pi

Name: pi
Availability: InStock
Author: whmathews15

Route build and comparison tasks through Pi with vault context.

1|Updated Jun 28, 2026

Search Tags:#claude code #context injection #skill routing #pi #comparison testing #terminal launch #beta mode

Ready to run

npx skills add https://github.com/whmathews15/DEX-Personal-Operating-System --skill pi-whmathews15

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pi
Source: https://github.com/whmathews15/DEX-Personal-Operating-System/tree/main/.claude/reference/beta-templates/pi/skills/pi
Command: npx skills add https://github.com/whmathews15/DEX-Personal-Operating-System --skill pi-whmathews15

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill lets you route work through Pi so you can compare its output against Claude Code without manually rebuilding the task context each time.

Core Features & Use Cases

Pi mode switching: Turn Pi preference on or off for the session so future build requests are routed consistently.
Skill-aware execution: Run a specific Dex skill through Pi with the same instructions Claude Code would receive.
Custom task launching: Send an ad hoc request to Pi in a new terminal window for side-by-side comparison.
Use case: A product manager can test whether Pi or Claude Code produces better daily planning, relationship tracking, or tool-building results for the same prompt.

Quick Start

Ask the assistant to enable Pi mode so your next build task is launched through Pi with the appropriate vault context.

Frequently Asked Questions about pi

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

FAQPage Schema

How do I compare Pi and Claude Code outputs for the same task?▼

To compare Pi and Claude Code outputs, you route build requests through Pi using a single command that automatically injects full vault context. This launches Pi in a new terminal window for side-by-side comparison testing without manually rebuilding the task context.

How do I route a specific Dex skill through Pi instead of Claude Code?▼

You route a specific Dex skill through Pi by requesting skill-aware execution, which sends the exact same instructions Claude Code would receive. This ensures the comparison test is isolated to the model's reasoning rather than differences in task context.

Can I toggle Pi mode for my entire session instead of running individual commands?▼

Yes, you can enable Pi mode to consistently route all future build requests through Pi for the duration of your session. This prevents the need to manually specify Pi for every individual task launch.

What happens if Pi or the required skill files are missing during a task launch?▼

If Pi or the required skill files are missing during a task launch, the environment-aware terminal launch process triggers error handling. This prevents silent failures and alerts you to the missing dependencies needed for context injection.

Does context injection work the same way when launching ad hoc requests in a new terminal?▼

Yes, context injection works the same way for ad hoc requests, gathering the necessary vault context before launching Pi in a new terminal window. This allows you to test custom prompts side-by-side with Claude Code results.