zemptime-marketplace

Use when writing Rails controllers or implementing state changes - enforces resource extraction, thin controllers delegating to models, params.expect, and controller concerns for scoping

Use when designing database schema, writing migrations, or making data storage decisions - enforces UUIDs, account_id multi-tenancy, no foreign keys, and proper index patterns

Use when writing Hotwire (Turbo/Stimulus) code in Rails - enforces dom_id helpers, morph updates, focused Stimulus controllers, and JavaScript private methods

Use when writing background jobs or async operations - enforces thin job wrappers (3-5 lines) that delegate to models using _later/_now naming pattern

Use when writing Rails models - enforces state-as-records not booleans, concerns as adjectives namespaced under model, and concern extraction triggers

Use when naming classes, methods, routes in vanilla Rails codebases - enforces concern adjectives (-able/-ible only), no bangs for state, resource naming cascade, and commit message format

Use when defining Rails routes, organizing controller directories, or adding resources - enforces resource extraction, shallow nesting, resolve helpers, and module scoping

Use after brainstorming to apply vanilla-rails patterns to a feature, producing structured handoff for implementation planning. Invoke with /shape.

Use when writing Ruby/Rails code - enforces expanded conditionals over guard clauses, private indentation, invocation-order methods, and bang method restrictions that contradict standard Ruby guides

Use when writing Rails tests - enforces fixtures-only, integration-style controller tests, Current.session setup, simple naming, and Minitest syntax (NO FactoryBot, NO RSpec)

Use when writing ERB templates, partials, or view helpers - covers partial organization, optional locals, CSS class patterns, and collection rendering with caching

Use when generating any output a human will read — interfaces, documentation, data visualizations, CLI output, tables, diagrams

Use when defining who the actors in a service are — segments, JTBD forces, context, constraints, and relationships between actors

Use when you need to understand what users believe, feel, and predict — builds empathy maps with emotional/informational layers from research, transcripts, and code

Use when identifying where user mental models diverge from system reality, where moments of truth occur, and where information scent misleads — finds the structural causes of confusion

Use when mapping what a user experiences over time — actions, thoughts, emotions, touchpoints across pre-service, during-service, and post-service stages

Use when mapping how a service actually works — frontstage/backstage/support lanes from code, docs, and operational knowledge

Use when starting or continuing service design analysis for a project — checks what artifacts exist, identifies gaps, recommends which analytical skill to run next

Use when you have existing service design artifacts and want to stress-test them — finds contradictions, blind spots, missing coverage, and unsupported claims across the artifact suite

Use when you have new source material (transcripts, interviews, support logs, docs, code changes) and want to reason about what existing service design artifacts need updating

Use when identifying bottlenecks, waste, and failure modes in a service — designs PDSA improvement experiments with lane-anchored measures

Use when mapping all actors in a service ecosystem — who serves whom, dependencies, interest alignment and conflict, power dynamics

Use when designing content systems where 5+ distinct types need to comingle in feeds, timelines, or searches with shared metadata and operations - NOT for simple polymorphic associations or 1-3 similar types

Use when refactoring fat Rails models with repetitive prefixes like entropy_*, notification_*, or multi-association coordination. Extracts PORO wrappers that group operations around nouns/concepts.