
# Add an important note (kept indefinitely)
add_context("note", "User prefers written communication over calls for work matters", "high")
# Add temporary context (auto-cleaned after 7 days)
add_context("temporary", "Currently working on project X deadline next week", "normal")Context Importance Levels:
"low" - Automatically cleaned up quickly"normal" - Standard retention (30 days for interactions, 7 days for temporary)"high" - Kept indefinitely (for important notes) or extended retentionRetrieving Context:
from assistant_db import get_context
# Get all context
all_context = get_context()
# Get specific type
interactions = get_context("recent_interactions")
notes = get_context("important_notes")
temp = get_context("temporary_context")The system automatically manages data retention, but you can trigger manual cleanup:
# Clean up data older than 30 days (default)
python3 scripts/assistant_db.py cleanup
# Clean up with custom retention period
python3 scripts/assistant_db.py cleanup 60What Gets Cleaned:
When users want to update their profile or preferences:
from assistant_db import get_profile, save_profile
# Load current profile
profile = get_profile()
# Update specific fields
profile["work_hours"]["start"] = "08:00"
profile["preferences"]["reminder_style"] = "firm"
# Save updated profile
save_profile(profile)Or update schedule information:
from assistant_db import get_schedule, save_schedule
schedule = get_schedule()
schedule["working_hours"]["Friday"] = {"start": "09:00", "end": "15:00"}
save_schedule(schedule)Always Load Context First
Be Proactive
Respect Preferences
Maintain Continuity
Keep Data Fresh
Provide Value
Update Incrementally
Example 1: First-Time User
User: "Help me organize my week"
Claude: [Checks profile - finds none]
I'd love to help you organize your week! To provide the most personalized assistance,
let me first learn about your schedule and preferences. This will only take a few minutes.
What's your typical work schedule like? For example, do you work 9-5, have flexible
hours, or something else?
[Proceeds through profile setup]
Great! Now let me look at your week and help you organize it effectively...Example 2: Task Management
User: "I have so many things to do, I'm overwhelmed"
Claude: [Loads tasks - finds 15 pending tasks, 8 with no due date]
I can see you have 15 pending tasks. Let me help you prioritize based on your goals
and schedule.
High Priority (Due Soon):
1. Quarterly report - Due Tuesday (aligns with your career goals)
2. Client presentation - Due Thursday
Medium Priority (This Week):
3. Code review - No deadline but good for Friday afternoon
4. Team feedback - Due next Monday
Let's start with the top 2. Your morning blocks (9-11am) work best for focused work
like the quarterly report. Shall I schedule it for tomorrow morning?
[Helps organize and prioritize based on profile]Example 3: Schedule Optimization
User: "I want to start exercising regularly"
Claude: [Loads profile - finds: evening person, free 18:00-19:00 most days]
Based on your schedule and preferences, I can see you're typically free between
6-7pm on weekdays. This aligns well with your peak energy time in the evenings.
I recommend:
- Monday, Wednesday, Friday: 18:00-19:00 (gym or home workout)
- Start with 30-minute sessions
This gives you recovery days and doesn't conflict with your Tuesday team dinner
or Thursday book club.
Shall I add these as recurring events to your calendar?Example 4: Returning User with Context
User: "How's my progress on learning Python?"
Claude: [Loads context - finds: Goal to learn Python, completed 4 tutorial sessions,
last one was 5 days ago]
You're making good progress! You've completed 4 Python tutorial sessions over the
past 3 weeks. However, I notice it's been 5 days since your last session.
To maintain momentum toward your 3-month goal, let's schedule your next session.
Your usual Thursday 7pm slot is open tomorrow. Does that work?
Also, you're at the point where building a small project would be valuable. What
interests you - a web scraper, a to-do app, or something else?Example 5: Preference Update
User: "I've started a new job, my schedule has changed"
Claude: [Loads current profile]
Congratulations on the new job! Let me update your profile with your new schedule.
What are your new working hours? And have any of your recurring commitments changed?
[Collects updated information and saves]
Perfect! I've updated your profile with your new 8-4 schedule and remote work setup.
I'll adjust all my suggestions accordingly. Your morning productivity block is now
8-10am instead of 9-11am.Data Storage Location:
All data is stored in ~/.claude/personal_assistant/:
profile.json - User profile and preferencestasks.json - Task list and completed tasksschedule.json - Calendar events and recurring commitmentscontext.json - Interaction history, notes, and temporary contextDatabase Commands:
# Profile management
python3 scripts/assistant_db.py has_profile
python3 scripts/assistant_db.py get_profile
# Task management
python3 scripts/assistant_db.py get_tasks
# Schedule management
python3 scripts/assistant_db.py get_schedule
# Context management
python3 scripts/assistant_db.py get_context
# Utilities
python3 scripts/assistant_db.py summary # Quick overview
python3 scripts/assistant_db.py cleanup [days] # Clean old data
python3 scripts/assistant_db.py export # Export all data
python3 scripts/assistant_db.py reset # Reset everythingTask Helper Commands:
python3 scripts/task_helper.py list
python3 scripts/task_helper.py add <title> [priority] [due_date] [category]
python3 scripts/task_helper.py complete <task_id>
python3 scripts/task_helper.py overdue
python3 scripts/task_helper.py today
python3 scripts/task_helper.py week
python3 scripts/task_helper.py category <name>Data Retention Policy:
Profile Data Structure:
{
"initialized": true,
"name": "John Doe",
"preferred_name": "John",
"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": ["Learn Python", "Run 5K"],
"long_term": ["Career advancement", "Financial independence"]
},
"working_style": "morning person"
}Main database management module providing:
Convenience script for quick task operations:
© ailabs-393, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (scripts, references) in packages/skills/personal-assistant of ailabs-393/ai-labs-claude-skills.
Open the folder on GitHubat commit 1a12bc7
Personal Assistant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Personal Assistant this skillailabs-393/ai-labs-claude-skills | 454 | — | ~4.9k | Automated safety check: Pass | MIT | |
| Superset Agent Standupsuperset-sh/superset | 15k | — | ~712 | Automated safety check: Pass | Custom licence | |
| AgentRQ Workspace Agentagentrq/agentrq | 1.1k | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 | |
| Markdown Task Managerioniks/MarkdownTaskManager | 535 | — | ~2.2k | Automated safety check: Pass | MPL-2.0 | |
| Pi Messenger Crewnicobailon/pi-messenger | 720 | — | ~3.7k | Automated safety check: Pass | None | |
| Codekanban CLIfy0/CodeKanban | 225 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 |
superset-sh/superset
Sweeps every Superset workspace, task and agent terminal to report what finished, what needs review and what is blocked, read-only, and can publish the digest as a page.
agentrq/agentrq
Guides a workspace agent through executing assigned tasks, replying to a remote human operator, and creating sub-tasks, memory and events inside an AgentRQ workspace.
ioniks/MarkdownTaskManager
A skill your agent uses when managing tasks, the system is a Kanban task manager based on local Markdown files (kanban.md and archive.md).
nicobailon/pi-messenger
Orchestrator reference for pi-messenger Crew planning, task management, configuration, and agent coordination.
fy0/CodeKanban
Operate CodeKanban workflows, terminal sessions, and web sessions through the installable codekanban-cli command.
Luciole-Studio/Misaka-Agent
Plan and run multi-agent video production pipelines. An agent skill from Luciole-Studio/Misaka-Agent.
ailabs-393/ai-labs-claude-skills
This skill should be used when analyzing HTML/CSS websites for SEO optimization, fixing SEO issues, generating SEO reports, or implementing SEO best practices.
ailabs-393/ai-labs-claude-skills
This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability.
ailabs-393/ai-labs-claude-skills
This skill should be used when the user requests to create professional business documents (proposals, business plans, or budgets) from templates.
ailabs-393/ai-labs-claude-skills
Comprehensive startup idea validation and market analysis tool.
ailabs-393/ai-labs-claude-skills
This skill should be used when containerizing applications with Docker, creating Dockerfiles, docker-compose configurations, or deploying containers to various platforms.
ailabs-393/ai-labs-claude-skills
Assist writers with story planning, character development, plot structuring, chapter writing, timeline tracking, and consistency checking.
Categories
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…. Personal Assistant is an agent skill from ailabs-393/ai-labs-claude-skills. 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.
Personal Assistant fits situations like: tasks that involve Task management.
Run `npx skills add ailabs-393/ai-labs-claude-skills --skill personal-assistant -a claude-code`. Or copy the skill folder (packages/skills/personal-assistant in ailabs-393/ai-labs-claude-skills) into .claude/skills/personal-assistant in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ailabs-393/ai-labs-claude-skills --skill personal-assistant -a codex`. Or copy the skill folder (packages/skills/personal-assistant in ailabs-393/ai-labs-claude-skills) into .agents/skills/personal-assistant in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ailabs-393/ai-labs-claude-skills --skill personal-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/personal-assistant, .gemini/skills/personal-assistant, .github/skills/personal-assistant and .opencode/skills/personal-assistant in your project.
Going by SKILL.md and its folder, Personal Assistant needs Python and JavaScript for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; Node.js.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Personal Assistant is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.9k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Personal Assistant: Superset Agent Standup (superset-sh/superset, 15k stars), AgentRQ Workspace Agent (agentrq/agentrq, 1.1k stars), Markdown Task Manager (ioniks/MarkdownTaskManager, 535 stars) and Pi Messenger Crew (nicobailon/pi-messenger, 720 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ailabs-393 (a GitHub user) maintains it in ailabs-393/ai-labs-claude-skills, which has 454 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on November 11, 2025.
Source: ailabs-393/ai-labs-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.