shine-research-phase

Spawn a shine-phase-researcher agent to generate a RESEARCH.md entry.

1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/diShine-digital-agency/SHINE-Code-System --skill shine-research-phase
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: shine-research-phase
Source: https://github.com/diShine-digital-agency/SHINE-Code-System/tree/main/skills/shine-research-phase
Command: npx skills add https://github.com/diShine-digital-agency/SHINE-Code-System --skill shine-research-phase

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Research how to implement a phase using a dedicated shine-phase-researcher agent.

Core Features & Use Cases

  • Standalone research command to explore phase feasibility and architecture.
  • Spawns shine-phase-researcher agent to gather context, validate against roadmap, and produce RESEARCH.md.
  • Use Case: perform pre-planning research before committing to a plan.

Quick Start

Initiate Phase Research by specifying a phase number to start the shine-phase-researcher workflow and generate the initial RESEARCH.md.

Frequently Asked Questions about shine-research-phase

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

FAQPage Schema
How do I perform standalone phase research before committing to a project roadmap?

Pre-planning phase research validates feasibility and architecture by spawning a dedicated agent to gather context, check roadmap alignment, and generate a RESEARCH.md entry before committing to a plan.

What do I need to start phase research for a specific development cycle?

Starting phase research requires a phase number argument and access to existing roadmap data. The workflow spawns a researcher agent to analyze context and generate an initial RESEARCH.md entry.

When do I need to run a standalone research workflow for a phase?

You need standalone phase research when exploring implementation feasibility before planning, or when re-evaluating architecture after a roadmap check. It validates context before committing to a plan.

What is the best way to re-evaluate a phase after a roadmap check?

The best way to re-evaluate a phase after a roadmap check is running standalone phase research. This spawns a researcher agent to gather updated context, validate architecture, and rewrite the RESEARCH.md entry.

Does phase research work without an existing roadmap?

Phase research does not work without an existing roadmap. The workflow explicitly requires access to roadmap data to validate context and produce accurate feasibility results in the RESEARCH.md entry.