gpd-discuss-phase

Identifies physics-aware gray areas and structures them into a decision-rich CONTEXT.md for downstream agents.

Updated Mar 15, 2026
One-click install
npx skills add https://github.com/MichaelsEngineering/get-physics-done-test --skill gpd-discuss-phase-michaelsengineering
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gpd-discuss-phase
Source: https://github.com/MichaelsEngineering/get-physics-done-test/tree/main/.agents/skills/gpd-discuss-phase
Command: npx skills add https://github.com/MichaelsEngineering/get-physics-done-test --skill gpd-discuss-phase-michaelsengineering

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured, AI-assisted workflow for planning research phases by extracting gray-area decisions and generating a formal CONTEXT.md to guide downstream agents.

Core Features & Use Cases

  • Identify phase-specific gray areas from ROADMAP.md and phase goals, focusing on physics-aware methodological decisions.
  • Conduct Socratic dialogue with controlled questioning (4 questions per area) and track answers to build a decision-rich CONTEXT.md.
  • Preserve user-stated observables, deliverables, references, and stop conditions to ensure continuity across phases.
  • Produce a ready-to-review CONTEXT.md plus a compact planning summary for the next steps.
  • Support deferment of ideas to future phases while keeping track of context.

Quick Start

Initiate a gpd-discuss-phase session for a specified phase, then select gray areas to discuss and generate CONTEXT.md.

Frequently Asked Questions about gpd-discuss-phase

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

FAQPage Schema
How do I structure a research phase decision context for downstream AI agents?

You can structure a research phase decision context by using a Socratic dialogue to probe physics-aware gray areas, surfacing assumptions, and recording decisions into a formal CONTEXT.md file to guide downstream agents.

What is the best way to identify methodological gray areas in a research workflow?

The best way to identify methodological gray areas in a research workflow is to analyze your ROADMAP.md and phase goals, isolating physics-aware decisions that require structured probing before execution.

Can I preserve user-stated observables and references when planning research phases?

Yes, you can preserve user-stated observables, deliverables, references, and stop conditions during phase planning, ensuring continuity across downstream agents without requiring further user prompts.

How does Socratic dialogue work for phase planning context management?

Socratic dialogue for phase planning works by asking controlled questions, typically four per gray area, tracking your answers to build a decision-rich context file while deferring non-phase ideas to future phases.

Do I need a ROADMAP.md to start generating a CONTEXT.md for my research workflow?

Yes, you need a ROADMAP.md and defined phase goals to start, as the process extracts phase-specific gray areas from these inputs to produce a ready-to-review CONTEXT.md and a compact planning summary.