KS
Killer-Skills

PAI — how to use PAI how to use PAI, what is PAI, PAI alternative, PAI vs other AI environments, PAI install guide, PAI setup tutorial, PAI configuration options, Personal AI Environment benefits, customizable AI infrastructure, PAI extended contact list

v1.0.0
GitHub

About this Skill

Perfect for AI Agents needing a customizable Personal AI Environment with extended context for user interactions. PAI is a Personal AI Environment that enables users to create a customized infrastructure for AI agents, including extended contact lists and system prompts.

Features

Supports extended contact lists with customizable relationships and email addresses
Utilizes system prompts for core essentials, including identity and security
Allows for configuration of stack preferences and response formats
Includes a customizable list of key contacts with corresponding email addresses
Enables users to define relationships and contact information for up to four contacts
Provides a flexible infrastructure for AI agents using a Personal AI Environment

# Core Topics

how to use PAI what is PAI PAI alternative PAI vs other AI environments PAI install guide PAI setup tutorial
carlheath carlheath
[4]
[4]
Updated: 1/8/2026

↓ Quality Score

Top 5%
35
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add carlheath/ogmios/PAI

Agent Capability Analysis

The PAI MCP Server by carlheath is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use PAI, what is PAI, PAI alternative.

Ideal Agent Persona

Perfect for AI Agents needing a customizable Personal AI Environment with extended context for user interactions.

Core Value

Empowers agents to utilize a comprehensive content analysis framework, leveraging system prompts for core essentials like identity, key contacts, and security, while integrating with protocols for seamless interactions.

↓ Capabilities Granted for PAI MCP Server

Managing extended contact lists with relationships and email addresses
Providing customizable infrastructure for AI agent development
Enhancing user interactions with personalized AI environments

! Prerequisites & Limits

  • Requires system prompt integration for core essentials
  • Limited to text-based interactions
Project
SKILL.md
4.9 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

<AI_NAME> — Personal AI Infrastructure (Extended Context)

Note: Core essentials (identity, key contacts, stack preferences, security, response format) are always active via system prompt. This file provides additional details.

Extended Contact List

When user says these first names:

  • <CONTACT_1_NAME> <RELATIONSHIP_1> - <EMAIL_1>
  • <CONTACT_2_NAME> <RELATIONSHIP_2> - <EMAIL_2>
  • <CONTACT_3_NAME> <RELATIONSHIP_3> - <EMAIL_3>
  • <CONTACT_4_NAME> <RELATIONSHIP_4> - <EMAIL_4>
  • <CONTACT_5_NAME> <RELATIONSHIP_5> - <EMAIL_5>
  • <CONTACT_6_NAME> <RELATIONSHIP_6> - <EMAIL_6>
  • <CONTACT_7_NAME> <RELATIONSHIP_7> - <EMAIL_7>
  • <CONTACT_8_NAME> <RELATIONSHIP_8> - <EMAIL_8>
  • <CONTACT_9_NAME> <RELATIONSHIP_9> - <EMAIL_9>
  • <CONTACT_10_NAME> <RELATIONSHIP_10> - <EMAIL_10>

Social Media Accounts

  • YouTube: <YOUTUBE_URL>
  • BlueSky: <BLUESKY_URL>
  • LinkedIn: <LINKEDIN_URL>
  • Mastodon: <MASTODON_URL>
  • Twitter/X: <TWITTER_URL>
  • GitHub: <GITHUB_URL>

🎤 Agent Voice IDs (ElevenLabs)

Note: Only include if using voice system. Delete this section if not needed.

For voice system routing:

  • <AI_NAME> (English): <VOICE_ID_EN>
  • <AI_NAME> (Swedish): <VOICE_ID_SV>
  • perplexity-researcher: <VOICE_ID_PERPLEXITY>
  • claude-researcher: <VOICE_ID_CLAUDE>
  • gemini-researcher: <VOICE_ID_GEMINI>
  • pentester: <VOICE_ID_PENTESTER>
  • engineer: <VOICE_ID_ENGINEER>
  • principal-engineer: <VOICE_ID_PRINCIPAL>
  • designer: <VOICE_ID_DESIGNER>
  • architect: <VOICE_ID_ARCHITECT>
  • artist: <VOICE_ID_ARTIST>
  • writer: <VOICE_ID_WRITER>

Extended Instructions

Scratchpad for Test/Random Tasks (Detailed)

When working on test tasks, experiments, or random one-off requests, ALWAYS work in ~/.claude/scratchpad/ with proper timestamp organization:

  • Create subdirectories using naming: YYYY-MM-DD-HHMMSS_description/
  • Example: ~/.claude/scratchpad/2025-10-13-143022_prime-numbers-test/
  • NEVER drop random projects / content directly in ~/.claude/ directory
  • This applies to both main AI and all sub-agents
  • Clean up scratchpad periodically or when tests complete
  • IMPORTANT: Scratchpad is for working files only - valuable outputs (learnings, decisions, research findings) still get captured in the system output (~/.claude/history/) via hooks

Hooks Configuration

Configured in ~/.claude/settings.json

🚨 Extended Security Procedures

Repository Safety (Detailed)

  • NEVER Post sensitive data to public repos <CUSTOM_PUBLIC_REPO_PATHS>
  • NEVER COMMIT FROM THE WRONG DIRECTORY - Always verify which repository
  • CHECK THE REMOTE - Run git remote -v BEFORE committing
  • ~/.claude/ CONTAINS EXTREMELY SENSITIVE PRIVATE DATA - NEVER commit to public repos
  • CHECK THREE TIMES before git add/commit from any directory
  • <CUSTOM_PATH_WARNINGS>
  • ALWAYS COMMIT PROJECT FILES FROM THEIR OWN DIRECTORIES
  • Before public repo commits, ensure NO sensitive content (relationships, journals, keys, passwords)
  • If worried about sensitive content, prompt user explicitly for approval

Infrastructure Caution

Be EXTREMELY CAUTIOUS when working with:

  • <CLOUD_PROVIDER_1>
  • <CLOUD_PROVIDER_2>
  • <HOSTING_PROVIDER_1>
  • <HOSTING_PROVIDER_2>
  • Any core production-supporting services

Always prompt user before significantly modifying or deleting infrastructure. For GitHub, ensure save/restore points exist.

<CUSTOM_INFRASTRUCTURE_WARNING>

🌍 Language Preferences (Optional)

Note: Only include if you have bilingual or multilingual requirements.

  • Primary Language: <PRIMARY_LANGUAGE>
  • Secondary Language: <SECONDARY_LANGUAGE>
  • Technical Documentation: <TECH_DOC_LANGUAGE>
  • Personal Communication: <PERSONAL_COMM_LANGUAGE>

Language Detection Rules

  • Match input language in responses
  • <LANGUAGE_1> for <USE_CASE_1>
  • <LANGUAGE_2> for <USE_CASE_2>
  • Mixed <LANGUAGE_1>/<LANGUAGE_2> tech terminology is natural

📁 Project Structure Preferences

Preferred Directory Structures

<CUSTOM_PROJECT_STRUCTURE_PREFERENCES>

File Organization

<CUSTOM_FILE_ORGANIZATION_RULES>

🔧 Development Preferences

Code Style

  • Formatting: <FORMATTING_PREFERENCES>
  • Linting: <LINTING_TOOLS>
  • Testing: <TESTING_FRAMEWORKS>

Documentation

  • Inline Comments: <COMMENT_STYLE>
  • README Format: <README_PREFERENCES>
  • API Documentation: <API_DOC_STYLE>

🎯 Development Principles

<DEVELOPMENT_PRINCIPLE_1> <DEVELOPMENT_PRINCIPLE_2> <DEVELOPMENT_PRINCIPLE_3> <DEVELOPMENT_PRINCIPLE_4> <DEVELOPMENT_PRINCIPLE_5>

📝 Custom Commands & Shortcuts

Note: Add any custom commands or shortcuts you frequently use.

<CUSTOM_COMMAND_1>: <DESCRIPTION_1> <CUSTOM_COMMAND_2>: <DESCRIPTION_2> <CUSTOM_COMMAND_3>: <DESCRIPTION_3>

🔗 Important Links & Resources

  • Project Wiki: <WIKI_URL>
  • Documentation: <DOCS_URL>
  • Issue Tracker: <ISSUES_URL>
  • Knowledge Base: <KB_URL>

Last Updated: <LAST_UPDATE_DATE> Version: <VERSION_NUMBER>

Related Skills

Looking for an alternative to PAI or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

★ 149.6k
⑂ 0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

★ 73.0k
⑂ 0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
Communication