msd-core/commands/gsd/research-phase.md at e8d68685c1091c73eaf6740b6825466f55779464

Files

Lex Christopherson e8d68685c1 feat(gsd): add research-phase for niche domain ecosystem discovery

- Add /gsd:research-phase command for comprehensive ecosystem research
- Rename FINDINGS.md → DISCOVERY.md for clarity
- Rename research-phase.md → discovery-phase.md (shallow "which library")
- New research-phase.md for deep "how experts build this" research
- Creates RESEARCH.md with stack, patterns, pitfalls, don't-hand-roll
- plan-phase loads RESEARCH.md when present

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2025-12-15 18:15:22 -06:00

2.9 KiB

Raw Blame History

description, argument-hint, allowed-tools

description

argument-hint

allowed-tools

Research how to implement a phase before planning

[phase]

Read

Bash

Glob

Grep

Write

WebFetch

WebSearch

mcp__context7__*

Comprehensive research on HOW to implement a phase before planning.

This is for niche/complex domains where Claude's training data is sparse or outdated. Research discovers:

What libraries exist for this problem
What architecture patterns experts use
What the standard stack looks like
What problems people commonly hit
What NOT to hand-roll (use existing solutions)

Output: RESEARCH.md with ecosystem knowledge that informs quality planning.

<execution_context> @~~/.claude/get-shit-done/workflows/research-phase.md @~~/.claude/get-shit-done/templates/research.md @~/.claude/get-shit-done/references/research-pitfalls.md </execution_context>

Phase number: $ARGUMENTS (required)

Load project state: @.planning/STATE.md

Load roadmap: @.planning/ROADMAP.md

Load phase context if exists: Check for .planning/phases/XX-name/{phase}-CONTEXT.md - bonus context from discuss-phase.

1. Validate phase number argument (error if missing or invalid) 2. Check if phase exists in roadmap - extract phase description 3. Check if RESEARCH.md already exists (offer to update or use existing) 4. Load CONTEXT.md if it exists (bonus context for research direction) 5. Follow research-phase.md workflow: - Analyze phase to identify knowledge gaps - Determine research domains (architecture, ecosystem, patterns, pitfalls) - Execute comprehensive research via Context7, official docs, WebSearch - Cross-verify all findings - Create RESEARCH.md with actionable ecosystem knowledge 6. Offer next steps (plan the phase)

<when_to_use> Use research-phase for:

3D graphics (Three.js, WebGL, procedural generation)
Game development (physics, collision, AI, procedural content)
Audio/music (Web Audio API, DSP, synthesis)
Shaders (GLSL, Metal, ISF)
ML/AI integration (model serving, inference, pipelines)
Real-time systems (WebSockets, WebRTC, sync)
Specialized frameworks with active ecosystems
Any domain where "how do experts do this" matters

Skip research-phase for:

Standard web dev (auth, CRUD, REST APIs)
Well-known patterns (forms, validation, testing)
Simple integrations (Stripe, SendGrid with clear docs)
Commodity features Claude handles well </when_to_use>

<success_criteria>

Phase validated against roadmap
Domain/ecosystem identified from phase description
Comprehensive research executed (Context7 + official docs + WebSearch)
All WebSearch findings cross-verified with authoritative sources
RESEARCH.md created with ecosystem knowledge
Standard stack/libraries identified
Architecture patterns documented
Common pitfalls catalogued
What NOT to hand-roll is clear
User knows next steps (plan phase) </success_criteria>

2.9 KiB Raw Blame History

2.9 KiB

Raw Blame History