adobe/data

build-app-entry

Wire built features into a running application — import peer schemas, lazy-load peers, and mount the root UI.

build-data

Build a feature's data/ layer — data-type namespaces and the State spec. The first, foundational feature phase.

build-systems

Build a feature's system-database — the real-time tick loop (systems the scheduler runs each frame). For real-time features only.

build-services

Build a feature's services/ layer — async capability contracts (ports to the outside world). Optional.

build-transactions

Build a feature's transaction-database — atomic mutations over the store.

meta-build

Iteratively build an application or game phase-by-phase in clean subagents, reviewing each phase and refining the build-* skills / rules until each is optimal, then summarizing.

review

Review built feature/application output against the @adobe/data feature rules; report whether it is optimal and where any fix belongs. Read-only.

build-actions

Build a feature's action-database — async orchestration over services and transactions. If the feature has async flows or side effects outside of the main store.

build-computed

Build a feature's computed-database — derived observable values.

build-core-database

Build a feature's schema — the core-database (components, resources, archetypes). The first main-service layer.

build-game

Build a game — an application whose features model game state, rules, and rendering.

build-indexes

Build a feature's index-database — component/archetype indexes for O(1) lookup. As needed.

build-service-database

Build a feature's service-database — db-bound service factories. If the feature exposes services.

build-ui

Build a feature's ui/ layer — presentation bound to the main-service database. The final, top layer.

build-application

Build an application — a base feature hosting lazily-loaded peer features.

build-feature

Build a complete feature step by step

graph-execute

executes a graph of steps

build-actions

Build a feature's ecs action-database — async orchestration over services and transactions. If the feature has async flows.

build-app-entry

Wire built features into a running application — import peer schemas, lazy-load peers, and mount the root UI.

build-application

Build an application — a base feature hosting lazily-loaded peer features.

build-computed

Build a feature's ecs computed-database — derived observable values.

build-core-database

Build a feature's ecs schema — the core-database (components, resources, archetypes). The first ecs layer.

build-data

Build a feature's data/ layer — data-type namespaces and the State spec. The first, foundational feature phase.

build-feature

Build a complete feature by piping the per-layer build-* skills bottom-up.

build-game

Build a game — an application whose features model game state, rules, and rendering.

build-indexes

Build a feature's ecs index-database — component/archetype indexes for O(1) lookup. As needed.

build-service-database

Build a feature's ecs service-database — db-bound service factories. If the feature exposes services.

build-services

Build a feature's services/ layer — async capability contracts (ports to the outside world). Optional.

build-systems

Build a feature's ecs system-database — the real-time tick loop (systems the scheduler runs each frame). For real-time features only.

build-transactions

Build a feature's ecs transaction-database — atomic mutations over the store.

build-ui

Build a feature's ui/ layer — presentation bound to the ecs database. The final, top layer.

meta-build

Iteratively build an application or game phase-by-phase in clean subagents, reviewing each phase and refining the build-* skills / rules until each is optimal, then summarizing.

review

Review built feature/application output against the @adobe/data feature rules; report whether it is optimal and where any fix belongs. Read-only.

structure

Use when laying out or reasoning about a feature's file/folder structure and layer dependencies.

x-execute

executes an input optionally with validate first

Source text: Undetermined

x-log

logs all named inputs to chat

x-subagent

executes the input within a subagent

x-trace

inserts a /x-log call right after every non log piped function

x-validate

validates nested or piped function calls to determine if output types match all required input types

think

Reflective Thought Composition. Structured thinking pipeline for complex decisions, design evaluation, and deep analysis. Use when quality of reasoning matters more than speed of response.