pi

Execute Dex skills and custom commands through the Pi AI agent.

461|129|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/davekilleen/Dex --skill pi-davekilleen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pi
Source: https://github.com/davekilleen/Dex/tree/main/.claude/reference/beta-templates/pi/skills/pi
Command: npx skills add https://github.com/davekilleen/Dex --skill pi-davekilleen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows you to easily run tasks and skills through Pi, an alternative AI coding agent, enabling direct comparison with Claude Code for evaluating performance and output quality.

Core Features & Use Cases

  • Direct Comparison: Run any Dex skill or custom command through Pi with identical context.
  • Mode Toggling: Switch between preferring Pi or Claude Code for task execution.
  • Use Case: You're developing a new feature and want to see how Pi's approach differs from Claude Code's. You can run the /build-feature skill using /pi /build-feature and then run it again using the default Claude Code to compare the results side-by-side.

Quick Start

Run the /daily-plan skill through Pi with full context.

Frequently Asked Questions about pi

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I compare AI code generation results between different agents?

Compare AI code generation results by executing identical tasks through the Pi agent and Claude Code. This Skill routes Dex skills and custom commands to the Pi AI agent with full context injection, enabling side-by-side evaluation of performance and output quality.

What is the best way to run a custom command through an alternative AI agent?

Run custom commands through an alternative AI agent by launching Pi in a dedicated terminal. This Skill integrates with user profile and vault configurations to inject comprehensive context, ensuring correct task routing and environment setup for the Pi AI agent.

Does this AI agent comparison tool support toggling between execution modes?

Yes, this AI agent comparison tool supports toggling between Pi and Claude Code for task execution. You can switch your preference to route Dex skills through either agent, allowing direct comparison of how each handles identical task execution and context injection.

Can I use my existing vault configurations when executing tasks through the Pi agent?

Yes, you can use your existing vault configurations when executing tasks through the Pi agent. The Skill integrates directly with your user profile and vault configurations to ensure proper task routing and environment setup during comparative analysis and custom command execution.

Why does task execution context matter when comparing AI coding agents?

Task execution context matters when comparing AI coding agents because output quality depends on environment setup. This Skill ensures fair comparative analysis by injecting comprehensive context from your user profile and vault configurations into the Pi agent, matching Claude Code's execution environment.