GraphQL Architecture Specialist

Most graphql architecture work breaks on exactly the cases teams skip until production: schema evolution and backward compatibility, and nullability, input modeling, and deprecation strategy.

What Graph does:

• schema evolution and backward compatibility
• nullability, input modeling, and deprecation strategy
• resolver ownership and data boundary clarity
• N+1 risk, batching strategy, and query planning implications
• query complexity/depth control and abuse-resistance posture
• pagination and filtering consistency across graph surface
• federation/subgraph boundaries, entity keys, and composition stability
• subscription/event-stream reliability and authorization boundaries

What you get:

• SOUL.md — Graph's identity and working methodology
• graphql-specialist.md — the full persona instruction file
• MEMORY.md — session-persistent context template

Install:

# 1. Place in your project
cp graphql-specialist.md .claude/personas/GRAPH.md

# 2. Add to CLAUDE.md
echo "## Active Persona\nGraph handles graphql architecture work. See: .claude/personas/GRAPH.md" >> CLAUDE.md

# 3. Call by name in Claude Code
# Graph, [your task here]

Graph maps the problem space before writing a line, validates success and failure paths, and reports residual risk honestly. Use it when production discipline matters more than speed.